Datasets:

KenLuo

/

qls

like 0

[ { "role": "user", "content": "Abstract: Background\nHepatic encephalopathy is a disorder of brain function as a result of liver failure or portosystemic shunt or both. Both hepatic encephalopathy (clinically overt) and minimal hepatic encephalopathy (not clinically overt) significantly impair patient’s quality of life and daily functioning, and represent a significant burden on healthcare resources. Probiotics are live micro-organisms, which when administered in adequate amounts, may confer a health benefit on the host.\nObjectives\nTo determine the beneficial and harmful effects of probiotics in any dosage, compared with placebo or no intervention, or with any other treatment for people with any grade of acute or chronic hepatic encephalopathy. This review did not consider the primary prophylaxis of hepatic encephalopathy.\nSearch methods\nWe searched The Cochrane Hepato-Biliary Group Controlled Trials Register, CENTRAL, MEDLINE, Embase, Science Citation Index Expanded, conference proceedings, reference lists of included trials, and the World Health Organization International Clinical Trials Registry Platform until June 2016.\nSelection criteria\nWe included randomised clinical trials that compared probiotics in any dosage with placebo or no intervention, or with any other treatment in people with hepatic encephalopathy.\nData collection and analysis\nWe used standard methodological procedures expected by The Cochrane Collaboration. We conducted random-effects model meta-analysis due to obvious heterogeneity of participants and interventions. We defined a P value of 0.05 or less as significant. We expressed dichotomous outcomes as risk ratio (RR) and continuous outcomes as mean difference (MD) with 95% confidence intervals (CI).\nMain results\nWe included 21 trials with 1420 participants, of these, 14 were new trials. Fourteen trials compared a probiotic with placebo or no treatment, and seven trials compared a probiotic with lactulose. The trials used a variety of probiotics; the most commonly used group of probiotic was VSL#3, a proprietary name for a group of eight probiotics. Duration of administration ranged from 10 days to 180 days. Eight trials declared their funding source, of which six were independently funded and two were industry funded. The remaining 13 trials did not disclose their funding source. We classified 19 of the 21 trials at high risk of bias.\nWe found no effect on all-cause mortality when probiotics were compared with placebo or no treatment (7 trials; 404 participants; RR 0.58, 95% CI 0.23 to 1.44; low-quality evidence). No-recovery (as measured by incomplete resolution of symptoms) was lower for participants treated with probiotic (10 trials; 574 participants; RR 0.67, 95% CI 0.56 to 0.79; moderate-quality evidence). Adverse events were lower for participants treated with probiotic than with no intervention when considering the development of overt hepatic encephalopathy (10 trials; 585 participants; RR 0.29, 95% CI 0.16 to 0.51; low-quality evidence), but effects on hospitalisation and change of/or withdrawal from treatment were uncertain (hospitalisation: 3 trials, 163 participants; RR 0.67, 95% CI 0.11 to 4.00; very low-quality evidence; change of/or withdrawal from treatment: 9 trials, 551 participants; RR 0.70, 95% CI 0.46 to 1.07; very low-quality evidence). Probiotics may slightly improve quality of life compared with no intervention (3 trials; 115 participants; results not meta-analysed; low-quality evidence). Plasma ammonia concentration was lower for participants treated with probiotic (10 trials; 705 participants; MD -8.29 μmol/L, 95% CI -13.17 to -3.41; low-quality evidence). There were no reports of septicaemia attributable to probiotic in any trial.\nWhen probiotics were compared with lactulose, the effects on all-cause mortality were uncertain (2 trials; 200 participants; RR 5.00, 95% CI 0.25 to 102.00; very low-quality evidence); lack of recovery (7 trials; 430 participants; RR 1.01, 95% CI 0.85 to 1.21; very low-quality evidence); adverse events considering the development of overt hepatic encephalopathy (6 trials; 420 participants; RR 1.17, 95% CI 0.63 to 2.17; very low-quality evidence); hospitalisation (1 trial; 80 participants; RR 0.33, 95% CI 0.04 to 3.07; very low-quality evidence); intolerance leading to discontinuation (3 trials; 220 participants; RR 0.35, 95% CI 0.08 to 1.43; very low-quality evidence); change of/or withdrawal from treatment (7 trials; 490 participants; RR 1.27, 95% CI 0.88 to 1.82; very low-quality evidence); quality of life (results not meta-analysed; 1 trial; 69 participants); and plasma ammonia concentration overall (6 trials; 325 participants; MD -2.93 μmol/L, 95% CI -9.36 to 3.50; very low-quality evidence). There were no reports of septicaemia attributable to probiotic in any trial.\nAuthors' conclusions\nThe majority of included trials suffered from a high risk of systematic error (‘bias’) and a high risk of random error (‘play of chance’). Accordingly, we consider the evidence to be of low quality. Compared with placebo or no intervention, probiotics probably improve recovery and may lead to improvements in the development of overt hepatic encephalopathy, quality of life, and plasma ammonia concentrations, but probiotics may lead to little or no difference in mortality. Whether probiotics are better than lactulose for hepatic encephalopathy is uncertain because the quality of the available evidence is very low. High-quality randomised clinical trials with standardised outcome collection and data reporting are needed to further clarify the true efficacy of probiotics.\n\nGiven the provided abstract, please respond to the following query: \"Why the review is important\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "Hepatic encephalopathy is a disorder of brain function as a result of liver failure or portosystemic shunt or both. Both hepatic encephalopathy (clinically overt) and minimal hepatic encephalopathy (not clinically overt) significantly impair patient’s quality of life and daily functioning and represent a significant burden on healthcare resources. Probiotics are live micro-organisms, which when administered in adequate amounts may confer a health benefit on the host. We searched and summarised randomised trials about the benefits and harms of any probiotic in any dosage, compared with placebo or no intervention, or with any other treatment for people with any grade of acute or chronic hepatic encephalopathy." } ]

[ { "role": "user", "content": "Abstract: Background\nIn an effort to improve outcomes of in vitro fertilisation (IVF) cycles, the use of growth hormone (GH) has been considered as adjuvant treatment in ovarian stimulation. Improving the outcomes of IVF is especially important for women with infertility who are considered 'poor responders'. We have compared the outcomes of IVF with adjuvant GH versus no adjuvant treatment in routine use, and specifically in poor responders.\nObjectives\nTo assess the effectiveness and safety of growth hormone as an adjunct to IVF compared to standard IVF for women with infertility\nSearch methods\nWe searched the following databases (to November 2020): Cochrane Gynaecology and Fertility (CGF) Group specialised register, CENTRAL, MEDLINE, Embase, CINAHL, Epistemonikos database and trial registers together with reference checking and contact with study authors and experts in the field to identify additional trials.\nSelection criteria\nWe included all randomised controlled trials (RCTs) of adjuvant GH treatment in IVF compared with no adjuvant treatment for women with infertility. We excluded trials where additional adjuvant treatments were used with GH. We also excluded trials comparing different IVF protocols.\nData collection and analysis\nWe used standard methodological procedures recommended by Cochrane. Two review authors independently performed assessment of trial risk of bias and extraction of relevant data. The primary review outcome was live birth rate. The secondary outcomes were clinical pregnancy rate, oocytes retrieved, embryo transfer, units of gonadotropin used and adverse events, i.e. ectopic pregnancy, multiple pregnancy, ovarian hyperstimulation syndrome (OHSS), congenital anomalies, oedema.\nMain results\nWe included 16 RCTs (1352 women). Two RCTs (80 women) studied GH in routine use, and 14 RCTs (1272 women) studied GH in poor responders. The evidence was low to very low certainty, the main limitations being risk of bias, imprecision and heterogeneity.\nAdjuvant growth hormone compared to no adjuvant: routine use for in vitro fertilisation (IVF)\nThe evidence is very uncertain about the effect of GH on live birth rate per woman randomised for routine use in IVF (odds ratio (OR) 1.32, 95% confidence interval (CI) 0.40 to 4.43; I2 = 0%; 2 trials, 80 participants; very low-certainty evidence). If the chance of live birth without adjuvant GH is assumed to be 15%, the chance of live birth with GH would be between 6% and 43%.\nThere was insufficient evidence to reach a conclusion regarding clinical pregnancy rates per woman randomised, number of women with at least one oocyte retrieved per woman randomised and embryo transfer achieved per woman randomised; reported data were unsuitable for analysis.\nThe evidence is very uncertain about the effect of GH on mean number of oocytes retrieved in normal responders (mean difference (MD) -0.02, 95% CI -0.79 to 0.74; I2 = 0%; 2 trials, 80 participants; very low-certainty evidence).\nThe evidence is very uncertain about the effect of GH on mean units of gonadotropin used in normal responders (MD 13.57, 95% CI -112.88 to 140.01; I2 = 0%; 2 trials, 80 participants; very low-certainty evidence).\nWe are uncertain of the effect of GH on adverse events in normal responders.\nAdjuvant growth hormone compared to no adjuvant: use in poor responders for in vitro fertilisation (IVF)\nThe evidence is very uncertain about the effect of GH on live birth rate per woman randomised for poor responders (OR 1.77, 95% CI 1.17 to 2.70; I2 = 0%; 8 trials, 737 participants; very low-certainty evidence). If the chance of live birth without adjuvant GH is assumed to be 11%, the chance of live birth with GH would be between 13% and 25%. Adjuvant GH results in a slight increase in pregnancy rates in poor responders (OR 1.85, 95% CI 1.35 to 2.53; I2 = 15%; 11 trials, 1033 participants; low-certainty evidence). The results suggest, if the pregnancy rate without adjuvant GH is assumed to be 15%, with GH the pregnancy rate in poor responders would be between 19% and 31%. The evidence suggests that GH results in little to no difference in number of women with at least one oocyte retrieved (OR 5.67, 95% CI 1.54 to 20.83; I2 = 0%; 2 trials, 148 participants; low-certainty evidence). If the chance of retrieving at least one oocyte in poor responders was 81%, with GH the chance is between 87% and 99%. There is a slight increase in mean number of oocytes retrieved with the use of GH for poor responders (MD 1.40, 95% CI 1.16 to 1.64; I2 = 87%; 12 trials, 1153 participants; low-certainty evidence). The evidence is very uncertain about the effect of GH on embryo transfer achieved (OR 2.32, 95% CI 1.08 to 4.96; I2 = 25%; 4 trials, 214 participants; very low-certainty evidence). If the chance of achieving embryo transfer is assumed to be 77%, the chance with GH will be 78% to 94%. Use of GH results in reduction of mean units of gonadotropins used for stimulation in poor responders (MD -1088.19, 95% CI -1203.20 to -973.18; I2 = 91%; 8 trials, 685 participants; low-certainty evidence).\nHigh heterogeneity in the analyses for mean number of oocytes retrieved and units of GH used suggests quite different effects according to differences including in trial protocols (populations, GH dose and schedule), so these results should be interpreted with caution.\nWe are uncertain of the effect of GH on adverse events in poor responders as six of the 14 included trials failed to report this outcome.\nAuthors' conclusions\nThe use of adjuvant GH in IVF treatment protocols has uncertain effect on live birth rates and mean number of oocytes retrieved in normal responders. However, it slightly increases the number of oocytes retrieved and pregnancy rates in poor responders, while there is an uncertain effect on live birth rates in this group. The results however, need to be interpreted with caution, as the included trials were small and few in number, with significant bias and imprecision. Also, the dose and regimen of GH used in trials was variable. Therefore, further research is necessary to fully define the role of GH as adjuvant therapy in IVF.\n\nGiven the provided abstract, please respond to the following query: \"Quality of the evidence\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "The evidence was of low to very low certainty, with the main limitations being poor reporting of study methods, imprecise data and variability among the trials." } ]

[ { "role": "user", "content": "Abstract: Background\nCognitive behavioural therapy (CBT) is an evidence-based treatment for anxiety disorders. Many people have difficulty accessing treatment, due to a variety of obstacles. Researchers have therefore explored the possibility of using the Internet to deliver CBT; it is important to ensure the decision to promote such treatment is grounded in high quality evidence.\nObjectives\nTo assess the effects of therapist-supported Internet CBT (ICBT) on remission of anxiety disorder diagnosis and reduction of anxiety symptoms in adults as compared to waiting list control, unguided CBT, or face-to-face CBT. Effects of treatment on quality of life and patient satisfaction with the intervention were also assessed.\nSearch methods\nWe searched the Cochrane Depression, Anxiety and Neurosis Review Group Specialised Register (CCDANCTR) to 16 March 2015. The CCDANCTR includes relevant randomised controlled trials from MEDLINE, EMBASE, PsycINFO and CENTRAL. We also searched online clinical trial registries and reference lists of included studies. We contacted authors to locate additional trials.\nSelection criteria\nEach identified study was independently assessed for inclusion by two authors. To be included, studies had to be randomised controlled trials of therapist-supported ICBT compared to a waiting list, attention, information, or online discussion group; unguided CBT (that is, self-help); or face-to-face CBT. We included studies that treated adults with an anxiety disorder (panic disorder, agoraphobia, social phobia, post-traumatic stress disorder, acute stress disorder, generalized anxiety disorder, obsessive compulsive disorder, and specific phobia) defined according to the Diagnostic and Statistical Manual of Mental Disorders III, III-R, IV, IV-TR or the International Classification of Disesases 9 or 10.\nData collection and analysis\nTwo authors independently assessed the risk of bias of included studies and judged overall study quality. We used data from intention-to-treat analyses wherever possible. We assessed treatment effect for the dichotomous outcome of clinically important improvement in anxiety using a risk ratio (RR) with 95% confidence interval (CI). For disorder-specific and general anxiety symptom measures and quality of life we assessed continuous scores using standardized mean differences (SMD). We examined statistical heterogeneity using the I2 statistic.\nMain results\nWe screened 1736 citations and selected 38 studies (3214 participants) for inclusion. The studies examined social phobia (11 trials), panic disorder with or without agoraphobia (8 trials), generalized anxiety disorder (5 trials), post-traumatic stress disorder (2 trials), obsessive compulsive disorder (2 trials), and specific phobia (2 trials). Eight remaining studies included a range of anxiety disorder diagnoses. Studies were conducted in Sweden (18 trials), Australia (14 trials), Switzerland (3 trials), the Netherlands (2 trials), and the USA (1 trial) and investigated a variety of ICBT protocols. Three primary comparisons were identified, therapist-supported ICBT versus waiting list control, therapist-supported versus unguided ICBT, and therapist-supported ICBT versus face-to-face CBT.\nLow quality evidence from 11 studies (866 participants) contributed to a pooled risk ratio (RR) of 3.75 (95% CI 2.51 to 5.60; I2 = 50%) for clinically important improvement in anxiety at post-treatment, favouring therapist-supported ICBT over a waiting list, attention, information, or online discussion group only. The SMD for disorder-specific symptoms at post-treatment (28 studies, 2147 participants; SMD -1.06, 95% CI -1.29 to -0.82; I2 = 83%) and general anxiety symptoms at post-treatment (19 studies, 1496 participants; SMD -0.75, 95% CI -0.98 to -0.52; I2 = 78%) favoured therapist-supported ICBT; the quality of the evidence for both outcomes was low.\nOne study compared unguided CBT to therapist-supported ICBT for clinically important improvement in anxiety at post-treatment, showing no difference in outcome between treatments (54 participants; very low quality evidence). At post-treatment there were no clear differences between unguided CBT and therapist-supported ICBT for disorder-specific anxiety symptoms (5 studies, 312 participants; SMD -0.22, 95% CI -0.56 to 0.13; I2 = 58%; very low quality evidence) or general anxiety symptoms (2 studies, 138 participants; SMD 0.28, 95% CI -2.21 to 2.78; I2 = 0%; very low quality evidence).\nCompared to face-to-face CBT, therapist-supported ICBT showed no significant differences in clinically important improvement in anxiety at post-treatment (4 studies, 365 participants; RR 1.09, 95% CI 0.89 to 1.34; I2 = 0%; low quality evidence). There were also no clear differences between face-to-face and therapist supported ICBT for disorder-specific anxiety symptoms at post-treatment (7 studies, 450 participants; SMD 0.06, 95% CI -0.25 to 0.37; I2 = 60%; low quality evidence) or general anxiety symptoms at post-treatment (5 studies, 317 participants; SMD 0.17, 95% CI -0.35 to 0.69; I2 = 78%; low quality evidence).\nOverall, risk of bias in included studies was low or unclear for most domains. However, due to the nature of psychosocial intervention trials, blinding of participants and personnel, and outcome assessment tended to have a high risk of bias. Heterogeneity across a number of the meta-analyses was substantial, some was explained by type of anxiety disorder or may be meta-analytic measurement artefact due to combining many assessment measures. Adverse events were rarely reported.\nAuthors' conclusions\nTherapist-supported ICBT appears to be an efficacious treatment for anxiety in adults. The evidence comparing therapist-supported ICBT to waiting list, attention, information, or online discussion group only control was low to moderate quality, the evidence comparing therapist-supported ICBT to unguided ICBT was very low quality, and comparisons of therapist-supported ICBT to face-to-face CBT were low quality. Further research is needed to better define and measure any potential harms resulting from treatment. These findings suggest that therapist-supported ICBT is more efficacious than a waiting list, attention, information, or online discussion group only control, and that there may not be a significant difference in outcome between unguided CBT and therapist-supported ICBT; however, this latter finding must be interpreted with caution due to imprecision. The evidence suggests that therapist-supported ICBT may not be significantly different from face-to-face CBT in reducing anxiety. Future research should explore heterogeneity among studies which is reducing the quality of the evidence body, involve equivalence trials comparing ICBT and face-to-face CBT, examine the importance of the role of the therapist in ICBT, and include effectiveness trials of ICBT in real-world settings. A timely update to this review is needed given the fast pace of this area of research.\n\nGiven the provided abstract, please respond to the following query: \"What does the evidence from the review tell us?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "ICBT with therapist support was significantly more effective than no treatment (waiting list) at improving anxiety and reducing symptoms. The quality of the evidence was low to moderate.\nThere was no significant difference in the effectiveness of ICBT with therapist support and unguided CBT, though the quality of the evidence was very low. Patient satisfaction was generally reported to be higher with therapist-supported ICBT, however patient satisfaction was not formally assessed.\nICBT with therapist support may not differ in effectiveness as compared to face-to-face CBT. The quality of the evidence was low.\nThere was a low risk of bias in the included studies, except for blinding of participants, personnel, and outcome assessment. Adverse events were rarely reported in the studies." } ]

[ { "role": "user", "content": "Abstract: Background\nThe dystrophinopathies include Duchenne muscular dystrophy (DMD), Becker muscular dystrophy (BMD), and X-linked dilated cardiomyopathy (XLDCM). In recent years, co-ordinated multidisciplinary management for these diseases has improved the quality of care, with early corticosteroid use prolonging independent ambulation, and the routine use of non-invasive ventilation signficantly increasing survival. The next target to improve outcomes is optimising treatments to delay the onset or slow the progression of cardiac involvement and so prolong survival further.\nObjectives\nTo assess the effects of interventions for preventing or treating cardiac involvement in DMD, BMD, and XLDCM, using measures of change in cardiac function over six months.\nSearch methods\nOn 16 October 2017 we searched the Cochrane Neuromuscular Specialised Register, CENTRAL, MEDLINE and Embase, and on 12 December 2017, we searched two clinical trials registries. We also searched conference proceedings and bibliographies.\nSelection criteria\nWe considered only randomised controlled trials (RCTs), quasi-RCTs and randomised cross-over trials for inclusion. In the Discussion, we reviewed open studies, longitudinal observational studies and individual case reports but only discussed studies that adequately described the diagnosis, intervention, pretreatment, and post-treatment states and in which follow-up lasted for at least six months.\nData collection and analysis\nTwo authors independently reviewed the titles and abstracts identified from the search and performed data extraction. All three authors assessed risk of bias independently, compared results, and decided which trials met the inclusion criteria. They assessed the certainty of evidence using GRADE criteria.\nMain results\nWe included five studies (N = 205) in the review; four studies included participants with DMD only, and one study included participants with DMD or BMD. All studied different interventions, and meta-analysis was not possible. We found no studies for XLDCM. None of the trials reported cardiac function as improved or stable cardiac versus deteriorated.\nThe randomised first part of a two-part study of perindopril (N = 28) versus placebo (N = 27) in boys with DMD with normal heart function at baseline showed no difference in the number of participants with a left ventricular ejection fraction (LVEF%) of less than 45% after three years of therapy (n = 1 in each group; risk ratio (RR) 1.04, 95% confidence interval (CI) 0.07 to 15.77). This result is uncertain because of study limitations, indirectness and imprecision. In a non-randomised follow-up study, after 10 years, more participants who had received placebo from the beginning had reduced LVEF% (less than 45%). Adverse event rates were similar between the placebo and treatment groups (low-certainty evidence).\nA study comparing treatment with lisinopril versus losartan in 23 boys newly diagnosed with Duchenne cardiomyopathy showed that after 12 months, both were equally effective in preserving or improving LVEF% (lisinopril 54.6% (standard deviation (SD) 5.19), losartan 55.2% (SD 7.19); mean difference (MD) −0.60% CI −6.67 to 5.47: N = 16). The certainty of evidence was very low because of very serious imprecision and study limitations (risk of bias). Two participants in the losartan group were withdrawn due to adverse events: one participant developed an allergic reaction, and a second exceeded the safety standard with a fall in ejection fraction greater than 10%. Authors reported no other adverse events related to the medication (N = 22; very low-certainty evidence).\nA study comparing idebenone versus placebo in 21 boys with DMD showed little or no difference in mean change in cardiac function between the two groups from baseline to 12 months; for fractional shortening the mean change was 1.4% (SD 4.1) in the idebenone group and 1.6% (SD 2.6) in the placebo group (MD −0.20%, 95% CI −3.07 to 2.67, N = 21), and for ejection fraction the mean change was −1.9% (SD 9.8) in the idebenone group and 0.4% (SD 5.5) in the placebo group (MD −2.30%, 95% CI −9.18 to 4.58, N = 21). The certainty of evidence was very low because of study limitations and very serious imprecision. Reported adverse events were similar between the treatment and placebo groups (low-certainty evidence).\nA multicentre controlled study added eplerenone or placebo to 42 patients with DMD with early cardiomyopathy but preserved left ventricular function already established on ACEI or ARB therapy. Results showed that eplerenone slowed the rate of decline of magnetic resonance (MR)-assessed left ventricular circumferential strain at 12 months (eplerenone group median 1.0%, interquartile range (IQR) 0.3 to −2.2; placebo group median 2.2%, IQR 1.3 to −3.1%; P = 0.020). The median decline in LVEF over the same period was also less in the eplerenone group (−1.8%, IQR −2.9 to 6.0) than in the placebo group (−3.7%, IQR −10.8 to 1.0; P = 0.032). We downgraded the certainty of evidence to very low for study limitations and serious imprecision. Serious adverse events were reported in two patients given placebo but none in the treatment group (very low-certainty evidence).\nA randomised placebo-controlled study of subcutaneous growth hormone in 16 participants with DMD or BMD showed an increase in left ventricular mass after three months' treatment but no significant improvement in cardiac function. The evidence was of very low certainty due to imprecision, indirectness, and study limitations. There were no clinically significant adverse events (very low-certainty evidence).\nSome studies were at risk of bias, and all were small. Therefore, although there is some evidence from non-randomised data to support the prophylactic use of perindopril for cardioprotection ahead of detectable cardiomyopathy, and for lisinopril or losartan plus eplerenone once cardiomyopathy is detectable, this must be considered of very low certainty. Findings from non-randomised studies, some of which have been long term, have led to the use of these drugs in daily clinical practice.\nAuthors' conclusions\nBased on the available evidence from RCTs, early treatment with ACE inhibitors or ARBs may be comparably beneficial for people with a dystrophinopathy; however, the certainty of evidence is very low. Very low-certainty evidence indicates that adding eplerenone might give additional benefit when early cardiomyopathy is detected. No clinically meaningful effect was seen for growth hormone or idebenone, although the certainty of the evidence is also very low.\n\nGiven the provided abstract, please respond to the following query: \"Study characteristics\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "Cochrane Review authors collected all relevant studies to answer their review question. They searched for trials looking to prevent or treat heart complications in people with DMD, BMD or XLDCM. They limited the review to trials that randomly assign participants to one treatment or another, which usually provide the best evidence. They identified five small trials, with a total of 205 participants.\n- A three-year study of perindopril versus placebo (an inactive pill) to prevent heart complications in 57 boys with DMD. The randomised trial was followed by two years of open treatment, then a follow-up study of 10 years when all children received perindopril.\n- A one-year study of lisinopril versus losartan in 23 patients with DMD and newly diagnosed heart complications.\n- A one-year study of idebenone versus placebo in 21 boys with DMD, which the manufacturer funded.\n- A one-year study of eplerenone versus placebo in 42 patients with DMD who already had heart complications, which the manufacturer partly funded.\n- A three-month study of growth hormone versus placebo in 10 patients with DMD or BMD." } ]

[ { "role": "user", "content": "Abstract: Background\nOlder people taking multiple medications represent a large and growing proportion of the population. Managing multiple medications can be challenging, and this is especially the case for older people, who have higher rates of comorbidity and physical and cognitive impairment than younger adults. Good medication-taking ability and medication adherence are necessary to ensure safe and effective use of medications.\nObjectives\nTo evaluate the effectiveness of interventions designed to improve medication-taking ability and/or medication adherence in older community-dwelling adults prescribed multiple long-term medications.\nSearch methods\nWe searched MEDLINE, Embase, Cochrane Central Register of Controlled Trials (CENTRAL), PsycINFO, CINAHL Plus, and International Pharmaceutical Abstracts from inception until June 2019. We also searched grey literature, online trial registries, and reference lists of included studies.\nSelection criteria\nWe included randomised controlled trials (RCTs), quasi-RCTs, and cluster-RCTs. Eligible studies tested interventions aimed at improving medication-taking ability and/or medication adherence among people aged ≥ 65 years (or of mean/median age > 65 years), living in the community or being discharged from hospital back into the community, and taking four or more regular prescription medications (or with group mean/median of more than four medications). Interventions targeting carers of older people who met these criteria were also included.\nData collection and analysis\nTwo review authors independently reviewed abstracts and full texts of eligible studies, extracted data, and assessed risk of bias of included studies. We conducted meta-analyses when possible and used a random-effects model to yield summary estimates of effect, risk ratios (RRs) for dichotomous outcomes, and mean differences (MDs) or standardised mean differences (SMDs) for continuous outcomes, along with 95% confidence intervals (CIs). Narrative synthesis was performed when meta-analysis was not possible. We assessed overall certainty of evidence for each outcome using Grades of Recommendation, Assessment, Development and Evaluation (GRADE). Primary outcomes were medication-taking ability and medication adherence. Secondary outcomes included health-related quality of life (HRQoL), emergency department (ED)/hospital admissions, and mortality.\nMain results\nWe identified 50 studies (14,269 participants) comprising 40 RCTs, six cluster-RCTs, and four quasi-RCTs. All included studies evaluated interventions versus usual care; six studies also reported a comparison between two interventions as part of a three-arm RCT design.\nInterventions were grouped on the basis of their educational and/or behavioural components: 14 involved educational components only, 7 used behavioural strategies only, and 29 provided mixed educational and behavioural interventions. Overall, our confidence in results regarding the effectiveness of interventions was low to very low due to a high degree of heterogeneity of included studies and high or unclear risk of bias across multiple domains in most studies.\nFive studies evaluated interventions for improving medication-taking ability, and 48 evaluated interventions for improving medication adherence (three studies evaluated both outcomes).\nNo studies involved educational or behavioural interventions alone for improving medication-taking ability. Low-quality evidence from five studies, each using a different measure of medication-taking ability, meant that we were unable to determine the effects of mixed interventions on medication-taking ability.\nLow-quality evidence suggests that behavioural only interventions (RR 1.22, 95% CI 1.07 to 1.38; 4 studies) and mixed interventions (RR 1.22, 95% CI 1.08 to 1.37; 12 studies) may increase the proportions of people who are adherent compared with usual care. We could not include in the meta-analysis results from two studies involving mixed interventions: one had a positive effect on adherence, and the other had little or no effect. Very low-quality evidence means that we are uncertain of the effects of educational only interventions (5 studies) on the proportions of people who are adherent.\nLow-quality evidence suggests that educational only interventions (SMD 0.16, 95% CI -0.12 to 0.43; 5 studies) and mixed interventions (SMD 0.47, 95% CI -0.08 to 1.02; 7 studies) may have little or no impact on medication adherence assessed through continuous measures of adherence. We excluded 10 studies (4 educational only and 6 mixed interventions) from the meta-analysis including four studies with unclear or no available results. Very low-quality evidence means that we are uncertain of the effects of behavioural only interventions (3 studies) on medication adherence when assessed through continuous outcomes.\nLow-quality evidence suggests that mixed interventions may reduce the number of ED/hospital admissions (RR 0.67, 95% CI 0.50 to 0.90; 11 studies) compared with usual care, although results from six further studies that we were unable to include in meta-analyses indicate that the intervention may have a smaller, or even no, effect on these outcomes. Similarly, low-quality evidence suggests that mixed interventions may lead to little or no change in HRQoL (7 studies), and very low-quality evidence means that we are uncertain of the effects on mortality (RR 0.93, 95% CI 0.67 to 1.30; 7 studies).\nModerate-quality evidence shows that educational interventions alone probably have little or no effect on HRQoL (6 studies) or on ED/hospital admissions (4 studies) when compared with usual care. Very low-quality evidence means that we are uncertain of the effects of behavioural interventions on HRQoL (1 study) or on ED/hospital admissions (2 studies). We identified no studies evaluating effects of educational or behavioural interventions alone on mortality.\nSix studies reported a comparison between two interventions; however due to the limited number of studies assessing the same types of interventions and comparisons, we are unable to draw firm conclusions for any outcomes.\nAuthors' conclusions\nBehavioural only or mixed educational and behavioural interventions may improve the proportion of people who satisfactorily adhere to their prescribed medications, but we are uncertain of the effects of educational only interventions. No type of intervention was found to improve adherence when it was measured as a continuous variable, with educational only and mixed interventions having little or no impact and evidence of insufficient quality to determine the effects of behavioural only interventions. We were unable to determine the impact of interventions on medication-taking ability. The quality of evidence for these findings is low due to heterogeneity and methodological limitations of studies included in the review. Further well-designed RCTs are needed to investigate the effects of interventions for improving medication-taking ability and medication adherence in older adults prescribed multiple medications.\n\nGiven the provided abstract, please respond to the following query: \"Main results\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "We identified 50 studies, involving 14,269 participants. All studies tested interventions versus usual care, with six studies also comparing two different types of interventions.\nFourteen studies tested educational interventions whereby people received education regarding their medications or a health professional reviewed their medications. Seven studies tested behavioural interventions such as changing dosing times, re-packaging medications into multi-compartment pill boxes to make medication regimens easier to take, or sending text message adherence reminders. Twenty-nine studies tested mixed educational and behavioural interventions.\nThe studies identified were very different in terms of what interventions people received, where interventions were delivered, and how and when people's medication-taking ability or adherence was measured. Due to these differences and problems with how the trials were conducted, the quality of the evidence was considered low or very low overall.\nLow-quality evidence means that the impact of mixed interventions on medication-taking ability could not be determined, and no studies were identified that assessed educational only or behavioural only interventions for improving medication-taking ability.\nLow-quality evidence suggests that compared with usual care, behavioural only and mixed interventions may improve the proportions of people who satisfactorily adhere to their prescribed medication, but very low-quality evidence means that the effects of educational only interventions are uncertain. Low- and very low-quality evidence means that no interventions were found to be effective in improving medication adherence when assessed by continuous measures such as percentage of medications consumed.\nLow-quality evidence also suggests that mixed interventions may reduce the number of emergency department visits or hospital admissions, and may lead to little or no change in health-related quality of life (HRQoL). Moderate-quality evidence shows that educational interventions alone probably have little or no effect on HRQoL or on emergency department or hospital admissions. The effects of behavioural interventions alone on HRQoL or emergency department or hospital admissions are uncertain because of very low-quality evidence. We are uncertain of the effects of behavioural, educational, or mixed interventions on mortality.\nStudies comparing one type of intervention with another were limited in number, and we are unable to draw firm conclusions for any key outcomes." } ]

[ { "role": "user", "content": "Abstract: Background\nUreteroscopy combined with laser stone fragmentation and basketing is a common approach for managing renal and ureteral stones. This procedure is associated with some degree of ureteral trauma. Ureteral trauma may lead to swelling, ureteral obstruction, and flank pain and may require subsequent interventions such as hospital admission or secondary ureteral stent placement. To prevent such issues, urologists often place temporary ureteral stents prophylactically, but the value of doing so remains unclear.\nObjectives\nTo assess the effects of postoperative ureteral stent placement after uncomplicated ureteroscopy.\nSearch methods\nWe performed a comprehensive search using multiple databases (the Cochrane Library, MEDLINE, Embase, Scopus, Google Scholar, and Web of Science), trials registries, other sources of grey literature, and conference proceedings, up to 01 February 2019. We applied no restrictions on publication language or status.\nSelection criteria\nWe included trials in which researchers randomised participants undergoing uncomplicated ureteroscopy to placement of a ureteral stent versus no ureteral stent.\nData collection and analysis\nTwo review authors independently classified studies and abstracted data from the included studies. We performed statistical analyses using a random-effects model. We rated the certainty of evidence (CoE) according to the GRADE approach.\nMain results\nPrimary outcomes\nStenting may slightly reduce the number of unplanned return visits (16 trials with 1970 participants; very low CoE), but we are very uncertain of this finding.\nPain on the day of surgery as measured on a visual analogue scale (scale 0 to 10; higher values reflect more pain) is probably similar (mean difference (MD) 0.32 higher, 95% confidence interval (CI) 0.13 lower to 0.78 higher; 4 trials with 346 participants; moderate CoE). Pain on postoperative days 1 to 3 may show little to no difference (standardised mean difference (SMD) 0.25 higher, 95% CI 0.32 lower to 0.82 higher; 8 trials with 683 participants; low CoE). On postoperative days 4 to 30, stented participants may experience more pain (8 trials with 903 participants; very low CoE), but we are very uncertain of this finding.\nStenting may result in little to no difference in the need for secondary interventions (risk ratio (RR) 1.15, 95% CI 0.39 to 3.33; 10 studies with 1435 participants; low CoE); this corresponds to three more interventions per 1000 participants (95% CI 13 fewer to 48 more).\nSecondary outcomes\nStenting may reduce the need for narcotics (7 trials with 830 participants; very low CoE), but we are very uncertain of this finding.\nRates of urinary tract infection (UTI) up to 90 days are probably not substantially different (RR 0.94, 95% CI 0.59 to 1.51; 10 trials with 1207 participants; moderate CoE); this corresponds to three fewer infections per 1000 participants (95% CI 23 fewer to 29 more).\nUreteral stricture rates up to 90 days may be slightly reduced (14 trials with 1625 participants; very low CoE), but we are very uncertain of this finding.\nRates of hospital admission may be slightly reduced (RR 0.70, 95% CI 0.32 to 1.55; 13 studies with 1647 participants; low CoE). This corresponds to 15 fewer admissions per 1000 participants (95% CI 33 fewer to 27 more).\nAuthors' conclusions\nFindings of this review illustrate the trade-offs of risks and benefits faced by urologists and their patients when it comes to decision-making about stent placement after uncomplicated ureteroscopy for stone disease. We noted that both desirable and undesirable effects were small in absolute terms, with findings based mostly on low and very low CoE. The main issues reducing our confidence in research findings were study limitations (mostly risk of performance and detection bias) and imprecision. We were unable to conduct any of the preplanned subgroup analyses, in particular those based on stone size, stone location, and use of ureteral dilation, which may be important effect modifiers. Given the importance of this question, higher-quality and sufficiently large trials are needed to better inform decision-making.\n\nGiven the provided abstract, please respond to the following query: \"Background\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "Urologists use small scopes and other tools to find, break up, and remove stones. Afterwards, swelling and blockage of the ureter can cause discomfort. To prevent that from happening, urologists often leave a temporary stent. It is unclear whether a stent makes things better or worse." } ]

[ { "role": "user", "content": "Abstract: Background\nHumour-based interventions are defined as any intervention that promotes health and wellness by stimulating a playful discovery, expression, or appreciation of the absurdity or incongruity of life's situations. Humour-based interventions can be implemented in different settings, including hospitals, nursing homes and day care centres. They have been posed as an adjunct to usual care for people with schizophrenia, but a summary of the evidence is lacking.\nObjectives\nTo examine the effects of humour-based interventions as an add-on intervention to standard care for people with schizophrenia.\nSearch methods\nOn 31 July 2019 and 10 February 2021 we searched the Cochrane Schizophrenia Group's study-based register of trials, which is based on CENTRAL, CINAHL, ClinicalTrials.Gov, Embase, ISRCTN, MEDLINE, PsycINFO, PubMed, and WHO ICTRP.\nSelection criteria\nWe included all randomised controlled trials comparing humour-based interventions with active controls, other psychological interventions, or standard care for people with schizophrenia. We excluded studies fulfilling our prespecified selection criteria but without useable data from further quantitative synthesis.\nData collection and analysis\nTwo review authors independently inspected citations, selected studies, extracted data and appraised study quality, following the guidance from the Cochrane Handbook for Systematic Reviews of Interventions. For binary outcomes we calculated risk ratios (RRs) and their 95% confidence intervals (CIs). For continuous outcomes we calculated the mean differences (MDs) and their 95% CIs. We assessed risks of bias for included studies and created summary of findings tables using the GRADE approach.\nMain results\nWe included three studies in this review for qualitative synthesis, although one study did not report any relevant outcomes. We therefore include two studies (n = 96) in our quantitative synthesis. No data were available on the following prespecified primary outcomes: clinically-important change in general mental state, clinically-important change in negative symptoms, clinically-important change in overall quality of life, and adverse effects. As compared with active control, humour-based interventions may not improve the average endpoint score of a general mental state scale (Positive and Negative Syndrome Scale (PANSS) total score: MD −1.70, 95% CI −17.01 to 13.61; 1 study, 30 participants; very low certainty of evidence); positive symptoms (PANSS positive symptom score: MD 0.00, 95% CI −2.58 to 2.58; 1 study, 30 participants; low certainty of evidence), negative symptoms (PANSS negative symptom score: MD −0.70, 95% CI −4.22 to 2.82; 1 study, 30 participants; very low certainty of evidence) and anxiety (State-Trait Anxiety Inventory (STAI): MD −2.60, 95% CI −5.76 to 0.56; 1 study, 30 participants; low certainty of evidence). Due to the small sample size, we remain uncertain about the effect of humour-based interventions on leaving the study early as compared with active control (no event, 1 study, 30 participants; very low certainty of evidence). On the other hand, humour-based interventions may reduce depressive symptoms (Beck Depression Inventory (BDI): MD −6.20, 95% CI −12.08 to −0.32; 1 study, 30 participants; low certainty of evidence). Compared with standard care, humour-based interventions may not improve  depressive symptoms (BDI second edition: MD 0.80, 95% CI −2.64 to 4.24; 1 study, 59 participants; low certainty of evidence). We are uncertain about the effect of humour-based interventions on leaving the study early for any reason compared with standard care (risk ratio 0.38, 95% CI 0.08 to 1.80; 1 study, 66 participants; very low certainty of evidence).\nAuthors' conclusions\nWe are currently uncertain whether the evidence supports the use of humour-based interventions in people with schizophrenia. Future research with rigorous and transparent methodology investigating clinically important outcomes is warranted.\n\nGiven the provided abstract, please respond to the following query: \"Searching for evidence\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "We ran an electronic search in February 2021 for trials that randomised people with schizophrenia to receive humour-based interventions in addition to usual care, or to receive usual care only, another psychological intervention or a control condition. We found eight records and checked them for suitability to include in our review." } ]

[ { "role": "user", "content": "Abstract: Background\nVasomotor symptoms, such as hot flushes and night sweats, are very common during the menopausal transition. Hormone therapy has traditionally been used as a highly effective treatment, but concerns about increased risk of some chronic diseases have markedly increased the interest of women in alternative treatments. Some of the most popular of these treatments are foods or supplements enriched with phytoestrogens—plant-derived chemicals that have estrogenic action.\nObjectives\nTo assess the efficacy, safety and acceptability of food products, extracts and dietary supplements containing high levels of phytoestrogens when compared with no treatment, placebo or hormone therapy for the amelioration of vasomotor menopausal symptoms (such as hot flushes and night sweats) in perimenopausal and postmenopausal women.\nSearch methods\nSearches targeted the following electronic databases: the Cochrane Menstrual Disorders and Subfertility Group Specialised Register of randomised trials (29 July 2013), the Cochrane Register of Controlled Trials (CENTRAL; 29 July 2013), MEDLINE (inception to 29 July 2013), EMBASE (inception to 29 July 2013), AMED (1985 to 29 July 2013), PsycINFO (inception to 29 July 2013) and CINAHL (inception to 29 July 2013). Attempts were made to access grey literature by sending letters to pharmaceutical companies and performing searches of ongoing trial registers. Reference lists of included trials were also searched.\nSelection criteria\nStudies were included if they were randomised, included perimenopausal or postmenopausal participants with vasomotor symptoms (hot flushes or night sweats), lasted at least 12 weeks and provided interventions such as foods or supplements with high levels of phytoestrogens (not combined with other herbal treatments). Trials that included women who had breast cancer or a history of breast cancer were excluded.\nData collection and analysis\nSelection of trials, extraction of data and assessment of quality were undertaken by at least two review authors. Most trials were too dissimilar for their results to be combined in a meta-analysis, so these findings are provided in narrative 'Summary of results' tables. Studies were grouped into broad categories: dietary soy, soy extracts, red clover extracts, genistein extracts and other types of phytoestrogens. Five trials used Promensil, a red clover extract; results of these trials were combined in a meta-analysis, and summary effect measures were calculated.\nMain results\nA total of 43 randomised controlled trials (4,364 participants) were included in this review. Very few trials provided data suitable for inclusion in a meta-analysis. Among the five trials that yielded data assessing the daily frequency of hot flushes suitable for pooling, no significant difference overall was noted in the incidence of hot flushes between participants taking Promensil (a red clover extract) and those given placebo (mean difference (MD) -0.93, 95% confidence interval (CI) -1.95 to 0.10, I2 = 31%). No evidence indicated a difference in percentage reduction in hot flushes in two trials between Promensil and placebo (MD 20.15, 95% CI -12.08 to 52.38, I2 = 82%). Four trials that were not combined in meta-analyses suggested that extracts with high (> 30 mg/d) levels of genistein consistently reduced the frequency of hot flushes. Individual results from the remaining trials were compared in broad subgroups such as dietary soy, soy extracts and other types of phytoestrogens that could not be combined. Some of these trials found that phytoestrogen treatments alleviated the frequency and severity of hot flushes and night sweats when compared with placebo, but many trials were small and were determined to be at high risk of bias. A strong placebo effect was noted in most trials, with a reduction in frequency ranging from 1% to 59% with placebo. No indication suggested that discrepant results were due to the amount of isoflavone in the active treatment arm, the severity of vasomotor symptoms or trial quality factors. Also, no evidence indicated that these treatments caused oestrogenic stimulation of the endometrium or the vagina or other adverse effects when used for up to two years.\nAuthors' conclusions\nNo conclusive evidence shows that phytoestrogen supplements effectively reduce the frequency or severity of hot flushes and night sweats in perimenopausal or postmenopausal women, although benefits derived from concentrates of genistein should be further investigated.\n\nGiven the provided abstract, please respond to the following query: \"Quality of the evidence\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "Many of the trials in this review were small, of short duration and of poor quality, and the types of phytoestrogens used varied substantially." } ]

[ { "role": "user", "content": "Abstract: Background\nThe current paradigm for cardiovascular disease (CVD) emphasises absolute risk assessment to guide treatment decisions in primary prevention. Although the derivation and validation of multivariable risk assessment tools, or CVD risk scores, have attracted considerable attention, their effect on clinical outcomes is uncertain.\nObjectives\nTo assess the effects of evaluating and providing CVD risk scores in adults without prevalent CVD on cardiovascular outcomes, risk factor levels, preventive medication prescribing, and health behaviours.\nSearch methods\nWe searched the Cochrane Central Register of Controlled Trials (CENTRAL) in the Cochrane Library (2016, Issue 2), MEDLINE Ovid (1946 to March week 1 2016), Embase (embase.com) (1974 to 15 March 2016), and Conference Proceedings Citation Index-Science (CPCI-S) (1990 to 15 March 2016). We imposed no language restrictions. We searched clinical trial registers in March 2016 and handsearched reference lists of primary studies to identify additional reports.\nSelection criteria\nWe included randomised and quasi-randomised trials comparing the systematic provision of CVD risk scores by a clinician, healthcare professional, or healthcare system compared with usual care (i.e. no systematic provision of CVD risk scores) in adults without CVD.\nData collection and analysis\nThree review authors independently selected studies, extracted data, and evaluated study quality. We used the Cochrane 'Risk of bias' tool to assess study limitations. The primary outcomes were: CVD events, change in CVD risk factor levels (total cholesterol, systolic blood pressure, and multivariable CVD risk), and adverse events. Secondary outcomes included: lipid-lowering and antihypertensive medication prescribing in higher-risk people. We calculated risk ratios (RR) for dichotomous data and mean differences (MD) or standardised mean differences (SMD) for continuous data using 95% confidence intervals. We used a fixed-effects model when heterogeneity (I²) was at least 50% and a random-effects model for substantial heterogeneity (I² > 50%). We evaluated the quality of evidence using the GRADE framework.\nMain results\nWe identified 41 randomised controlled trials (RCTs) involving 194,035 participants from 6422 reports. We assessed studies as having high or unclear risk of bias across multiple domains. Low-quality evidence evidence suggests that providing CVD risk scores may have little or no effect on CVD events compared with usual care (5.4% versus 5.3%; RR 1.01, 95% confidence interval (CI) 0.95 to 1.08; I² = 25%; 3 trials, N = 99,070). Providing CVD risk scores may reduce CVD risk factor levels by a small amount compared with usual care. Providing CVD risk scores reduced total cholesterol (MD −0.10 mmol/L, 95% CI −0.20 to 0.00; I² = 94%; 12 trials, N = 20,437, low-quality evidence), systolic blood pressure (MD −2.77 mmHg, 95% CI −4.16 to −1.38; I² = 93%; 16 trials, N = 32,954, low-quality evidence), and multivariable CVD risk (SMD −0.21, 95% CI −0.39 to −0.02; I² = 94%; 9 trials, N = 9549, low-quality evidence). Providing CVD risk scores may reduce adverse events compared with usual care, but results were imprecise (1.9% versus 2.7%; RR 0.72, 95% CI 0.49 to 1.04; I² = 0%; 4 trials, N = 4630, low-quality evidence). Compared with usual care, providing CVD risk scores may increase new or intensified lipid-lowering medications (15.7% versus 10.7%; RR 1.47, 95% CI 1.15 to 1.87; I² = 40%; 11 trials, N = 14,175, low-quality evidence) and increase new or increased antihypertensive medications (17.2% versus 11.4%; RR 1.51, 95% CI 1.08 to 2.11; I² = 53%; 8 trials, N = 13,255, low-quality evidence).\nAuthors' conclusions\nThere is uncertainty whether current strategies for providing CVD risk scores affect CVD events. Providing CVD risk scores may slightly reduce CVD risk factor levels and may increase preventive medication prescribing in higher-risk people without evidence of harm. There were multiple study limitations in the identified studies and substantial heterogeneity in the interventions, outcomes, and analyses, so readers should interpret results with caution. New models for implementing and evaluating CVD risk scores in adequately powered studies are needed to define the role of applying CVD risk scores in primary CVD prevention.\n\nGiven the provided abstract, please respond to the following query: \"Background\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "Cardiovascular disease (CVD) is a group of conditions that includes heart disease and stroke. CVD prevention guidelines emphasise the use of risk scores, equations that use clinical variables to estimate the chance of a first heart attack or stroke, to guide treatment decisions in the general population. While there has been much attention to developing different types of CVD risk scores, there is uncertainty about the effects of providing a CVD risk score in clinical practice.\nThe aim of this systematic review was to assess the effects of evaluating CVD risk scores in adults without a history of heart disease or stroke on cardiovascular outcomes, risk factor levels, preventive medication prescribing, and health behaviours." } ]

[ { "role": "user", "content": "Abstract: Background\nSurgical resection for early-stage non-small cell lung cancer (NSCLC) offers the best chance of cure, but it is associated with a risk of postoperative pulmonary complications. It is unclear if preoperative exercise training, and the potential resultant improvement in exercise capacity, may improve postoperative outcomes. This review updates our initial 2017 systematic review.\nObjectives\n1. To evaluate the benefits and harm of preoperative exercise training on postoperative outcomes, such as the risk of developing a postoperative pulmonary complication and the postoperative duration of intercostal catheter, in adults scheduled to undergo lung resection for NSCLC.\n2. To determine the effect on length of hospital stay (and costs associated with postoperative hospital stay), fatigue, dyspnoea, exercise capacity, lung function and postoperative mortality.\nSearch methods\nWe used standard, extensive Cochrane search methods. The latest search date was from 28 November 2016 to 23 November 2021.\nSelection criteria\nWe included randomised controlled trials (RCTs) in which study participants who were scheduled to undergo lung resection for NSCLC were allocated to receive either preoperative exercise training or no exercise training.\nData collection and analysis\nWe used standard Cochrane methods. Our primary outcomes were 1. risk of developing a postoperative pulmonary complication; 2. postoperative duration of intercostal catheter and 3. safety. Our secondary outcomes were 1. postoperative length of hospital stay; 2. postintervention fatigue; 3. postintervention dyspnoea; 4. postintervention and postoperative exercise capacity; 5. postintervention lung function and 6. postoperative mortality. We used GRADE to assess the certainty of evidence for each outcome.\nMain results\nAlong with the five RCTs included in the original version, we identified an additional five RCTs, resulting in 10 RCTs involving 636 participants. Preoperative exercise training results in a large reduction in the risk of developing a postoperative pulmonary complication compared to no preoperative exercise training (risk ratio (RR) 0.45, 95% CI 0.33 to 0.61; I2 = 0%; 9 studies, 573 participants; high-certainty evidence). The evidence is very uncertain about its effect on postoperative intercostal catheter duration (MD −2.07 days, 95% CI −4.64 to 0.49; I2 = 77%, 3 studies, 111 participants; very low-certainty evidence). Preoperative exercise training is likely safe as studies reported no adverse events. Preoperative exercise training likely results in a reduction in postoperative length of hospital stay (MD −2.24 days, 95% CI −3.64 to −0.85; I2 = 85%; 9 studies, 573 participants; moderate-certainty evidence). Preoperative exercise training likely increases postintervention exercise capacity measured by peak oxygen consumption (MD 3.36 mL/kg/minute, 95% CI 2.70 to 4.02; I2 = 0%; 2 studies, 191 participants; moderate-certainty evidence); but the evidence is very uncertain about its effect on postintervention exercise capacity measured by the 6-minute walk distance (MD 29.55 m, 95% CI 12.05 to 47.04; I2 = 90%; 6 studies, 474 participants; very low-certainty evidence). Preoperative exercise training may result in little to no effect on postintervention lung function (forced expiratory volume in one second: MD 5.87% predicted, 95% CI 4.46 to 7.28; I2 = 0%; 4 studies, 197 participants; low-certainty evidence).\nAuthors' conclusions\nPreoperative exercise training results in a large reduction in the risk of developing a postoperative pulmonary complication compared to no preoperative exercise training for people with NSCLC. It may also reduce postoperative length of hospital stay, and improve exercise capacity and lung function in people undergoing lung resection for NSCLC. The findings of this review should be interpreted with caution due to risk of bias. Research investigating the cost-effectiveness and long-term outcomes associated with preoperative exercise training in NSCLC is warranted.\n\nGiven the provided abstract, please respond to the following query: \"Review questions\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "What is the benefit of exercise undertaken before surgery for lung cancer and how safe is exercise at this time?" } ]

[ { "role": "user", "content": "Abstract: Background\nAcne is an inflammatory disorder with a high global burden. It is common in adolescents and primarily affects sebaceous gland-rich areas. The clinical benefit of the topical acne treatments azelaic acid, salicylic acid, nicotinamide, sulphur, zinc, and alpha-hydroxy acid is unclear.\nObjectives\nTo assess the effects of topical treatments (azelaic acid, salicylic acid, nicotinamide, zinc, alpha-hydroxy acid, and sulphur) for acne.\nSearch methods\nWe searched the following databases up to May 2019: the Cochrane Skin Group Specialised Register, CENTRAL, MEDLINE, Embase, and LILACS. We also searched five trials registers.\nSelection criteria\nClinical randomised controlled trials of the six topical treatments compared with other topical treatments, placebo, or no treatment in people with acne.\nData collection and analysis\nWe used standard methodological procedures expected by Cochrane. Key outcomes included participants' global self-assessment of acne improvement (PGA), withdrawal for any reason, minor adverse events (assessed as total number of participants who experienced at least one minor adverse event), and quality of life.\nMain results\nWe included 49 trials (3880 reported participants) set in clinics, hospitals, research centres, and university settings in Europe, Asia, and the USA.\nThe vast majority of participants had mild to moderate acne, were aged between 12 to 30 years (range: 10 to 45 years), and were female. Treatment lasted over eight weeks in 59% of the studies. Study duration ranged from three months to three years.\nWe assessed 26 studies as being at high risk of bias in at least one domain, but most domains were at low or unclear risk of bias.\nWe grouped outcome assessment into short-term (less than or equal to 4 weeks), medium-term (from 5 to 8 weeks), and long-term treatment (more than 8 weeks). The following results were measured at the end of treatment, which was mainly long-term for the PGA outcome and mixed length (medium-term mainly) for minor adverse events.\nAzelaic acid\nIn terms of treatment response (PGA), azelaic acid is probably less effective than benzoyl peroxide (risk ratio (RR) 0.82, 95% confidence interval (CI) 0.72 to 0.95; 1 study, 351 participants), but there is probably little or no difference when comparing azelaic acid to tretinoin (RR 0.94, 95% CI 0.78 to 1.14; 1 study, 289 participants) (both moderate-quality evidence). There may be little or no difference in PGA when comparing azelaic acid to clindamycin (RR 1.13, 95% CI 0.92 to 1.38; 1 study, 229 participants; low-quality evidence), but we are uncertain whether there is a difference between azelaic acid and adapalene (1 study, 55 participants; very low-quality evidence).\nLow-quality evidence indicates there may be no differences in rates of withdrawal for any reason when comparing azelaic acid with benzoyl peroxide (RR 0.88, 95% CI 0.60 to 1.29; 1 study, 351 participants), clindamycin (RR 1.30, 95% CI 0.48 to 3.56; 2 studies, 329 participants), or tretinoin (RR 0.66, 95% CI 0.29 to 1.47; 2 studies, 309 participants), but we are uncertain whether there is a difference between azelaic acid and adapalene (1 study, 55 participants; very low-quality evidence).\nIn terms of total minor adverse events, we are uncertain if there is a difference between azelaic acid compared to adapalene (1 study; 55 participants) or benzoyl peroxide (1 study, 30 participants) (both very low-quality evidence). There may be no difference when comparing azelaic acid to clindamycin (RR 1.50, 95% CI 0.67 to 3.35; 1 study, 100 participants; low-quality evidence). Total minor adverse events were not reported in the comparison of azelaic acid versus tretinoin, but individual application site reactions were reported, such as scaling.\nSalicylic acid\nFor PGA, there may be little or no difference between salicylic acid and tretinoin (RR 1.00, 95% CI 0.92 to 1.09; 1 study, 46 participants; low-quality evidence); we are not certain whether there is a difference between salicylic acid and pyruvic acid (1 study, 86 participants; very low-quality evidence); and PGA was not measured in the comparison of salicylic acid versus benzoyl peroxide.\nThere may be no difference between groups in withdrawals when comparing salicylic acid and pyruvic acid (RR 0.89, 95% CI 0.53 to 1.50; 1 study, 86 participants); when salicylic acid was compared to tretinoin, neither group had withdrawals (both based on low-quality evidence (2 studies, 74 participants)). We are uncertain whether there is a difference in withdrawals between salicylic acid and benzoyl peroxide (1 study, 41 participants; very low-quality evidence).\nFor total minor adverse events, we are uncertain if there is any difference between salicylic acid and benzoyl peroxide (1 study, 41 participants) or tretinoin (2 studies, 74 participants) (both very low-quality evidence). This outcome was not reported for salicylic acid versus pyruvic acid, but individual application site reactions were reported, such as scaling and redness.\nNicotinamide\nFour studies evaluated nicotinamide against clindamycin or erythromycin, but none measured PGA. Low-quality evidence showed there may be no difference in withdrawals between nicotinamide and clindamycin (RR 1.12, 95% CI 0.49 to 2.60; 3 studies, 216 participants) or erythromycin (RR 1.40, 95% CI 0.46 to 4.22; 1 study, 158 participants), or in total minor adverse events between nicotinamide and clindamycin (RR 1.20, 95% CI 0.73 to 1.99; 3 studies, 216 participants; low-quality evidence). Total minor adverse events were not reported in the nicotinamide versus erythromycin comparison.\nAlpha-hydroxy (fruit) acid\nThere may be no difference in PGA when comparing glycolic acid peel to salicylic-mandelic acid peel (RR 1.06, 95% CI 0.88 to 1.26; 1 study, 40 participants; low-quality evidence), and we are uncertain if there is a difference in total minor adverse events due to very low-quality evidence (1 study, 44 participants). Neither group had withdrawals (2 studies, 84 participants; low-quality evidence).\nAuthors' conclusions\nCompared to benzoyl peroxide, azelaic acid probably leads to a worse treatment response, measured using PGA. When compared to tretinoin, azelaic acid probably makes little or no difference to treatment response. For other comparisons and outcomes the quality of evidence was low or very low.\nRisk of bias and imprecision limit our confidence in the evidence. We encourage the comparison of more methodologically robust head-to-head trials against commonly used active drugs.\n\nGiven the provided abstract, please respond to the following query: \"Study characteristics\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "We included 49 trials (3880 reported participants). At least one study assessed each eligible treatment.\nMost trial participants were female, aged between 12 and 30 years, with mild to moderate acne. Nearly 60% of the trials treated participants for longer than eight weeks. Study duration ranged from three months to three years.\nNine trials reported pharmaceutical support. The studies were mainly conducted in Europe, Asia, and the USA, in clinics, hospitals, research centres, and universities." } ]

[ { "role": "user", "content": "Abstract: Background\nChronic venous insufficiency (CVI) is a progressive and common disease that affects the superficial and deep venous systems of the lower limbs. CVI is characterised by valvular incompetence, reflux, venous obstruction or a combination of these symptoms, with consequent distal venous hypertension. Clinical manifestations of CVI include oedema, pain, skin changes, ulcerations and dilated skin veins in the lower limbs. It places a large financial burden on health systems. There is a wide variety of treatment options for CVI, ranging from surgery and medication to compression and physiotherapy. Balneotherapy (treatments involving water) may be a relatively cheap and efficient way to deliver physiotherapy to people with CVI. This is an update of a review first published in 2019.\nObjectives\nTo assess the effectiveness and safety of balneotherapy for the treatment of people with chronic venous insufficiency.\nSearch methods\nWe used standard, extensive Cochrane search methods. The latest search date was 28 June 2022.\nSelection criteria\nWe included randomised and quasi-randomised controlled trials comparing balneotherapy to no treatment or other types of treatment for CVI. We also included studies that used a combination of treatments.\nData collection and analysis\nWe used standard Cochrane methods. Our primary outcomes were 1. disease severity, 2. health-related quality of life (HRQoL) and 3. adverse effects. Our secondary outcomes were 1. pain, 2. oedema, 3. leg ulcer incidence and 4. skin pigmentation changes. We used GRADE to assess the certainty of evidence for each outcome.\nMain results\nWe included nine randomised controlled trials involving 1126 participants with CVI. Seven studies evaluated balneotherapy versus no treatment, one study evaluated balneotherapy versus a phlebotonic drug (melilotus officinalis), and one study evaluated balneotherapy versus dryland exercises. We downgraded our certainty in the evidence due to a lack of blinding of participants and investigators, participant-reported outcomes and imprecision.\nBalneotherapy versus no treatment\nBalneotherapy compared to no treatment probably results in slightly improved disease severity signs and symptoms scores as assessed by the Venous Clinical Severity Score (VCSS; mean difference (MD) −1.75, 95% confidence interval (CI) −3.02 to −0.49; 3 studies, 671 participants; moderate-certainty evidence).\nBalneotherapy compared to no treatment may improve HRQoL as assessed by the Chronic Venous Insufficiency Quality of Life Questionnaire 2 (CIVIQ2) at three months, but we are very uncertain about the results (MD −10.46, 95% CI −19.21 to −1.71; 2 studies, 153 participants; very low-certainty evidence). The intervention may improve HRQoL at 12 months (MD −4.48, 95% CI −8.61 to −0.36; 2 studies, 417 participants; low-certainty evidence). It is unclear if the intervention has an effect at six months (MD −2.99, 95% CI −6.53 to 0.56; 2 studies, 436 participants; low-certainty evidence) or nine months (MD −6.40, 95% CI −13.84 to 1.04; 1 study, 59 participants; very low-certainty evidence).\nBalneotherapy compared with no treatment may have little or no effect on the occurrence of adverse effects. The main adverse effects were thromboembolic events (odds radio (OR) 0.35, 95% CI 0.09 to 1.42; 3 studies, 584 participants; low-certainty evidence), erysipelas (OR 2.58, 95% CI 0.65 to 10.22; 2 studies, 519 participants; low-certainty evidence) and palpitations (OR 0.33, 95% CI 0.01 to 8.52; 1 study, 59 participants; low-certainty evidence). No studies reported any serious adverse effects.\nBalneotherapy compared with no treatment may improve pain scores slightly at three months (MD −1.12, 95% CI −1.35 to −0.88; 2 studies, 354 participants; low-certainty evidence); and six months (MD −1.02, 95% CI −1.25 to −0.78; 2 studies, 352 participants; low-certainty evidence).\nBalneotherapy compared with no treatment may have little or no effect on oedema (measured by leg circumference) at 24 days to three months, but we are very uncertain about the results (standardised mean difference (SMD) 0.32 cm, 95% CI −0.70 to 1.34; 3 studies, 369 participants; very low-certainty evidence).\nBalneotherapy compared with no treatment may have little or no effect on the incidence of leg ulcers at 12 months, but we are very uncertain about the results (OR 1.06, 95% CI 0.27 to 4.14; 2 studies, 449 participants; very low-certainty evidence).\nBalneotherapy compared with no treatment may slightly reduce skin pigmentation changes as measured by the pigmentation index at 12 months (MD −3.60, 95% CI −5.95 to −1.25; 1 study, 59 participants; low-certainty evidence).\nBalneotherapy versus melilotus officinalis\nFor the comparison balneotherapy versus a phlebotonic drug (melilotus officinalis), there was little or no difference in pain symptoms (OR 0.29, 95% CI 0.03 to 2.87; 1 study, 35 participants; very low-certainty evidence) or oedema (OR 0.21, 95% CI 0.02 to 2.27; 1 study, 35 participants; very low-certainty evidence), but we are very uncertain about the results. The study reported no other outcomes of interest.\nBalneotherapy versus dryland exercise\nFor the comparison balneotherapy versus dryland exercise, evidence from one study showed that balneotherapy may improve HRQoL as assessed by the Varicose Vein Symptom Questionnaire (VVSymQ), but we are very uncertain about the results (MD −3.00, 95% CI −3.80 to −2.20; 34 participants, very low-certainty evidence). Balneotherapy compared with dryland exercises may reduce oedema (leg volume) after five sessions of treatment (right leg: MD −840.70, 95% CI −1053.26 to −628.14; left leg: MD −767.50, 95% CI −910.07 to −624.93; 1 study, 34 participants, low-certainty evidence). The study reported no other outcomes of interest.\nAuthors' conclusions\nFor the comparison balneotherapy versus no treatment, we identified moderate-certainty evidence that the intervention improves disease severity signs and symptoms scores slightly, low-certainty evidence that it improves pain and skin pigmentation changes, and very low-certainty evidence that it improves HRQoL. Balneotherapy compared with no treatment made little or no difference to adverse effects, oedema or incidence of leg ulcers. Evidence comparing balneotherapy with other interventions was very limited. To ensure adequate comparison between trials, future trials should standardise measurements of outcomes (e.g. disease severity signs and symptoms score, HRQoL, pain and oedema) and follow-up time points.\n\nGiven the provided abstract, please respond to the following query: \"How up to date is this evidence?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "This is an update of a previous Cochrane Review. The evidence is current to June 2022." } ]

[ { "role": "user", "content": "Abstract: Background\nStudies consistently show a relationship between social disadvantage and low birthweight. Many countries have programmes offering special assistance to women thought to be at risk for giving birth to a low birthweight infant. These programmes, collectively referred to in this review as additional social support, may include emotional support, which gives a person a feeling of being loved and cared for, tangible/instrumental support, in the form of direct assistance/home visits, and informational support, through the provision of advice, guidance and counselling. The programmes may be delivered by multidisciplinary teams of health professionals, specially trained lay workers, or a combination of lay and professional workers. This is an update of a review first published in 2003 and updated in 2010.\nObjectives\nThe primary objective was to assess the effects of programmes offering additional social support (emotional, instrumental/tangible and informational) compared with routine care, for pregnant women believed to be at high risk for giving birth to babies that are either preterm (less than 37 weeks' gestation) or weigh less than 2500 g, or both, at birth. Secondary objectives were to determine whether the effectiveness of support was mediated by timing of onset (early versus later in pregnancy) or type of provider (healthcare professional or lay person).\nSearch methods\nFor this update, we searched Cochrane Pregnancy and Childbirth’s Trials Register, ClinicalTrials.gov, the WHO International Clinical Trials Registry Platform (ICTRP) on 5 February 2018, and reference lists of retrieved studies.\nSelection criteria\nRandomised trials of additional social support during at-risk pregnancy by either a professional (social worker, midwife, or nurse) or specially trained lay person, compared to routine care. We defined additional social support as some form of emotional support (e.g. caring, empathy, trust), tangible/instrumental support (e.g. transportation to clinic appointments, home visits complemented with phone calls, help with household responsibilities) or informational support (advice and counselling about nutrition, rest, stress management, use of alcohol/recreational drugs).\nData collection and analysis\nTwo review authors independently assessed studies for inclusion and risk of bias, extracted data and checked them for accuracy. We assessed the quality of the evidence using the GRADE approach.\nMain results\nThis updated review includes a total of 25 studies, with outcome data for 11,246 mothers and babies enrolled in 21 studies. We assessed the overall risk of bias of included studies to be low or unclear, mainly because of limited reporting or uncertainty in how randomisation was generated or concealed (which led us to downgrade the quality of most outcomes to moderate), and the impracticability of blinding participants.\nWhen compared with routine care, programmes offering additional social support for at-risk pregnant women may slightly reduce the number of babies born with a birthweight less than 2500 g from 127 per 1000 to 120 per 1000 (risk ratio (RR) 0.94, 95% confidence interval (CI) 0.86 to 1.04; 16 studies, n = 11,770; moderate-quality evidence), and the number of babies born with a gestational age less than 37 weeks at birth from 128 per 1000 to 117 per 1000 (RR 0.92, 95% CI 0.84 to 1.01, 14 studies, n = 12,282; moderate-quality evidence), though the confidence intervals for the pooled effect for both of these outcomes just crossed the line of no effect, suggesting any effect is not large. There may be little or no difference between interventions for stillbirth/neonatal death (RR 1.11, 95% CI 0.88 to 1.41; 15 studies, n = 12,091; low-quality evidence). Secondary outcomes of moderate quality suggested that there is probably a reduction in caesarean section (from 215 per 1000 to 194 per 1000; RR 0.90, 95% CI 0.83 to 0.97; 15 studies, n = 9550), a reduction in the number of antenatal hospital admissions per participant (RR 0.78, 95% CI 0.68 to 0.91; 4 studies; n = 787), and a reduction in the mean number of hospitalisation episodes (mean difference −0.05, 95% CI −0.06 to −0.04; 1 study, n = 1525) in the social support group, compared to the controls.\nPostnatal depression and women's satisfaction were reported in different ways in the studies that considered these outcomes and so we could not include data in a meta-analysis. In one study postnatal depression appeared to be slightly lower in the support group in women who screened positively on the Edinbugh Postnatal Depression Scale at eight to 12 weeks postnatally (RR 0.74, 95% CI 0.55 to 1.01; 1 study, n = 1008; moderate-quality evidence). In another study, again postnatal depression appeared to be slightly lower in the support group and this was a self-report measure assessed at six weeks postnatally (RR 0.85, 95% CI 0.69 to 1.05; 1 study, n = 458; low-quality evidence). A higher proportion of women in one study reported that their prenatal care was very helpful in the supported group (RR 1.17, 95% CI 1.05 to 1.30; 1 study, n = 223; moderate-quality evidence), although in another study results were similar. Another study assessed satisfaction with prenatal care as being \"not good\" in 51 of 945 in the additional support group, compared with 45 of 942 in the usual care group.\nNo studies considered long-term morbidity for the infant. No single outcome was reported in all studies. Subgroup analysis demonstrated consistency of effect when the support was provided by a healthcare professional or a trained lay worker.\nThe descriptions of the additional social support were generally consistent across all studies and included emotional support, tangible support such as home visits, and informational support.\nAuthors' conclusions\nPregnant women need the support of caring family members, friends, and health professionals. While programmes that offer additional social support during pregnancy are unlikely to have a large impact on the proportion of low birthweight babies or birth before 37 weeks' gestation and no impact on stillbirth or neonatal death, they may be helpful in reducing the likelihood of caesarean birth and antenatal hospital admission.\n\nGiven the provided abstract, please respond to the following query: \"Why is this important?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "Many countries offer programmes giving special assistance to women thought to be at risk of giving birth to low birthweight babies. These programmes can include emotional support, direct assistance such as home visits, transportation to clinic appointments or help with household responsibilities, and informational support such as guidance and counselling. We set out to assess the effects of programmes offering additional social support compared with routine care, for pregnant women believed to be at high risk of giving birth to low birthweight babies." } ]

[ { "role": "user", "content": "Abstract: Background\nHip fractures are a major healthcare problem, presenting a huge challenge and burden to individuals and healthcare systems. The number of hip fractures globally is rising rapidly. The majority of hip fractures are treated surgically. This review evaluates evidence for types of arthroplasty: hemiarthroplasties (HAs), which replace part of the hip joint; and total hip arthroplasties (THAs), which replace all of it.\nObjectives\nTo determine the effects of different designs, articulations, and fixation techniques of arthroplasties for treating hip fractures in adults.\nSearch methods\nWe searched CENTRAL, MEDLINE, Embase, seven other databases and one trials register in July 2020.\nSelection criteria\nWe included randomised controlled trials (RCTs) and quasi-RCTs comparing different arthroplasties for treating fragility intracapsular hip fractures in older adults. We included THAs and HAs inserted with or without cement, and comparisons between different articulations, sizes, and types of prostheses. We excluded studies of people with specific pathologies other than osteoporosis and with hip fractures resulting from high-energy trauma.\nData collection and analysis\nWe used standard methodological procedures expected by Cochrane. We collected data for seven outcomes: activities of daily living, functional status, health-related quality of life, mobility (all early: within four months of surgery), early mortality and at 12 months after surgery, delirium, and unplanned return to theatre at the end of follow-up.\nMain results\nWe included 58 studies (50 RCTs, 8 quasi-RCTs) with 10,654 participants with 10,662 fractures. All studies reported intracapsular fractures, except one study of extracapsular fractures. The mean age of participants in the studies ranged from 63 years to 87 years, and 71% were women.\nWe report here the findings of three comparisons that represent the most substantial body of evidence in the review. Other comparisons were also reported, but with many fewer participants.\nAll studies had unclear risks of bias in at least one domain and were at high risk of detection bias. We downgraded the certainty of many outcomes for imprecision, and for risks of bias where sensitivity analysis indicated that bias sometimes influenced the size or direction of the effect estimate.\nHA: cemented versus uncemented (17 studies, 3644 participants)\nThere was moderate-certainty evidence of a benefit with cemented HA consistent with clinically small to large differences in health-related quality of life (HRQoL) (standardised mean difference (SMD) 0.20, 95% CI 0.07 to 0.34; 3 studies, 1122 participants), and reduction in the risk of mortality at 12 months (RR 0.86, 95% CI 0.78 to 0.96; 15 studies, 3727 participants). We found moderate-certainty evidence of little or no difference in performance of activities of daily living (ADL) (SMD -0.03, 95% CI -0.21 to 0.16; 4 studies, 1275 participants), and independent mobility (RR 1.04, 95% CI 0.95 to 1.14; 3 studies, 980 participants). We found low-certainty evidence of little or no difference in delirium (RR 1.06, 95% CI 0.55 to 2.06; 2 studies, 800 participants), early mortality (RR 0.95, 95% CI 0.80 to 1.13; 12 studies, 3136 participants) or unplanned return to theatre (RR 0.70, 95% CI 0.45 to 1.10; 6 studies, 2336 participants). For functional status, there was very low-certainty evidence showing no clinically important differences.\nThe risks of most adverse events were similar. However, cemented HAs led to less periprosthetic fractures intraoperatively (RR 0.20, 95% CI 0.08 to 0.46; 7 studies, 1669 participants) and postoperatively (RR 0.29, 95% CI 0.14 to 0.57; 6 studies, 2819 participants), but had a higher risk of pulmonary embolus (RR 3.56, 95% CI 1.26 to 10.11, 6 studies, 2499 participants).\nBipolar HA versus unipolar HA (13 studies, 1499 participants)\nWe found low-certainty evidence of little or no difference between bipolar and unipolar HAs in early mortality (RR 0.94, 95% CI 0.54 to 1.64; 4 studies, 573 participants) and 12-month mortality (RR 1.17, 95% CI 0.89 to 1.53; 8 studies, 839 participants). We are unsure of the effect for delirium, HRQoL, and unplanned return to theatre, which all indicated little or no difference between articulation, because the certainty of the evidence was very low. No studies reported on early ADL, functional status and mobility.\nThe overall risk of adverse events was similar. The absolute risk of dislocation was low (approximately 1.6%) and there was no evidence of any difference between treatments.\nTHA versus HA (17 studies, 3232 participants)\nThe difference in the risk of mortality at 12 months was consistent with clinically relevant benefits and harms (RR 1.00, 95% CI 0.83 to 1.22; 11 studies, 2667 participants; moderate-certainty evidence). There was no evidence of a difference in unplanned return to theatre, but this effect estimate includes clinically relevant benefits of THA (RR 0.63, 95% CI 0.37 to 1.07, favours THA; 10 studies, 2594 participants; low-certainty evidence). We found low-certainty evidence of little or no difference between THA and HA in delirium (RR 1.41, 95% CI 0.60 to 3.33; 2 studies, 357 participants), and mobility (MD -0.40, 95% CI -0.96 to 0.16, favours THA; 1 study, 83 participants). We are unsure of the effect for early functional status, ADL, HRQoL, and mortality, which indicated little or no difference between interventions, because the certainty of the evidence was very low.\nThe overall risks of adverse events were similar. There was an increased risk of dislocation with THA (RR 1.96, 95% CI 1.17 to 3.27; 12 studies, 2719 participants) and no evidence of a difference in deep infection.\nAuthors' conclusions\nFor people undergoing HA for intracapsular hip fracture, it is likely that a cemented prosthesis will yield an improved global outcome, particularly in terms of HRQoL and mortality. There is no evidence to suggest a bipolar HA is superior to a unipolar prosthesis. Any benefit of THA compared with hemiarthroplasty is likely to be small and not clinically appreciable. We encourage researchers to focus on alternative implants in current clinical practice, such as dual-mobility bearings, for which there is limited available evidence.\n\nGiven the provided abstract, please respond to the following query: \"Background\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "A hip fracture is a break at the top of the leg bone. These types of breaks are common in older adults whose bones may be fragile because of a condition called osteoporosis. One method of treatment is to replace the broken hip with an artifical one. This can be done using a hemiarthroplasty (HA), which replaces part of the hip joint (the ball part of the joint). These replacements can be unipolar (a single artificial joint), or bipolar (with an additional joint within the HA). Alternatively, surgery may replace the whole hip joint, which also includes the socket in which the ball of the hip joint sits - this a total hip arthroplasty (THA). Both of these artificial joints can be fixed in place with or without bone cement." } ]

[ { "role": "user", "content": "Abstract: Background\nDysmenorrhoea is a common gynaecological problem consisting of painful cramps accompanying menstruation, which in the absence of any underlying abnormality is known as primary dysmenorrhoea. Research has shown that women with dysmenorrhoea have high levels of prostaglandins, hormones known to cause cramping abdominal pain. Nonsteroidal anti-inflammatory drugs (NSAIDs) are drugs that act by blocking prostaglandin production. They inhibit the action of cyclooxygenase (COX), an enzyme responsible for the formation of prostaglandins. The COX enzyme exists in two forms, COX-1 and COX-2. Traditional NSAIDs are considered 'non-selective' because they inhibit both COX-1 and COX-2 enzymes. More selective NSAIDs that solely target COX-2 enzymes (COX-2-specific inhibitors) were launched in 1999 with the aim of reducing side effects commonly reported in association with NSAIDs, such as indigestion, headaches and drowsiness.\nObjectives\nTo determine the effectiveness and safety of NSAIDs in the treatment of primary dysmenorrhoea.\nSearch methods\nWe searched the following databases in January 2015: Cochrane Menstrual Disorders and Subfertility Group Specialised Register, Cochrane Central Register of Controlled Trials (CENTRAL, November 2014 issue), MEDLINE, EMBASE and Web of Science. We also searched clinical trials registers (ClinicalTrials.gov and ICTRP). We checked the abstracts of major scientific meetings and the reference lists of relevant articles.\nSelection criteria\nAll randomised controlled trial (RCT) comparisons of NSAIDs versus placebo, other NSAIDs or paracetamol, when used to treat primary dysmenorrhoea.\nData collection and analysis\nTwo review authors independently selected the studies, assessed their risk of bias and extracted data, calculating odds ratios (ORs) for dichotomous outcomes and mean differences for continuous outcomes, with 95% confidence intervals (CIs). We used inverse variance methods to combine data. We assessed the overall quality of the evidence using GRADE methods.\nMain results\nWe included 80 randomised controlled trials (5820 women). They compared 20 different NSAIDs (18 non-selective and two COX-2-specific) versus placebo, paracetamol or each other.\nNSAIDs versus placebo\nAmong women with primary dysmenorrhoea, NSAIDs were more effective for pain relief than placebo (OR 4.37, 95% CI 3.76 to 5.09; 35 RCTs, I2 = 53%, low quality evidence). This suggests that if 18% of women taking placebo achieve moderate or excellent pain relief, between 45% and 53% taking NSAIDs will do so.\nHowever, NSAIDs were associated with more adverse effects (overall adverse effects: OR 1.29, 95% CI 1.11 to 1.51, 25 RCTs, I2 = 0%, low quality evidence; gastrointestinal adverse effects: OR 1.58, 95% CI 1.12 to 2.23, 14 RCTs, I2 = 30%; neurological adverse effects: OR 2.74, 95% CI 1.66 to 4.53, seven RCTs, I2 = 0%, low quality evidence). The evidence suggests that if 10% of women taking placebo experience side effects, between 11% and 14% of women taking NSAIDs will do so.\nNSAIDs versus other NSAIDs\nWhen NSAIDs were compared with each other there was little evidence of the superiority of any individual NSAID for either pain relief or safety. However, the available evidence had little power to detect such differences, as most individual comparisons were based on very few small trials.\nNon-selective NSAIDs versus COX-2-specific selectors\nOnly two of the included studies utilised COX-2-specific inhibitors (etoricoxib and celecoxib). There was no evidence that COX-2-specific inhibitors were more effective or tolerable for the treatment of dysmenorrhoea than traditional NSAIDs; however data were very scanty.\nNSAIDs versus paracetamol\nNSAIDs appeared to be more effective for pain relief than paracetamol (OR 1.89, 95% CI 1.05 to 3.43, three RCTs, I2 = 0%, low quality evidence). There was no evidence of a difference with regard to adverse effects, though data were very scanty.\nMost of the studies were commercially funded (59%); a further 31% failed to state their source of funding.\nAuthors' conclusions\nNSAIDs appear to be a very effective treatment for dysmenorrhoea, though women using them need to be aware of the substantial risk of adverse effects. There is insufficient evidence to determine which (if any) individual NSAID is the safest and most effective for the treatment of dysmenorrhoea. We rated the quality of the evidence as low for most comparisons, mainly due to poor reporting of study methods.\n\nGiven the provided abstract, please respond to the following query: \"Background\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "Nearly three-quarters of women suffer from period pain or menstrual cramps (dysmenorrhoea). Research has shown that women with severe period pain have high levels of prostaglandins, hormones known to cause cramping abdominal pain. NSAIDs are drugs which act by blocking prostaglandin production. NSAIDs include the common painkillers aspirin, naproxen, ibuprofen and mefenamic acid. Researchers in The Cochrane Collaboration reviewed the evidence about the safety and effectiveness of NSAIDs for period pain. The evidence is current to January 2015." } ]

[ { "role": "user", "content": "Abstract: Background\nAlthough delirium is typically an acute reversible cognitive impairment, its presence is associated with devastating impact on both short-term and long-term outcomes for critically ill patients. Advances in our understanding of the negative impact of delirium on patient outcomes have prompted trials evaluating multiple pharmacological interventions. However, considerable uncertainty surrounds the relative benefits and safety of available pharmacological interventions for this population.\nObjectives\nPrimary objective\n1. To assess the effects of pharmacological interventions for treatment of delirium on duration of delirium in critically ill adults with confirmed or documented high risk of delirium\nSecondary objectives\nTo assess the following:\n1. effects of pharmacological interventions on delirium-free and coma-free days; days with coma; delirium relapse; duration of mechanical ventilation; intensive care unit (ICU) and hospital length of stay; mortality; and long-term outcomes (e.g. cognitive; discharge disposition; health-related quality of life); and\n2. the safety of such treatments for critically ill adult patients.\nSearch methods\nWe searched the following databases from their inception date to 21 March 2019: Ovid MEDLINE®, Ovid MEDLINE® In-Process & Other Non-Indexed Citations, Embase Classic+Embase, and PsycINFO using the Ovid platform. We also searched the Cochrane Library on Wiley, the International Prospective Register of Systematic Reviews (PROSPERO) (http://www.crd.york.ac.uk/PROSPERO/), the Cumulative Index to Nursing and Allied Health Literature (CINAHL), and Web of Science. We performed a grey literature search of relevant databases and websites using the resources listed in Grey Matters developed by the Canadian Agency for Drugs and Technologies in Health (CADTH). We also searched trial registries and abstracts from annual scientific critical care and delirium society meetings.\nSelection criteria\nWe sought randomized controlled trials (RCTs), including quasi-RCTs, of any pharmacological (drug) for treatment of delirium in critically ill adults. The drug intervention was to be compared to another active drug treatment, placebo, or a non-pharmacological intervention (e.g. mobilization). We did not apply any restrictions in terms of drug class, dose, route of administration, or duration of delirium or drug exposure. We defined critically ill patients as those treated in an ICU of any specialty (e.g. burn, cardiac, medical, surgical, trauma) or high-dependency unit.\nData collection and analysis\nTwo review authors independently identified studies from the search results; four review authors (in pairs) performed data extraction and assessed risk of bias independently. We performed data synthesis through pairwise meta-analysis and network meta-analysis (NMA). Our hypothetical network structure was designed to be analysed at the drug class level and illustrated a network diagram of 'nodes' (i.e. drug classes) and 'edges' (i.e. comparisons between different drug classes from existing trials), thus describing a treatment network of all possible comparisons between drug classes. We assessed the quality of the body of evidence according to GRADE, as very low, low, moderate, or high.\nMain results\nWe screened 7674 citations, from which 14 trials with 1844 participants met our inclusion criteria. Ten RCTs were placebo-controlled, and four reported comparisons of different drugs. Drugs examined in these trials were the following: antipsychotics (n = 10), alpha2 agonists (n = 3; all dexmedetomidine), statins (n = 2), opioids (n = 1; morphine), serotonin antagonists (n = 1; ondansetron), and cholinesterase (CHE) inhibitors (n = 1; rivastigmine). Only one of these trials consistently used non-pharmacological interventions that are known to improve patient outcomes in both intervention and control groups.\nEleven studies (n = 1153 participants) contributed to analysis of the primary outcome. Results of the NMA showed that the intervention with the smallest ratio of means (RoM) (i.e. most preferred) compared with placebo was the alpha2 agonist dexmedetomidine (0.58; 95% credible interval (CrI) 0.26 to 1.27; surface under the cumulative ranking curve (SUCRA) 0.895; moderate-quality evidence). In order of descending SUCRA values (best to worst), the next best interventions were atypical antipsychotics (RoM 0.80, 95% CrI 0.50 to 1.11; SUCRA 0.738; moderate-quality evidence), opioids (RoM 0.88, 95% CrI 0.37 to 2.01; SUCRA 0.578; very-low quality evidence), and typical antipsychotics (RoM 0.96, 95% CrI 0.64 to1.36; SUCRA 0.468; high-quality evidence).\nThe NMAs of multiple secondary outcomes revealed that only the alpha2 agonist dexmedetomidine was associated with a shorter duration of mechanical ventilation (RoM 0.55, 95% CrI 0.34 to 0.89; moderate-quality evidence), and the CHE inhibitor rivastigmine was associated with a longer ICU stay (RoM 2.19, 95% CrI 1.47 to 3.27; moderate-quality evidence). Adverse events often were not reported in these trials or, when reported, were rare; pair-wise analysis of QTc prolongation in seven studies did not show significant differences between antipsychotics, ondansetron, dexmedetomidine, and placebo.\nAuthors' conclusions\nWe identified trials of varying quality that examined six different drug classes for treatment of delirium in critically ill adults. We found evidence that the alpha2 agonist dexmedetomidine may shorten delirium duration, although this small effect (compared with placebo) was seen in pairwise analyses based on a single study and was not seen in the NMA results. Alpha2 agonists also ranked best for duration of mechanical ventilation and length of ICU stay, whereas the CHE inhibitor rivastigmine was associated with longer ICU stay. We found no evidence of a difference between placebo and any drug in terms of delirium-free and coma-free days, days with coma, physical restraint use, length of stay, long-term cognitive outcomes, or mortality. No studies reported delirium relapse, resolution of symptoms, or quality of life. The ten ongoing studies and the six studies awaiting classification that we identified, once published and assessed, may alter the conclusions of the review.\n\nGiven the provided abstract, please respond to the following query: \"Quality of the evidence\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "Most of the included studies were small but of good design. Nine of the 14 studies were considered to have low risk of bias." } ]

[ { "role": "user", "content": "Abstract: Background\nSupportive interventions such as serving meals in a dining room environment or the use of assistants to feed patients are frequently recommended for the management of nutritionally vulnerable groups. Such interventions are included in many policy and guideline documents and have implications for staff time but may incur additional costs, yet there appears to be a lack of evidence for their efficacy.\nObjectives\nTo assess the effects of supportive interventions for enhancing dietary intake in malnourished or nutritionally at-risk adults.\nSearch methods\nWe identified publications from comprehensive searches of the Cochrane Library, MEDLINE, Embase, AMED, British Nursing Index, CINAHL, SCOPUS, ISI Web of Science databases, scrutiny of the reference lists of included trials and related systematic reviews and handsearching the abstracts of relevant meetings. The date of the last search for all databases was 31 March 2013. Additional searches of CENTRAL, MEDLINE, ClinicalTrials.gov and WHO ICTRP were undertaken to September 2016. The date of the last search for these databases was 14 September 2016.\nSelection criteria\nRandomised controlled trials of supportive interventions given with the aim of enhancing dietary intake in nutritionally vulnerable adults compared with usual care.\nData collection and analysis\nThree review authors and for the final search, the editor, selected trials from titles and abstracts and independently assessed eligibility of selected trials. Two review authors independently extracted data and assessed risk of bias, as well as evaluating overall quality of the evidence utilising the GRADE instrument, and then agreed as they entered data into the review. The likelihood of clinical heterogeneity amongst trials was judged to be high as trials were in populations with widely different clinical backgrounds, conducted in different healthcare settings and despite some grouping of similar interventions, involved interventions that varied considerably. We were only able, therefore, to conduct meta-analyses for the outcome measures, 'all-cause mortality', 'hospitalisation' and 'nutritional status (weight change)'.\nMain results\nForty-one trials (10,681 participants) met the inclusion criteria. Trials were grouped according to similar interventions (changes to organisation of nutritional care (N = 13; 3456 participants), changes to the feeding environment (N = 5; 351 participants), modification of meal profile or pattern (N = 12; 649 participants), additional supplementation of meals (N = 10; 6022 participants) and home meal delivery systems (N = 1; 203 participants). Follow-up ranged from ‘duration of hospital stay’ to 12 months.\nThe overall quality of evidence was moderate to very low, with the majority of trials judged to be at an unclear risk of bias in several risk of bias domains. The risk ratio (RR) for all-cause mortality was 0.78 (95% confidence interval (CI) 0.66 to 0.92); P = 0.004; 12 trials; 6683 participants; moderate-quality evidence. This translates into 26 (95% CI 9 to 41) fewer cases of death per 1000 participants in favour of supportive interventions. The RR for number of participants with any medical complication ranged from 1.42 in favour of control compared with 0.59 in favour of supportive interventions (very low-quality evidence). Only five trials (4451 participants) investigated health-related quality of life showing no substantial differences between intervention and comparator groups. Information on patient satisfaction was unreliable. The effects of supportive interventions versus comparators on hospitalisation showed a mean difference (MD) of -0.5 days (95% CI -2.6 to 1.6); P = 0.65; 5 trials; 667 participants; very low-quality evidence. Only three of 41 included trials (4108 participants; very low-quality evidence) reported on adverse events, describing intolerance to the supplement (diarrhoea, vomiting; 5/34 participants) and discontinuation of oral nutritional supplements because of refusal or dislike of taste (567/2017 participants). Meta-analysis across 17 trials with adequate data on weight change revealed an overall improvement in weight in favour of supportive interventions versus control: MD 0.6 kg (95% CI 0.21 to 1.02); 2024 participants; moderate-quality evidence. A total of 27 trials investigated nutritional intake with a majority of trials not finding marked differences in energy intake between intervention and comparator groups. Only three trials (1152 participants) reported some data on economic costs but did not use accepted health economic methods (very low-quality evidence).\nAuthors' conclusions\nThere is evidence of moderate to very low quality to suggest that supportive interventions to improve nutritional care results in minimal weight gain. Most of the evidence for the lower risk of all-cause mortality for supportive interventions comes from hospital-based trials and more research is needed to confirm this effect. There is very low-quality evidence regarding adverse effects; therefore whilst some of these interventions are advocated at a national level clinicians should recognise the lack of clear evidence to support their role. This review highlights the importance of assessing patient-important outcomes in future research.\n\nGiven the provided abstract, please respond to the following query: \"Study characteristics\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "We included 41 randomised controlled studies (clinical studies where people are randomly put into one of two or more treatment groups) with a total of 10,681 people in our review. There were five different interventions which we call 'supportive interventions': changes to the organisation of nutritional care (13 studies, 3456 people), changes to the feeding environment (5 studies, 351 people), modification of the meal profile or pattern (12 studies, 649 people), additional supplementation of meals (10 studies, 6022 people) and home meal delivery systems (1 study, 203 people). Monitoring participants over time (follow-up) ranged from ‘duration of hospital stay’ to 12 months. The comparator groups received 'usual' care. More than half of all participants took part in studies investigating the additional supplementation of meals (for example a protein-energy oral nutritional supplement in addition to the usual diet)." } ]

[ { "role": "user", "content": "Abstract: Background\nWomen with inflammatory bowel disease (IBD) may require surgery, which may result in higher risk of infertility. Restorative proctocolectomy with ileal anal pouch anastomosis (IPAA) may increase infertility, but the degree to which IPAA affects infertility remains unclear, and the impact of other surgical interventions on infertility is unknown.\nObjectives\nPrimary objective\n• To determine the effects of surgical interventions for IBD on female infertility.\nSecondary objectives\n• To evaluate the impact of surgical interventions on the need for assisted reproductive technology (ART), time to pregnancy, miscarriage, stillbirth, prematurity, mode of delivery (spontaneous vaginal, instrumental vaginal, or Caesarean section), infant requirement for resuscitation and neonatal intensive care, low and very low birth weight, small for gestational age, antenatal and postpartum hemorrhage, retained placenta, postpartum depression, gestational diabetes, and gestational hypertension/preeclampsia.\nSearch methods\nWe searched MEDLINE, Embase, CENTRAL, and the Cochrane IBD Group Specialized Register from inception to September 27, 2018, to identify relevant studies. We also searched references of relevant articles, conference abstracts, grey literature, and trials registers.\nSelection criteria\nWe included observational studies that compared women of reproductive age (≥ 12 years of age) who underwent surgery to women with IBD who had a different type of surgery or no surgery (i.e. treated medically). We also included studies comparing women before and after surgery. Any type of IBD-related surgery was permitted. Infertility was defined as an inability to become pregnant following 12 months of unprotected intercourse. Infertility at 6, 18, and 24 months was included as a secondary outcome. We excluded studies that included women without IBD and those comparing women with IBD to women without IBD..\nData collection and analysis\nTwo review authors independently screened studies and extracted data. We used the Newcastle-Ottawa Scale to assess bias and GRADE to assess the overall certainty of evidence. We calculated the pooled risk ratio (RR) and 95% confidence interval (CI) using random-effects models. When individual studies reported odds ratios (ORs) and did not provide raw numbers, we pooled ORs instead.\nMain results\nWe identified 16 observational studies for inclusion. Ten studies were included in meta-analyses, of which nine compared women with and without a previous IBD-related surgery and the other compared women with open and laparoscopic IPAA. Of the ten studies included in meta-analyses, four evaluated infertility, one evaluated ART, and seven reported on pregnancy-related outcomes. Seven studies in which women were compared before and after colectomy and/or IPAA were summarized qualitatively, of which five included a comparison of infertility, three included the use of ART, and three included other pregnancy-related outcomes. One study included a comparison of women with and without IPAA, as well as before and after IPAA, and was therefore included in both the meta-analysis and the qualitative summary. All studies were at high risk of bias for at least two domains.\nWe are very uncertain of the effect of IBD surgery on infertility at 12 months (RR 5.45, 95% CI 0.41 to 72.57; 114 participants; 2 studies) and at 24 months (RR 3.59, 95% CI 1.32 to 9.73; 190 participants; 1 study). Infertility was lower in women who received laparoscopic surgery compared to open restorative proctocolectomy at 12 months (RR 0.70, 95% CI 0.38 to 1.27; 37 participants; 1 study).\nWe are very uncertain of the effect of IBD surgery on pregnancy-related outcomes, including miscarriage (OR 2.03, 95% CI 1.14 to 3.60; 776 pregnancies; 5 studies), use of ART (RR 25.09, 95% CI 1.56 to 403.76; 106 participants; 1 study), delivery via Caesarean section (RR 2.23, 95% CI 1.00 to 4.95; 20 pregnancies; 1 study), stillbirth (RR 1.96, 95% CI 0.42 to 9.18; 246 pregnancies; 3 studies), preterm birth (RR 1.91, 95% CI 0.67 to 5.48; 194 pregnancies; 3 studies), low birth weight (RR 0.61, 95% CI 0.08 to 4.83), and small for gestational age (RR 2.54, 95% CI 0.80 to 8.01; 65 pregnancies; 1 study).\nStudies comparing infertility before and after IBD-related surgery reported numerically higher rates of infertility at six months (before: 1/5, 20.0%; after: 9/15, 60.0%; 1 study), at 12 months (before: 68/327, 20.8%; after: 239/377, 63.4%; 5 studies), and at 24 months (before: 14/89, 15.7%; after: 115/164, 70.1%; 2 studies); use of ART (before: 5.3% to 42.2%; after: 30.3% to 34.3%; proportions varied across studies due to differences in which women were identified as at risk of using ART); and delivery via Caesarean section (before: 8/73, 11.0%; after: 36/75, 48.0%; 2 studies). In addition, women had a longer time to conception after surgery (two to five months; 2 studies) than before surgery (5 to 16 months; 2 studies). The proportions of women experiencing miscarriage (before: 19/123, 15.4%; after: 21/134, 15.7%; 3 studies) and stillbirth (before: 2/38, 5.3%; after: 3/80: 3.8%; 2 studies) were similar before and after surgery. Fewer women experienced gestational diabetes after surgery (before: 3/37, 8.1%; after: 0/37; 1 study), and the risk of preeclampsia was similar before and after surgery (before: 2/37, 5.4%; after: 0/37; 1 study). We are very uncertain of the effects of IBD-related surgery on these outcomes due to poor quality evidence, including confounding bias due to increased age of women after surgery.\nWe rated evidence for all outcomes and comparisons as very low quality due to the observational nature of the data, inclusion of small studies with imprecise estimates, and high risk of bias among included studies.\nAuthors' conclusions\nThe effect of surgical therapy for IBD on female infertility is uncertain. It is also uncertain if there are any differences in infertility among those undergoing open versus laparoscopic procedures. Previous surgery was associated with higher risk of miscarriage, use of ART, Caesarean section delivery, and giving birth to a low birth weight infant, but was not associated with risk of stillbirth, preterm delivery, or delivery of a small for gestational age infant. These findings are based on very low-quality evidence. As a result, definitive conclusions cannot be made, and future well-designed studies are needed to fully understand the impact of surgery on infertility and pregnancy outcomes.\n\nGiven the provided abstract, please respond to the following query: \"What did researchers find?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "Researchers found 16 studies that reported the impact of surgery on infertility or pregnancy outcomes in women with IBD. Nine studies compared women with and without previous surgery. Four of these studies reported on the impact of surgery on a woman’s ability to become pregnant. We were unable to reach conclusions about the association between surgery and infertility because of the low quality of evidence from these studies. Eight reported on pregnancy outcomes and complications. Evidence from these studies was also of very low quality, and we are unable to draw conclusions about the impact of IBD surgery on pregnancy outcomes. Evidence from the one study comparing infertility among women undergoing open and laparoscopic surgery was also of low quality. Thus, we could not draw conclusions about the impact of open and laparoscopic procedures on infertility. The remaining six studies compared women before and after surgery. One study that compared women with IBD who did and did not have surgery also compared women before and after surgery. These seven studies comparing women before and after surgery provided low-quality evidence on differences in women’s ability to get pregnant and on outcomes of pregnancy before and after surgery." } ]

[ { "role": "user", "content": "Abstract: Background\nChildren with developmental speech sound disorders have difficulties in producing the speech sounds of their native language. These speech difficulties could be due to structural, sensory or neurophysiological causes (e.g. hearing impairment), but more often the cause of the problem is unknown. One treatment approach used by speech-language therapists/pathologists is non-speech oral motor treatment (NSOMT). NSOMTs are non-speech activities that aim to stimulate or improve speech production and treat specific speech errors. For example, using exercises such as smiling, pursing, blowing into horns, blowing bubbles, and lip massage to target lip mobility for the production of speech sounds involving the lips, such as /p/, /b/, and /m/. The efficacy of this treatment approach is controversial, and evidence regarding the efficacy of NSOMTs needs to be examined.\nObjectives\nTo assess the efficacy of non-speech oral motor treatment (NSOMT) in treating children with developmental speech sound disorders who have speech errors.\nSearch methods\nIn April 2014 we searched the Cochrane Central Register of Controlled Trials (CENTRAL), Ovid MEDLINE (R) and Ovid MEDLINE In-Process & Other Non-Indexed Citations, EMBASE, Education Resources Information Center (ERIC), PsycINFO and 11 other databases. We also searched five trial and research registers, checked the reference lists of relevant titles identified by the search and contacted researchers to identify other possible published and unpublished studies.\nSelection criteria\nRandomised and quasi-randomised controlled trials that compared (1) NSOMT versus placebo or control; and (2) NSOMT as adjunctive treatment or speech intervention versus speech intervention alone, for children aged three to 16 years with developmental speech sound disorders, as judged by a speech and language therapist. Individuals with an intellectual disability (e.g. Down syndrome) or a physical disability were not excluded.\nData collection and analysis\nThe Trials Search Co-ordinator of the Cochrane Developmental, Psychosocial and Learning Problems Group and one review author ran the searches. Two review authors independently screened titles and abstracts to eliminate irrelevant studies, extracted data from the included studies and assessed risk of bias in each of these studies. In cases of ambiguity or information missing from the paper, we contacted trial authors.\nMain results\nThis review identified three studies (from four reports) involving a total of 22 children that investigated the efficacy of NSOMT as adjunctive treatment to conventional speech intervention versus conventional speech intervention for children with speech sound disorders. One study, a randomised controlled trial (RCT), included four boys aged seven years one month to nine years six months - all had speech sound disorders, and two had additional conditions (one was diagnosed as \"communication impaired\" and the other as \"multiply disabled\"). Of the two quasi-randomised controlled trials, one included 10 children (six boys and four girls), aged five years eight months to six years nine months, with speech sound disorders as a result of tongue thrust, and the other study included eight children (four boys and four girls), aged three to six years, with moderate to severe articulation disorder only. Two studies did not find NSOMT as adjunctive treatment to be more effective than conventional speech intervention alone, as both intervention and control groups made similar improvements in articulation after receiving treatments. One study reported a change in postintervention articulation test results but used an inappropriate statistical test and did not report the results clearly. None of the included studies examined the effects of NSOMTs on any other primary outcomes, such as speech intelligibility, speech physiology and adverse effects, or on any of the secondary outcomes such as listener acceptability.\nThe RCT was judged at low risk for selection bias. The two quasi-randomised trials used randomisation but did not report the method for generating the random sequence and were judged as having unclear risk of selection bias. The three included studies were deemed to have high risk of performance bias as, given the nature of the intervention, blinding of participants was not possible. Only one study implemented blinding of outcome assessment and was at low risk for detection bias. One study showed high risk of other bias as the baseline characteristics of participants seemed to be unequal. The sample size of each of the included studies was very small, which means it is highly likely that participants in these studies were not representative of its target population. In the light of these serious limitations in methodology, the overall quality of the evidence provided by the included trials is judged to be low. Therefore, further research is very likely to have an important impact on our confidence in the estimate of treatment effect and is likely to change the estimate.\nAuthors' conclusions\nThe three included studies were small in scale and had a number of serious methodological limitations. In addition, they covered limited types of NSOMTs for treating children with speech sound disorders of unknown origin with the sounds /s/ and /z/. Hence, we judged the overall applicability of the evidence as limited and incomplete. Results of this review are consistent with those of previous reviews: Currently no strong evidence suggests that NSOMTs are an effective treatment or an effective adjunctive treatment for children with developmental speech sound disorders. Lack of strong evidence regarding the treatment efficacy of NSOMTs has implications for clinicians when they make decisions in relation to treatment plans. Well-designed research is needed to carefully investigate NSOMT as a type of treatment for children with speech sound disorders.\n\nGiven the provided abstract, please respond to the following query: \"Key results\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "Two studies (one that used oral placement therapy and one that used Hanson's 1977 approach) did not find NSOMT as an adjunctive treatment to be more effective than conventional speech intervention only, as both intervention and control groups had made similar improvements in articulation after treatment (i.e. fewer speech errors or increased percentage of correct articulation). The study that used oral motor exercises for speech clarity as the NSOMT reported a change in articulation test results after treatment, but used an inappropriate statistical test and did not report the results clearly." } ]

[ { "role": "user", "content": "Abstract: Background\nThe keratocystic odontogenic tumours (KCOTs) account for between about 2% and 11% of all jaw cysts and can occur at any age. They are more common in males than females with a male:female ratio of approximately 2:1. Although they are benign, KCOTs are locally very aggressive and have a tendency to recur after treatment. Reported recurrence rates range from 3% to 60%. The traditional method for the treatment of most KCOTs is surgical enucleation. However, due to the lining of the cyst being delicate and the fact that they frequently recur, this method alone is not sufficient. Adjunctive surgical treatment has been proposed in addition to the surgical enucleation, such as removal of the peripheral bone (ostectomy) or resection of the cyst with surrounding bone (en-bloc) resection. Other adjunctive treatments proposed are: cryotherapy (freezing) with liquid nitrogen and the use of the fixative Carnoy's solution placed in the cyst cavity after enucleation; both of which attempt to address residual tissue to prevent recurrence.\nObjectives\nTo assess the available evidence comparing the effectiveness of interventions for the treatment of KCOTs.\nSearch methods\nWe searched the following electronic databases: the Cochrane Oral Health Group Trials Register (to 17 March 2015), the Cochrane Central Register of Controlled Trials (CENTRAL) (The Cochrane Library, 2015, Issue 2), MEDLINE via Ovid (1946 to 17 March 2015) and EMBASE via Ovid (1980 to 17 March 2015). We searched the US National Institutes of Health Trials Register (http://clinicaltrials.gov) and the WHO Clinical Trials Registry Platform for ongoing trials. No restrictions were placed on the language or date of publication when searching the electronic databases.\nSelection criteria\nRandomised controlled trials comparing one modality of intervention with another with or without adjunctive treatment for the treatment of KCOTs. Adults, over the age of 18 with a validated diagnosis of solitary KCOTs arising in the jaw bones of the maxilla or mandible. Patients with known Gorlin syndrome were to be excluded.\nData collection and analysis\nReview authors screened trials for inclusion. Full papers were obtained for relevant and potentially relevant trials. If data had been extracted, it would have been synthesised using the fixed-effect model, if substantial clinical diversity were identified between studies we planned to use the random-effects model with studies grouped by action provided there were four or more studies included in the meta-analysis, and we would have explored the heterogeneity between the included studies.\nMain results\nNo randomised controlled trials that met the inclusion criteria were identified.\nAuthors' conclusions\nThere are no published randomised controlled trials relevant to this review question, therefore no conclusions could be reached about the effectiveness or otherwise of the interventions considered in this review. There is a need for well designed and conducted randomised controlled trials to evaluate treatments for KCOTs.\n\nGiven the provided abstract, please respond to the following query: \"Key results and quality of the evidence\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "This review revealed that there is no high quality evidence for the effectiveness of available treatments and there is therefore a need for further research to help clinicians and patients to make informed choices about treatment options." } ]

[ { "role": "user", "content": "Abstract: Background\nChronic pulmonary infection is a hallmark of lung disease in cystic fibrosis. Infections dominated by organisms of the Burkholderia cepacia complex, a group of at least 18 closely-related species of gram-negative bacteria, are particularly difficult to treat. These infections may be associated with a fulminant necrotising pneumonia. Burkholderia cepacia complex bacteria are resistant to many common antibiotics and able to acquire resistance against many more. Following patient segregation in cystic fibrosis medical care, the more virulent epidemic strains are not as frequent, and new infections are more likely to be with less virulent environmentally-acquired strains. Although evidence-based guidelines exist for treating respiratory exacerbations involving Pseudomonas aeruginosa, these cannot be extended to Burkholderia cepacia complex infections. This review, which is an update of a previous review, aims to assess the available trial evidence for the choice and application of treatments for these infections.\nObjectives\nTo assess the effectiveness and safety of different antibiotic regimens in people with cystic fibrosis experiencing an exacerbation and chronically infected with organisms of the Burkholderia cepacia complex.\nSearch methods\nWe searched the Cochrane Cystic Fibrosis Trials Register, compiled from electronic database searches and handsearching of journals and conference abstract books. We also searched the reference lists of relevant articles and reviews.\nDate of latest search: 29 May 2019.\nSelection criteria\nRandomised and quasi-randomised controlled trials of treatments for exacerbations of pulmonary symptoms in people with cystic fibrosis chronically infected with organisms of the Burkholderia cepacia complex.\nData collection and analysis\nNo relevant trials were identified.\nMain results\nNo trials were included in this review.\nAuthors' conclusions\nBurkholderia cepacia complex infections present a significant challenge for people with cystic fibrosis and their clinicians. The incidence is likely to increase as the cystic fibrosis population ages; and managing and treating these infections will become more important. There is a lack of trial evidence to guide decision making and no conclusions can be drawn from this review about the optimal antibiotic regimens for people with cystic fibrosis who have chronic Burkholderia cepacia complex infections. Clinicians must continue to assess each person individually, taking into account in vitro antibiotic susceptibility data, previous clinical responses and their own experience. Multicentre randomised clinical trials are needed to assess the effectiveness of different antibiotic regimens in people with cystic fibrosis infected with organisms of the Burkholderia cepacia complex.\n\nGiven the provided abstract, please respond to the following query: \"Key results\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "More research is needed to find out which treatments are best for improving lung function and survival and for reducing side effects and length of time spent in hospital for people infected with Burkholderia cepacia complex bacteria experiencing an exacerbation." } ]

[ { "role": "user", "content": "Abstract: Background\nProper sedation for neonates undergoing uncomfortable procedures may reduce stress and avoid complications. Midazolam is a short-acting benzodiazepine that is used increasingly in neonatal intensive care units (NICUs). However, its effectiveness as a sedative in neonates has not been systematically evaluated.\nObjectives\nPrimary objecive\nTo assess the effectiveness of intravenous midazolam infusion for sedation, as evaluated by behavioural and/or physiological measurements of sedation levels, in critically ill neonates in the NICU.\nSecondary objectives\nTo assess effects of intravenous midazolam infusion for sedation on complications including the following.\n1. Incidence of intraventricular haemorrhage (IVH)/periventricular leukomalacia (PVL).\n2. Mortality.\n3. Occurrence of adverse effects associated with the use of midazolam (hypotension, neurological abnormalities).\n4. Days of ventilation.\n5. Days of supplemental oxygen.\n6. Incidence of pneumothorax.\n7. Length of NICU stay (days).\n8. Long-term neurodevelopmental outcomes.\nSearch methods\nWe used the standard search strategy of the Cochrane Neonatal Review Group to search the Cochrane Central Register of Controlled Trials (CENTRAL; 2016, Issue 5), MEDLINE via PubMed (1966 to 16 June 2016), Embase (1980 to 16 June 2016) and the Cumulative Index to Nursing and Allied Health Literature (CINAHL; 1982 to 16 June 2016). We searched clinical trials databases, conference proceedings and reference lists of retrieved articles for randomised controlled trials and quasi-randomised trials.\nSelection criteria\nWe selected for review randomised and quasi-randomised controlled trials of intravenous midazolam infusion for sedation in infants aged 28 days or younger.\nData collection and analysis\nWe abstracted data regarding the primary outcome of level of sedation. We assessed secondary outcomes such as intraventricular haemorrhage, periventricular leukomalacia, death, length of NICU stay and adverse effects associated with midazolam. When appropriate, we performed meta-analyses using risk ratios (RRs) and risk differences (RDs), and if the RD was statistically significant, we calculated the number needed to treat for an additional beneficial outcome (NNTB) or an additional harmful outcome (NNTH), along with their 95% confidence intervals (95% CIs) for categorical variables, and weighted mean differences (WMDs) for continuous variables. We assessed heterogeneity by performing the I-squared (I2) test.\nMain results\nWe included in the review three trials enrolling 148 neonates. We identified no new trials for this update. Using different sedation scales, each study showed a statistically significantly higher sedation level in the midazolam group compared with the placebo group. However, none of the sedation scales used have been validated in preterm infants; therefore, we could not ascertain the effectiveness of midazolam in this population. Duration of NICU stay was significantly longer in the midazolam group than in the placebo group (WMD 5.4 days, 95% CI 0.40 to 10.5; I2 = 0%; two studies, 89 infants). One study (43 infants) reported significantly lower Premature Infant Pain Profile (PIPP) scores during midazolam infusion than during dextrose (placebo) infusion (MD -3.80, 95% CI -5.93 to -1.67). Another study (46 infants) observed a higher incidence of adverse neurological events at 28 days' postnatal age (death, grade III or IV IVH or PVL) in the midazolam group compared with the morphine group (RR 7.64, 95% CI 1.02 to 57.21; RD 0.28, 95% CI 0.07 to 0.49; NNTH 4, 95% CI 2 to 14) (tests for heterogeneity not applicable). We considered these trials to be of moderate quality according to GRADE assessment based on the following outcomes: mortality during hospital stay, length of NICU stay, adequacy of analgesia according to PIPP scores and poor neurological outcomes by 28 days' postnatal age.\nAuthors' conclusions\nData are insufficient to promote the use of intravenous midazolam infusion as a sedative for neonates undergoing intensive care. This review raises concerns about the safety of midazolam in neonates. Further research on the effectiveness and safety of midazolam in neonates is needed.\n\nGiven the provided abstract, please respond to the following query: \"Background\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "Proper sedation for babies undergoing uncomfortable procedures while receiving intensive care may reduce stress and avoid complications. Midazolam is a sedative that is used increasingly in NICUs. However, researchers have not systematically reviewed the evidence to see if it is effective and safe for babies in this setting." } ]

[ { "role": "user", "content": "Abstract: Background\nSickle cell disease (SCD) is a group of inherited disorders of haemoglobin (Hb) structure in a person who has inherited two mutant globin genes (one from each parent), at least one of which is always the sickle mutation. It is estimated that between 5% and 7% of the world's population are carriers of the mutant Hb gene, and SCD is the most commonly inherited blood disorder.\nSCD is characterized by distorted sickle-shaped red blood cells. Manifestations of the disease are attributed to either haemolysis (premature red cell destruction) or vaso-occlusion (obstruction of blood flow, the most common manifestation). Shortened lifespans are attributable to serious comorbidities associated with the disease, including renal failure, acute cholecystitis, pulmonary hypertension, aplastic crisis, pulmonary embolus, stroke, acute chest syndrome, and sepsis.\nVaso-occlusion can lead to an acute, painful crisis (sickle cell crisis, vaso-occlusive crisis (VOC) or vaso-occlusive episode). Pain is most often reported in the joints, extremities, back or chest, but it can occur anywhere and can last for several days or weeks. The bone and muscle pain experienced during a sickle cell crisis is both acute and recurrent.\nKey pharmacological treatments for VOC include opioid analgesics, non-opioid analgesics, and combinations of drugs. Non-pharmacological approaches, such as relaxation, hypnosis, heat, ice and acupuncture, have been used in conjunction to rehydrating the patient and reduce the sickling process.\nObjectives\nTo assess the analgesic efficacy and adverse events of pharmacological interventions to treat acute painful sickle cell vaso-occlusive crises in adults, in any setting.\nSearch methods\nWe searched the Cochrane Central Register of Controlled Trials (CENTRAL) via the Cochrane Register of Studies Online, MEDLINE via Ovid, Embase via Ovid and LILACS, from inception to September 2019. We also searched the reference lists of retrieved studies and reviews, and searched online clinical trial registries.\nSelection criteria\nRandomized, controlled, double-blind trials of pharmacological interventions, of any dose and by any route, compared to placebo or any active comparator, for the treatment (not prevention) of painful sickle cell VOC in adults.\nData collection and analysis\nThree review authors independently assessed studies for eligibility. We planned to use dichotomous data to calculate risk ratio (RR) and number needed to treat for one additional event, using standard methods. Our primary outcomes were participant-reported pain relief of 50%, or 30%, or greater; Patient Global Impression of Change (PGIC) very much improved, or much or very much improved. Our secondary outcomes included adverse events, serious adverse events, and withdrawals due to adverse events. We assessed GRADE and created three 'Summary of findings' tables.\nMain results\nWe included nine studies with data for 638 VOC events and 594 participants aged 17 to 42 years with SCD presenting to a hospital emergency department in a painful VOC. Three studies investigated a non-steroidal anti-inflammatory drug (NSAID) compared to placebo. One study compared an opioid with a placebo, two studies compared an opioid with an active comparator, two studies compared an anticoagulant with a placebo, and one study compared a combination of three drugs with a combination of four drugs.\nRisk of bias across the nine studies varied. Studies were primarily at an unclear risk of selection, performance, and detection bias. Studies were primarily at a high risk of bias for size with fewer than 50 participants per treatment arm; two studies had 50 to 199 participants per treatment arm (unclear risk).\nNon-steroidal anti-inflammatory drugs (NSAID) compared with placebo\nNo data were reported regarding participant-reported pain relief of 50% or 30% or greater.\nThe efficacy was uncertain regarding PGIC very much improved, and PGIC much or very much improved (no difference; 1 study, 21 participants; very low-quality evidence).\nVery low-quality, uncertain results suggested similar rates of adverse events across both the NSAIDs group (16/45 adverse events, 1/56 serious adverse events, and 1/56 withdrawal due to adverse events) and the placebo group (19/45 adverse events, 2/56 serious adverse events, and 1/56 withdrawal due to adverse events).\nOpioids compared with placebo\nNo data were reported regarding participant-reported pain relief of 50% or 30%, PGIC, or adverse events (any adverse event, serious adverse events, and withdrawals due to adverse events).\nOpioids compared with active comparator\nNo data were reported regarding participant-reported pain relief of 50% or 30% or greater.\nThe results were uncertain regarding PGIC very much improved (33% of the opioids group versus 19% of the placebo group). No data were reported regarding PGIC much or very much improved.\nVery low-quality, uncertain results suggested similar rates of adverse events across both the opioids group (9/66 adverse events, and 0/66 serious adverse events) and the placebo group (7/64 adverse events, 0/66 serious adverse events). No data were reported regarding withdrawal due to adverse events.\nQuality of the evidence\nWe downgraded the quality of the evidence by three levels to very low-quality because there are too few data to have confidence in results (e.g. too few participants per treatment arm). Where no data were reported for an outcome, we had no evidence to support or refute (quality of the evidence is unknown).\nAuthors' conclusions\nThis review identified only nine studies, with insufficient data for all pharmacological interventions for analysis.\nThe available evidence is very uncertain regarding the efficacy or harm from pharmacological interventions used to treat pain related to sickle cell VOC in adults. This area could benefit most from more high quality, certain evidence, as well as the establishment of suitable registries which record interventions and outcomes for this group of people.\n\nGiven the provided abstract, please respond to the following query: \"Background\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "People with sickle cell disease have abnormally shaped red cells in their blood. Sickle cell disease is the most common inherited blood disorder around the world. It is estimated globally that 367 million to 500 million people are carriers. People with sickle cell disease have a higher chance of life-threatening complications, such as infection, severe chest pain and stroke in early life, and kidney or liver damage in adulthood.\nA pain crisis is the most common problem of sickle cell disease and can require several treatments at once, usually in an emergency situation. The first priority is to control the pain, using medicines (such as opioids, non-steroidal anti-inflammatories, paracetamol, and blood thinners) or relaxation, hypnosis, heat, ice, or acupuncture." } ]

[ { "role": "user", "content": "Abstract: Background\nCannabis and cannabinoids are often promoted as treatment for many illnesses and are widely used among patients with ulcerative colitis (UC). Few studies have evaluated the use of these agents in UC. Further, cannabis has potential for adverse events and the long-term consequences of cannabis and cannabinoid use in UC are unknown.\nObjectives\nTo assess the efficacy and safety of cannabis and cannabinoids for the treatment of patients with UC.\nSearch methods\nWe searched MEDLINE, Embase, WHO ICTRP, AMED, PsychINFO, the Cochrane IBD Group Specialized Register, CENTRAL, ClinicalTrials.Gov and the European Clinical Trials Register from inception to 2 January 2018. Conference abstracts and references were searched to identify additional studies.\nSelection criteria\nRandomized controlled trials (RCTs) comparing any form or dose of cannabis or its cannabinoid derivatives (natural or synthetic) to placebo or an active therapy for adults (> 18 years) with UC were included.\nData collection and analysis\nTwo authors independently screened search results, extracted data and assessed bias using the Cochrane risk of bias tool. The primary outcomes were clinical remission and relapse (as defined by the primary studies). Secondary outcomes included clinical response, endoscopic remission, endoscopic response, histological response, quality of life, C-reactive protein (CRP) and fecal calprotectin measurements, symptom improvement, adverse events, serious adverse events, withdrawal due to adverse events, psychotropic adverse events, and cannabis dependence and withdrawal effects. We calculated the risk ratio (RR) and corresponding 95% confidence interval for dichotomous outcomes. For continuous outcomes, we calculated the mean difference (MD) and corresponding 95% CI. Data were pooled for analysis when the interventions, patient groups and outcomes were sufficiently similar (determined by consensus). Data were analyzed on an intention-to-treat basis. GRADE was used to evaluate the overall certainty of evidence.\nMain results\nTwo RCTs (92 participants) met the inclusion criteria. One study (N = 60) compared 10 weeks of cannabidiol capsules with up to 4.7% D9-tetrahydrocannabinol (THC) with placebo capsules in participants with mild to moderate UC. The starting dose of cannabidiol was 50 mg twice daily increasing to 250 mg twice daily if tolerated. Another study (N = 32) compared 8 weeks of therapy with two cannabis cigarettes per day containing 0.5 g of cannabis, corresponding to 23 mg THC/day to placebo cigarettes in participants with UC who did not respond to conventional medical treatment. No studies were identified that assessed cannabis therapy in quiescent UC. The first study was rated as low risk of bias and the second study (published as an abstract) was rated as high risk of bias for blinding of participants and personnel. The studies were not pooled due to differences in the interventional drug.\nThe effect of cannabidiol capsules (100 mg to 500 mg daily) compared to placebo on clinical remission and response is uncertain. Clinical remission at 10 weeks was achieved by 24% (7/29) of the cannabidiol group compared to 26% (8/31) in the placebo group (RR 0.94, 95% CI 0.39 to 2.25; low certainty evidence). Clinical response at 10 weeks was achieved in 31% (9/29) of cannabidiol participants compared to 22% (7/31) of placebo patients (RR 1.37, 95% CI 0.59 to 3.21; low certainty evidence). Serum CRP levels were similar in both groups after 10 weeks of therapy. The mean CRP in the cannabidiol group was 9.428 mg/L compared to 7.638 mg/L in the placebo group (MD 1.79, 95% CI -5.67 to 9.25; moderate certainty evidence). There may be a clinically meaningful improvement in quality of life at 10 weeks, measured with the IBDQ scale (MD 17.4, 95% CI -3.45 to 38.25; moderate certainty evidence). Adverse events were more frequent in cannabidiol participants compared to placebo. One hundred per cent (29/29) of cannabidiol participants had an adverse event, compared to 77% (24/31) of placebo participants (RR 1.28, 95% CI 1.05 to1.56; moderate certainty evidence). However, these adverse events were considered to be mild or moderate in severity. Common adverse events included dizziness, disturbance in attention, headache, nausea and fatigue. None (0/29) of the cannabidiol participants had a serious adverse event compared to 10% (3/31) of placebo participants (RR 0.15, 95% CI 0.01 to 2.83; low certainty evidence). Serious adverse events in the placebo group included worsening of UC and one complicated pregnancy. These serious adverse events were thought to be unrelated to the study drug. More participants in the cannabidiol group withdrew due to an adverse event than placebo participants. Thirty-four per cent (10/29) of cannabidiol participants withdrew due to an adverse event compared to 16% (5/31) of placebo participants (RR 2.14, 95% CI 0.83 to 5.51; low certainty evidence). Withdrawls in the cannabidiol group were mostly due to dizziness. Withdrawals in the placebo group were due to worsening UC.\nThe effect of cannabis cigarettes (23 mg THC/day) compared to placebo on mean disease activity, CRP levels and mean fecal calprotectin levels is uncertain. After 8 weeks, the mean disease activity index score in cannabis participants was 4 compared with 8 in placebo participants (MD -4.00, 95% CI -5.98 to -2.02). After 8 weeks, the mean change in CRP levels was similar in both groups (MD -0.30, 95% CI -1.35 to 0.75; low certainty evidence). The mean fecal calprotectin level in cannabis participants was 115 mg/dl compared to 229 mg/dl in placebo participants (MD -114.00, 95% CI -246.01 to 18.01). No serious adverse events were observed. This study did not report on clinical remission, clinical response, quality of life, adverse events or withdrawal due to adverse events.\nAuthors' conclusions\nThe effects of cannabis and cannabidiol on UC are uncertain, thus no firm conclusions regarding the efficacy and safety of cannabis or cannabidiol in adults with active UC can be drawn.There is no evidence for cannabis or cannabinoid use for maintenance of remission in UC. Further studies with a larger number of patients are required to assess the effects of cannabis in UC patients with active and quiescent disease. Different doses of cannabis and routes of administration should be investigated. Lastly, follow-up is needed to assess the long term safety outcomes of frequent cannabis use.\n\nGiven the provided abstract, please respond to the following query: \"Conclusions\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "The effects of cannabis and cannabis oil on ulcerative colitis are uncertain, thus no firm conclusions regarding the effectiveness and safety of cannabis or cannabis oil in adults with active ulcerative colitis can be drawn. There is no evidence for cannabis or cannabis oil use for maintenance of remission in ulcerative colitis. Further studies with a larger number of participants are required to assess the effects of cannabis in people with active and inactive ulcerative colitis. Different doses of cannabis and routes of administration should be investigated. Lastly, follow-up is needed to assess the long term safety outcomes of frequent cannabis use." } ]

[ { "role": "user", "content": "Abstract: Background\nOtitis media is inflammation of the middle ear and is usually caused by infection. It affects people of all ages but is particularly common in young children. Around 164 million people worldwide have long-term hearing loss caused by this condition, 90% of them in low-income countries. As zinc supplements prevent pneumonia in disadvantaged children, we wanted to investigate whether zinc supplements could also prevent otitis media.\nObjectives\nTo evaluate whether zinc supplements prevent otitis media in adults and children of different ages.\nSearch methods\nWe searched CENTRAL (2014, Issue 1), MEDLINE (1950 to February week 4, 2014) and EMBASE (1974 to March 2014).\nSelection criteria\nRandomised, placebo-controlled trials of zinc supplements given at least once a week for at least a month for preventing otitis media.\nData collection and analysis\nTwo review authors independently assessed the eligibility and methodological quality of the included trials and extracted and analysed data. We summarised results using risk ratios (RRs) or rate ratios for dichotomous data and mean differences (MDs) for continuous data. We combined trial results where appropriate.\nMain results\nNo new trials were identified for inclusion in this update. We identified 12 trials for inclusion, 10 of which contributed outcomes data. There were a total of 6820 participants. In trials of healthy children living in low-income communities, two trials did not demonstrate a significant difference between the zinc-supplemented and placebo groups in the numbers of participants experiencing an episode of definite otitis media during follow-up (3191 participants); another trial showed a significantly lower incidence rate of otitis media in the zinc group (rate ratio 0.69, 95% confidence interval (CI) 0.61 to 0.79, n = 1621). A small trial of 39 infants undergoing treatment for severe malnutrition suggested a benefit of zinc for the mean number of episodes of otitis media (mean difference (MD) -1.12 episodes, 95% CI -2.21 to -0.03). Zinc supplements did not seem to cause any serious adverse events but a small minority of children were reported to have vomited shortly after ingestion of the supplements. The trial evidence included is generally of good quality, with a low risk of bias.\nAuthors' conclusions\nEvidence on whether zinc supplementation can reduce the incidence of otitis media in healthy children under the age of five years living in low- and middle-income countries is mixed. There is some evidence of benefit in children being treated for marasmus (severe malnutrition), but this is based on one small trial and should therefore be treated with caution.\n\nGiven the provided abstract, please respond to the following query: \"Results\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "The results of the trials provided no convincing evidence that zinc supplements reduce the occurrence of middle ear infections in healthy children. However, in one small study of severely malnourished children, those receiving zinc supplements had fewer middle ear infections. The only adverse effect was vomiting." } ]

[ { "role": "user", "content": "Abstract: Background\nMany women would like to avoid pharmacological or invasive methods of pain management in labour and this may contribute to the popularity of complementary methods of pain management. This review examined currently available evidence on the use of relaxation therapies for pain management in labour. This is an update of a review first published in 2011.\nObjectives\nTo examine the effects of mind-body relaxation techniques for pain management in labour on maternal and neonatal well-being during and after labour.\nSearch methods\nWe searched Cochrane Pregnancy and Childbirth's Trials Register (9 May 2017), the Cochrane Central Register of Controlled Trials (CENTRAL) (The Cochrane Library, Issue 5 2017), MEDLINE (1966 to 24 May 2017), CINAHL (1980 to 24 May 2017), the Australian New Zealand Clinical Trials Registry (18 May 2017), ClinicalTrials.gov (18 May 2017), the ISRCTN Register (18 May 2017), the WHO International Clinical Trials Registry Platform (ICTRP) (18 May 2017), and reference lists of retrieved studies.\nSelection criteria\nRandomised controlled trials (including quasi randomised and cluster trials) comparing relaxation methods with standard care, no treatment, other non-pharmacological forms of pain management in labour or placebo.\nData collection and analysis\nTwo review authors independently assessed trials for inclusion and risk of bias, extracted data and checked them for accuracy. We attempted to contact study authors for additional information. We assessed evidence quality with GRADE methodology.\nMain results\nThis review update includes 19 studies (2519 women), 15 of which (1731 women) contribute data. Interventions examined included relaxation, yoga, music and mindfulness. Approximately half of the studies had a low risk of bias for random sequence generation and attrition bias. The majority of studies had a high risk of bias for performance and detection bias, and unclear risk of bias for, allocation concealment, reporting bias and other bias. We assessed the evidence from these studies as ranging from low to very low quality, and therefore the effects below should be interpreted with caution.\nRelaxation\nWe found that relaxation compared to usual care provided lowered the intensity of pain (measured on a scale of 0 to 10 with low scores indicating less pain) during the latent phase of labour (mean difference (MD) -1.25, 95% confidence interval (CI) -1.97 to -0.53, one trial, 40 women). Four trials reported pain intensity in the active phase; there was high heterogeneity between trials and very low-quality evidence suggested that there was no strong evidence that the effects were any different between groups for this outcome (MD -1.08, 95% CI -2.57 to 0.41, four trials, 271 women, random-effects analysis). Very low-quality evidence showed that women receiving relaxation reported greater satisfaction with pain relief during labour (risk ratio (RR) 8.00, 95% CI 1.10 to 58.19, one trial, 40 women), and showed no clear benefit for satisfaction with childbirth experience (assessed using different scales) (standard mean difference (SMD) -0.03, 95% CI -0.37 to 0.31, three trials, 1176 women). For safety outcomes there was very low-quality evidence of no clear reduction in assisted vaginal birth (average RR 0.61, 95% CI 0.20 to 1.84, four trials, 1122 women) or in caesarean section rates (average RR 0.73, 95% CI 0.26 to 2.01, four trials, 1122 women). Sense of control in labour, and breastfeeding were not reported under this comparison.\nYoga\nWhen comparing yoga to control interventions there was low-quality evidence that yoga lowered pain intensity (measured on a scale of 0 to 10) with low scores indicating less pain) (MD -6.12, 95% CI -11.77 to -0.47, one trial, 66 women), greater satisfaction with pain relief (MD 7.88, 95% CI 1.51 to 14.25, one trial, 66 women) and greater satisfaction with childbirth experience (MD 6.34, 95% CI 0.26 to 12.42 one trial, 66 women (assessed using the Maternal Comfort Scale with higher score indicating greater comfort). Sense of control in labour, breastfeeding, assisted vaginal birth, and caesarean section were not reported under this comparison.\nMusic\nWhen comparing music to control interventions there was evidence of lower pain intensity in the latent phase for women receiving music (measured on a scale of 0 to 10 with low scores indicating less pain) (MD -0.73, 95% CI -1.01 to -0.45, random-effects analysis, two trials, 192 women) and very low-quality evidence of no clear benefit in the active phase (MD -0.51, 95% CI -1.10 to 0.07, three trials, 217 women). Very low-quality evidence suggested no clear benefit in terms of reducing assisted vaginal birth (RR 0.41, 95% CI 0.08 to 2.05, one trial, 156 women) or caesarean section rate (RR 0.78, 95% CI 0.36 to 1.70, two trials, 216 women). Satisfaction with pain relief, sense of control in labour, satisfaction with childbirth experience, and breastfeeding were not reported under this comparison.\nAudio analgesia\nOne trial evaluating audio analgesia versus control only reported one outcome and showed no evidence of benefit in satisfaction with pain relief.\nMindfulness\nOne trial evaluating mindfulness versus usual care found an increase in sense of control for the mindfulness group (using the Childbirth Self-Efficacy Inventory) (MD 31.30, 95% CI 1.61 to 60.99, 26 women). There is no strong evidence that the effects were any different between groups for satisfaction in childbirth, or for caesarean section rate, need for assisted vaginal delivery or need for pharmacological pain relief. No other outcomes were reported in this trial.\nAuthors' conclusions\nRelaxation, yoga and music may have a role with reducing pain, and increasing satisfaction with pain relief, although the quality of evidence varies between very low to low. There was insufficient evidence for the role of mindfulness and audio-analgesia. The majority of trials did not report on the safety of the interventions. Further randomised controlled trials of relaxation modalities for pain management in labour are needed. Trials should be adequately powered and include clinically relevant outcomes such as those described in this review.\n\nGiven the provided abstract, please respond to the following query: \"Why is this important?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "The pain of labour can be intense, with body tension, anxiety and fear making it worse. Many women would like to go through labour without using drugs, or invasive methods such as an epidural. These women often turn to complementary therapies to help to reduce the intensity of pain in labour and improve their experiences of labour.\nMany complementary therapies are used by women in labour, including acupuncture, mind-body techniques, massage, reflexology, herbal medicines or homoeopathy, hypnosis, music and aromatherapy. Mind-body techniques for relaxation can be widely accessible to women through the teaching of these techniques during antenatal classes. The relaxation techniques include guided imagery, progressive relaxation and breathing techniques. We also include yoga and music in this review. Other Cochrane Reviews cover hypnosis in labour, manual methods (like massage and reflexology), aromatherapy and acupuncture/acupressure. Many of these relaxation techniques are coping strategies used to reduce the experience of pain. These techniques utilise practices that aim to reduce stress and reduce the perception of pain. It is important to examine if these therapies work and are safe, to enable women to make informed decisions about their care." } ]

[ { "role": "user", "content": "Abstract: Background\nThe Informant Questionnaire for Cognitive Decline in the Elderly (IQCODE) is a structured interview based on informant responses that is used to assess for possible dementia. IQCODE has been used for retrospective or contemporaneous assessment of cognitive decline. There is considerable interest in tests that may identify those at future risk of developing dementia. Assessing a population free of dementia for the prospective development of dementia is an approach often used in studies of dementia biomarkers. In theory, questionnaire-based assessments, such as IQCODE, could be used in a similar way, assessing for dementia that is diagnosed on a later (delayed) assessment.\nObjectives\nTo determine the accuracy of the informant-based questionnaire IQCODE for the early detection of dementia across a variety of health care settings.\nSearch methods\nWe searched these sources on 16 January 2016: ALOIS (Cochrane Dementia and Cognitive Improvement Group), MEDLINE Ovid SP, Embase Ovid SP, PsycINFO Ovid SP, BIOSIS Previews on Thomson Reuters Web of Science, Web of Science Core Collection (includes Conference Proceedings Citation Index) on Thomson Reuters Web of Science, CINAHL EBSCOhost, and LILACS BIREME. We also searched sources specific to diagnostic test accuracy: MEDION (Universities of Maastricht and Leuven); DARE (Database of Abstracts of Reviews of Effects, in the Cochrane Library); HTA Database (Health Technology Assessment Database, in the Cochrane Library), and ARIF (Birmingham University). We checked reference lists of included studies and reviews, used searches of included studies in PubMed to track related articles, and contacted research groups conducting work on IQCODE for dementia diagnosis to try to find additional studies. We developed a sensitive search strategy; search terms were designed to cover key concepts using several different approaches run in parallel, and included terms relating to cognitive tests, cognitive screening, and dementia. We used standardised database subject headings, such as MeSH terms (in MEDLINE) and other standardised headings (controlled vocabulary) in other databases, as appropriate.\nSelection criteria\nWe selected studies that included a population free from dementia at baseline, who were assessed with the IQCODE and subsequently assessed for the development of dementia over time. The implication was that at the time of testing, the individual had a cognitive problem sufficient to result in an abnormal IQCODE score (defined by the study authors), but not yet meeting dementia diagnostic criteria.\nData collection and analysis\nWe screened all titles generated by the electronic database searches, and reviewed abstracts of all potentially relevant studies. Two assessors independently checked the full papers for eligibility and extracted data. We determined quality assessment (risk of bias and applicability) using the QUADAS-2 tool, and reported quality using the STARDdem tool.\nMain results\nFrom 85 papers describing IQCODE, we included three papers, representing data from 626 individuals. Of this total, 22% (N = 135/626) were excluded because of prevalent dementia. There was substantial attrition; 47% (N = 295) of the study population received reference standard assessment at first follow-up (three to six months) and 28% (N = 174) received reference standard assessment at final follow-up (one to three years). Prevalence of dementia ranged from 12% to 26% at first follow-up and 16% to 35% at final follow-up.\nThe three studies were considered to be too heterogenous to combine, so we did not perform meta-analyses to describe summary estimates of interest. Included patients were poststroke (two papers) and hip fracture (one paper). The IQCODE was used at three thresholds of positivity (higher than 3.0, higher than 3.12 and higher than 3.3) to predict those at risk of a future diagnosis of dementia. Using a cut-off of 3.0, IQCODE had a sensitivity of 0.75 (95%CI 0.51 to 0.91) and a specificity of 0.46 (95%CI 0.34 to 0.59) at one year following stroke. Using a cut-off of 3.12, the IQCODE had a sensitivity of 0.80 (95%CI 0.44 to 0.97) and specificity of 0.53 (95C%CI 0.41 to 0.65) for the clinical diagnosis of dementia at six months after hip fracture. Using a cut-off of 3.3, the IQCODE had a sensitivity of 0.84 (95%CI 0.68 to 0.94) and a specificity of 0.87 (95%CI 0.76 to 0.94) for the clinical diagnosis of dementia at one year after stroke.\nIn generaI, the IQCODE was sensitive for identification of those who would develop dementia, but lacked specificity. Methods for both excluding prevalent dementia at baseline and assessing for the development of dementia were varied, and had the potential to introduce bias.\nAuthors' conclusions\nIncluded studies were heterogenous, recruited from specialist settings, and had potential biases. The studies identified did not allow us to make specific recommendations on the use of the IQCODE for the future detection of dementia in clinical practice. The included studies highlighted the challenges of delayed verification dementia research, with issues around prevalent dementia assessment, loss to follow-up over time, and test non-completion potentially limiting the studies. Future research should recognise these issues and have explicit protocols for dealing with them.\n\nGiven the provided abstract, please respond to the following query: \"Background\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "Accurately identifying people with dementia is an area of public and professional concern. Dementia is often not diagnosed until late in the disease, and this may limit timely access to appropriate health and social support. There is a growing interest in tests that detect dementia at an early stage, before symptoms have become problematic or noticeable. One way to do this is to test a person and then re-assess them over time to see if they have developed dementia.\nOur review focused on the accuracy of a questionnaire-based assessment for dementia, called the IQCODE (Informant Questionnaire for Cognitive Decline in the Elderly). We described whether the initial IQCODE score can identify people who will develop dementia months or years after their first IQCODE assessment.\nWe searched electronic databases of published research studies, looking for all studies that looked at IQCODE and a later diagnosis of dementia. We searched from the first available papers in scientific databases up to and including January 2016." } ]

[ { "role": "user", "content": "Abstract: Background\nPneumonia is a common and potentially serious illness. Corticosteroids have been suggested for the treatment of different types of infection, however their role in the treatment of pneumonia remains unclear. This is an update of a review published in 2011.\nObjectives\nTo assess the efficacy and safety of corticosteroids in the treatment of pneumonia.\nSearch methods\nWe searched the Cochrane Acute Respiratory Infections Group's Specialised Register, CENTRAL, MEDLINE, Embase, and LILACS on 3 March 2017, together with relevant conference proceedings and references of identified trials. We also searched three trials registers for ongoing and unpublished trials.\nSelection criteria\nWe included randomised controlled trials (RCTs) that assessed systemic corticosteroid therapy, given as adjunct to antibiotic treatment, versus placebo or no corticosteroids for adults and children with pneumonia.\nData collection and analysis\nWe used standard methodological procedures expected by Cochrane. Two review authors independently assessed risk of bias and extracted data. We contacted study authors for additional information. We estimated risk ratios (RR) with 95% confidence intervals (CI) and pooled data using the Mantel–Haenszel fixed-effect model when possible.\nMain results\nWe included 17 RCTs comprising a total of 2264 participants; 13 RCTs included 1954 adult participants, and four RCTs included 310 children. This update included 12 new studies, excluded one previously included study, and excluded five new trials. One trial awaits classification.\nAll trials limited inclusion to inpatients with community-acquired pneumonia (CAP), with or without healthcare-associated pneumonia (HCAP). We assessed the risk of selection bias and attrition bias as low or unclear overall. We assessed performance bias risk as low for nine trials, unclear for one trial, and high for seven trials. We assessed reporting bias risk as low for three trials and high for the remaining 14 trials.\nCorticosteroids significantly reduced mortality in adults with severe pneumonia (RR 0.58, 95% CI 0.40 to 0.84; moderate-quality evidence), but not in adults with non-severe pneumonia (RR 0.95, 95% CI 0.45 to 2.00). Early clinical failure rates (defined as death from any cause, radiographic progression, or clinical instability at day 5 to 8) were significantly reduced with corticosteroids in people with severe and non-severe pneumonia (RR 0.32, 95% CI 0.15 to 0.7; and RR 0.68, 95% CI 0.56 to 0.83, respectively; high-quality evidence). Corstocosteroids reduced time to clinical cure, length of hospital and intensive care unit stays, development of respiratory failure or shock not present at pneumonia onset, and rates of pneumonia complications.\nAmong children with bacterial pneumonia, corticosteroids reduced early clinical failure rates (defined as for adults, RR 0.41, 95% CI 0.24 to 0.70; high-quality evidence) based on two small, clinically heterogeneous trials, and reduced time to clinical cure.\nHyperglycaemia was significantly more common in adults treated with corticosteroids (RR 1.72, 95% CI 1.38 to 2.14). There were no significant differences between corticosteroid-treated people and controls for other adverse events or secondary infections (RR 1.19, 95% CI 0.73 to 1.93).\nAuthors' conclusions\nCorticosteroid therapy reduced mortality and morbidity in adults with severe CAP; the number needed to treat for an additional beneficial outcome was 18 patients (95% CI 12 to 49) to prevent one death. Corticosteroid therapy reduced morbidity, but not mortality, for adults and children with non-severe CAP. Corticosteroid therapy was associated with more adverse events, especially hyperglycaemia, but the harms did not seem to outweigh the benefits.\n\nGiven the provided abstract, please respond to the following query: \"Study characteristics\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "We included 17 studies evaluating systemic corticosteroid therapy (given intravenously or by tablets) for people with pneumonia (2264 participants; 1954 adults and 310 children). We included 12 new studies in this update and excluded one previously included study. All included studies evaluated people who had acquired pneumonia in the community (community-acquired pneumonia (CAP)) being treated in the hospital; no studies assessed people who had developed pneumonia while in hospital or who were on breathing machines (mechanically ventilated)." } ]

[ { "role": "user", "content": "Abstract: Background\nEarly accurate detection of all skin cancer types is essential to guide appropriate management, reduce morbidity and improve survival. Basal cell carcinoma (BCC) is usually localised to the skin but has potential to infiltrate and damage surrounding tissue, while cutaneous squamous cell carcinoma (cSCC) and melanoma have a much higher potential to metastasise and ultimately lead to death. Exfoliative cytology is a non-invasive test that uses the Tzanck smear technique to identify disease by examining the structure of cells obtained from scraped samples. This simple procedure is a less invasive diagnostic test than a skin biopsy, and for BCC it has the potential to provide an immediate diagnosis that avoids an additional clinic visit to receive skin biopsy results. This may benefit patients scheduled for either Mohs micrographic surgery or non-surgical treatments such as radiotherapy. A cytology scrape can never give the same information as a skin biopsy, however, so it is important to better understand in which skin cancer situations it may be helpful.\nObjectives\nTo determine the diagnostic accuracy of exfoliative cytology for detecting basal cell carcinoma (BCC) in adults, and to compare its accuracy with that of standard diagnostic practice (visual inspection with or without dermoscopy). Secondary objectives were: to determine the diagnostic accuracy of exfoliative cytology for detecting cSCC, invasive melanoma and atypical intraepidermal melanocytic variants, and any other skin cancer; and for each of these secondary conditions to compare the accuracy of exfoliative cytology with visual inspection with or without dermoscopy in direct test comparisons; and to determine the effect of observer experience.\nSearch methods\nWe undertook a comprehensive search of the following databases from inception up to August 2016: Cochrane Central Register of Controlled Trials; MEDLINE; Embase; CINAHL; CPCI; Zetoc; Science Citation Index; US National Institutes of Health Ongoing Trials Register; NIHR Clinical Research Network Portfolio Database; and the World Health Organization International Clinical Trials Registry Platform. We also studied the reference lists of published systematic review articles.\nSelection criteria\nStudies evaluating exfoliative cytology in adults with lesions suspicious for BCC, cSCC or melanoma, compared with a reference standard of histological confirmation.\nData collection and analysis\nTwo review authors independently extracted all data using a standardised data extraction and quality assessment form (based on QUADAS-2). Where possible we estimated summary sensitivities and specificities using the bivariate hierarchical model.\nMain results\nWe synthesised the results of nine studies contributing a total of 1655 lesions to our analysis, including 1120 BCCs (14 datasets), 41 cSCCs (amongst 401 lesions in 2 datasets), and 10 melanomas (amongst 200 lesions in 1 dataset). Three of these datasets (one each for BCC, melanoma and any malignant condition) were derived from one study that also performed a direct comparison with dermoscopy. Studies were of moderate to poor quality, providing inadequate descriptions of participant selection, thresholds used to make cytological and histological diagnoses, and blinding. Reporting of participants' prior referral pathways was particularly poor, as were descriptions of the cytodiagnostic criteria used to make diagnoses. No studies evaluated the use of exfoliative cytology as a primary diagnostic test for detecting BCC or other skin cancers in lesions suspicious for skin cancer. Pooled data from seven studies using standard cytomorphological criteria (but various stain methods) to detect BCC in participants with a high clinical suspicion of BCC estimated the sensitivity and specificity of exfoliative cytology as 97.5% (95% CI 94.5% to 98.9%) and 90.1% (95% CI 81.1% to 95.1%). respectively. When applied to a hypothetical population of 1000 clinically suspected BCC lesions with a median observed BCC prevalence of 86%, exfoliative cytology would miss 21 BCCs and would lead to 14 false positive diagnoses of BCC. No false positive cases were histologically confirmed to be melanoma. Insufficient data are available to make summary statements regarding the accuracy of exfoliative cytology to detect melanoma or cSCC, or its accuracy compared to dermoscopy.\nAuthors' conclusions\nThe utility of exfoliative cytology for the primary diagnosis of skin cancer is unknown, as all included studies focused on the use of this technique for confirming strongly suspected clinical diagnoses. For the confirmation of BCC in lesions with a high clinical suspicion, there is evidence of high sensitivity and specificity. Since decisions to treat low-risk BCCs are unlikely in practice to require diagnostic confirmation given that clinical suspicion is already high, exfoliative cytology might be most useful for cases of BCC where the treatments being contemplated require a tissue diagnosis (e.g. radiotherapy). The small number of included studies, poor reporting and varying methodological quality prevent us from drawing strong conclusions to guide clinical practice. Despite insufficient data on the use of cytology for cSCC or melanoma, it is unlikely that cytology would be useful in these scenarios since preservation of the architecture of the whole lesion that would be available from a biopsy provides crucial diagnostic information. Given the paucity of good quality data, appropriately designed prospective comparative studies may be required to evaluate both the diagnostic value of exfoliative cytology by comparison to dermoscopy, and its confirmatory value in adequately reported populations with a high probability of BCC scheduled for further treatment requiring a tissue diagnosis.\n\nGiven the provided abstract, please respond to the following query: \"Who do the results of this review apply to?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "Studies were conducted in the UK, across Europe and in Australia. Study authors rarely described patient characteristics, such as age and location of the lesion. The percentage of people included in the studies with a final diagnosis of BCC ranged from 18% to 90% (nine studies). For cSCC it was 4% and 18% (two studies), and for melanoma it was 5% (one study). It was not possible to tell from the studies how clinicians had decided that study participants had lesions that could be a skin cancer." } ]

[ { "role": "user", "content": "Abstract: Background\nHeart failure (HF) is a chronic disease with significant impact on quality of life and presents many challenges to those diagnosed with the condition, due to a seemingly complex daily regimen of self-care which includes medications, monitoring of weight and symptoms, identification of signs of deterioration and follow-up and interaction with multiple healthcare services. Education is vital for understanding the importance of this regimen, and adhering to it. Traditionally, education has been provided to people with heart failure in a face-to-face manner, either in a community or a hospital setting, using paper-based materials or video/DVD presentations. In an age of rapidly-evolving technology and uptake of smartphones and tablet devices, mHealth-based technology (defined by the World Health Organization as mobile and wireless technologies to achieve health objectives) is an innovative way to provide health education which has the benefit of being able to reach people who are unable or unwilling to access traditional heart failure education programmes and services.\nObjectives\nTo systematically review and quantify the potential benefits and harms of mHealth-delivered education for people with heart failure.\nSearch methods\nWe performed an extensive search of bibliographic databases and registries (CENTRAL, MEDLINE, Embase, CINAHL, PsycINFO, IEEE Xplore, ClinicalTrials.gov and WHO International Clinical Trials Registry Platform (ICTRP) Search Portal), using terms to identify HF, education and mHealth. We searched all databases from their inception to October 2019 and imposed no restriction on language of publication.\nSelection criteria\nWe included studies if they were conducted as a randomised controlled trial (RCT), involving adults (≥ 18 years) with a diagnosis of HF. We included trials comparing mHealth-delivered education such as internet and web-based education programmes for use on smartphones and tablets (including apps) and other mobile devices, SMS messages and social media-delivered education programmes, versus usual HF care.\nData collection and analysis\nTwo review authors independently selected studies, assessed risks of bias, and extracted data from all included studies. We calculated the mean difference (MD) or standardised mean difference (SMD) for continuous data and the odds ratio (OR) for dichotomous data with a 95% confidence interval (CI). We assessed heterogeneity using the I2 statistic and assessed the quality of evidence using GRADE criteria.\nMain results\nWe include five RCTs (971 participants) of mHealth-delivered education interventions for people with HF in this review. The number of trial participants ranged from 28 to 512 participants. Mean age of participants ranged from 60 years to 75 years, and 63% of participants across the studies were men. Studies originated from Australia, China, Iran, Sweden, and The Netherlands. Most studies included participants with symptomatic HF, NYHA Class II - III.\nThree studies addressed HF knowledge, revealing that the use of mHealth-delivered education programmes showed no evidence of a difference in HF knowledge compared to usual care (MD 0.10, 95% CI −0.2 to 0.40, P = 0.51, I2 = 0%; 3 studies, 411 participants; low-quality evidence). One study assessing self-efficacy reported that both study groups had high levels of self-efficacy at baseline and uncertainty in the evidence for the intervention (MD 0.60, 95% CI −0.57 to 1.77; P = 0.31; 1 study, 29 participants; very low-quality evidence).Three studies evaluated HF self-care using different scales. We did not pool the studies due to the heterogenous nature of the outcome measures, and the evidence is uncertain. None of the studies reported adverse events. Four studies examined health-related quality of life (HRQoL). There was uncertainty in the evidence for the use of mHealth-delivered education on HRQoL (MD −0.10, 95% CI −2.35 to 2.15; P = 0.93, I2 = 61%; 4 studies, 942 participants; very low-quality evidence). Three studies reported on HF-related hospitalisation. The use of mHealth-delivered education may result in little to no difference in HF-related hospitalisation (OR 0.74, 95% CI 0.52 to 1.06; P = 0.10, I2 = 0%; 3 studies, 894 participants; low-quality evidence). We downgraded the quality of the studies due to limitations in study design and execution, heterogeneity, wide confidence intervals and fewer than 500 participants in the analysis.\nAuthors' conclusions\nWe found that the use of mHealth-delivered educational interventions for people with HF shows no evidence of a difference in HF knowledge; uncertainty in the evidence for self-efficacy, self-care and health-related quality of life; and may result in little to no difference in HF-related hospitalisations. The identification of studies currently underway and those awaiting classification indicate that this is an area of research from which further evidence will emerge in the short and longer term.\n\nGiven the provided abstract, please respond to the following query: \"Study characteristics\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "We include in this review five randomised controlled trials (971 participants) of mHealth-delivered education interventions for people with HF. The average age of participants ranged from 60 years to 75 years and 63% of participants were men. Studies came from Australia, China, Iran, Sweden and The Netherlands." } ]

[ { "role": "user", "content": "Abstract: Background\nThis is an update of the Cochrane Review last published in 2017. Survivors of stroke due to intracerebral haemorrhage (ICH) are at risk of major adverse cardiovascular events (MACE). Antithrombotic (antiplatelet or anticoagulant) treatments may lower the risk of ischaemic MACE after ICH, but they may increase the risk of bleeding.\nObjectives\nTo determine the overall effectiveness and safety of antithrombotic drugs on MACE and its components for people with ICH.\nSearch methods\nWe searched the Cochrane Stroke Group Trials Register (5 October 2021). We also searched the Cochrane Central Register of Controlled Trials (CENTRAL: the Cochrane Library 2021, Issue 10), MEDLINE Ovid (from 1948 to October 2021) and Embase Ovid (from 1980 to October 2021). The online registries of clinical trials searched were the US National Institutes of Health Ongoing Trials Register ClinicalTrials.gov (clinicaltrials.gov) and the World Health Organization (WHO) International Clinical Trials Registry Platform (ICTRP) (5 October 2021). We screened the reference lists of included randomised controlled trials (RCTs) for additional, potentially relevant RCTs.\nSelection criteria\nWe selected RCTs in which participants with ICH of any age were allocated to a class of antithrombotic treatment as intervention or comparator.\nData collection and analysis\nIn accordance with standard methodological procedures recommended by Cochrane, two review authors assessed each selected RCT for its risk of bias and extracted data independently. The primary outcome was a composite of MACE, and secondary outcomes included death, individual components of the MACE composite, ICH growth, functional status and cognitive status. We estimated effects using the frequency of outcomes that occurred during the entire duration of follow-up and calculated a risk ratio (RR) for each RCT. We grouped RCTs separately for analysis according to 1) the class(es) of antithrombotic treatment used for the intervention and comparator, and 2) the duration of antithrombotic treatment use (short term versus long term). We pooled the intention-to-treat populations of RCTs using a fixed-effect model for meta-analysis, but used a random-effects model if RCTs differed substantially in their design or there was considerable heterogeneity (I2 ≥ 75%) in their results. We applied GRADE to assess the certainty of the evidence.\nMain results\nWe identified seven new completed RCTs for this update, resulting in the inclusion of a total of nine RCTs based in secondary care, comprising 1491 participants (average age ranged from 61 to 79 years and the proportion of men ranged from 44% to 67%). The proportion of included RCTs at low risk of bias, by category was: random sequence generation (67%), allocation concealment (67%), performance (22%), detection (78%), attrition (89%), and reporting (78%).\nFor starting versus avoiding short-term prophylactic dose anticoagulation after ICH, no RCT reported MACE. The evidence is very uncertain about the effect of starting short-term prophylactic dose anticoagulation on death (RR 1.00, 95% CI 0.59 to 1.70, P = 1.00; 3 RCTs; very low-certainty evidence), venous thromboembolism (RR 0.84, 95% CI 0.51 to 1.37, P = 0.49; 4 RCTs; very low-certainty evidence), ICH (RR 0.24, 95% CI 0.04 to 1.38, P = 0.11; 2 RCTs; very low-certainty evidence), and independent functional status (RR 2.03, 95% CI 0.78 to 5.25, P = 0.15; 1 RCT; very low-certainty evidence) over 90 days.\nFor starting versus avoiding long-term therapeutic dose oral anticoagulation for atrial fibrillation after ICH, starting long-term therapeutic dose oral anticoagulation probably reduces MACE (RR 0.61, 95% CI 0.40 to 0.94, P = 0.02; 3 RCTs; moderate-certainty evidence) and probably reduces all major occlusive vascular events (RR 0.27, 95% CI 0.14 to 0.53, P = 0.0002; 3 RCTs; moderate-certainty evidence), but probably results in little to no difference in death (RR 1.05, 95% CI 0.62 to 1.78, P = 0.86; 3 RCTs; moderate-certainty evidence), probably increases intracranial haemorrhage (RR 2.43, 95% CI 0.88 to 6.73, P = 0.09; 3 RCTs; moderate-certainty evidence), and may result in little to no difference in independent functional status (RR 0.98, 95% CI 0.78 to 1.24, P = 0.87; 2 RCTs; low-certainty evidence) over one to three years.\nFor starting versus avoiding long-term antiplatelet therapy after ICH, the evidence is uncertain about the effects of starting long-term antiplatelet therapy on MACE (RR 0.89, 95% CI 0.64 to 1.22, P = 0.46; 1 RCT; moderate-certainty evidence), death (RR 1.08, 95% CI 0.76 to 1.53, P = 0.66; 1 RCT; moderate-certainty evidence), all major occlusive vascular events (RR 1.03, 95% CI 0.68 to 1.55, P = 0.90; 1 RCT; moderate-certainty evidence), ICH (RR 0.52, 95% CI 0.27 to 1.03, P = 0.06; 1 RCT; moderate-certainty evidence) and independent functional status (RR 0.95, 95% CI 0.77 to 1.18, P = 0.67; 1 RCT; moderate-certainty evidence) over a median follow-up of two years.\nFor adults within 180 days of non-cardioembolic ischaemic stroke or transient ischaemic attack and a clinical history of prior ICH, there was no evidence of an effect of long-term cilostazol compared to aspirin on MACE (RR 1.33, 95% CI 0.74 to 2.40, P = 0.34; subgroup of 1 RCT; low-certainty evidence), death (RR 1.65, 95% CI 0.55 to 4.91, P = 0.37; subgroup of 1 RCT; low-certainty evidence), or ICH (RR 1.29, 95% CI 0.35 to 4.69, P = 0.70; subgroup of 1 RCT; low-certainty evidence) over a median follow-up of 1.8 years; all major occlusive vascular events and functional status were not reported.\nAuthors' conclusions\nWe did not identify beneficial or hazardous effects of short-term prophylactic dose parenteral anticoagulation and long-term oral antiplatelet therapy after ICH on important outcomes. Although there was a significant reduction in MACE and all major occlusive vascular events after long-term treatment with therapeutic dose oral anticoagulation for atrial fibrillation after ICH, the pooled estimates were imprecise, the certainty of evidence was only moderate, and effects on other important outcomes were uncertain. Large RCTs with a low risk of bias are required to resolve the ongoing dilemmas about antithrombotic treatment after ICH.\n\nGiven the provided abstract, please respond to the following query: \"Background\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "People with stroke due to brain haemorrhage are more likely to develop clots in their blood vessels than people without brain haemorrhage. Immobility early after the stroke can cause clots in the veins of the legs and pelvis. Patients' underlying medical conditions in both the short and long term after the stroke can also cause clots in the arteries of the lungs, brain, heart, legs or other organs. These clots can cause serious illness or death. Antithrombotic drugs can prevent clots. However, these drugs can also lead to bleeding problems, which can cause serious illness or death. Whether antithrombotic drugs benefit or harm patients after brain haemorrhage is unknown. This is an update of a Cochrane Review, which was last published in 2017." } ]

[ { "role": "user", "content": "Abstract: Background\nBefore extraction and synthetic chemistry were invented, musculoskeletal complaints were treated with preparations from medicinal plants. They were either administered orally or topically. In contrast to the oral medicinal plant products, topicals act in part as counterirritants or are toxic when given orally.\nObjectives\nTo update the previous Cochrane review of herbal therapy for osteoarthritis from 2000 by evaluating the evidence on effectiveness for topical medicinal plant products.\nSearch methods\nDatabases for mainstream and complementary medicine were searched using terms to include all forms of arthritis combined with medicinal plant products. We searched electronic databases (Cochrane Central Register of Controlled Trials (CENTRAL), MEDLINE, EMBASE, AMED, CINAHL, ISI Web of Science, World Health Organization Clinical Trials Registry Platform) to February 2013, unrestricted by language. We also searched the reference lists from retrieved trials.\nSelection criteria\nRandomised controlled trials of herbal interventions used topically, compared with inert (placebo) or active controls, in people with osteoarthritis were included.\nData collection and analysis\nTwo review authors independently selected trials for inclusion, assessed the risk of bias of included studies and extracted data.\nMain results\nSeven studies (seven different medicinal plant interventions; 785 participants) were included. Single studies (five studies, six interventions) and non-comparable studies (two studies, one intervention) precluded pooling of results.\nModerate evidence from a single study of 174 people with hand osteoarthritis indicated that treatment with Arnica extract gel probably results in similar benefits as treatment with ibuprofen (non-steroidal anti-inflammatory drug) with a similar number of adverse events. Mean pain in the ibuprofen group was 44.2 points on a 100 point scale; treatment with Arnica gel reduced the pain by 4 points after three weeks: mean difference (MD) -3.8 points (95% confidence intervals (CI) -10.1 to 2.5), absolute reduction 4% (10% reduction to 3% increase). Hand function was 7.5 points on a 30 point scale in the ibuprofen-treated group; treatment with Arnica gel reduced function by 0.4 points (MD -0.4, 95% CI -1.75 to 0.95), absolute improvement 1% (6% improvement to 3% decline)). Total adverse events were higher in the Arnica gel group (13% compared to 8% in the ibuprofen group): relative risk (RR) 1.65 (95% CI 0.72 to 3.76).\nModerate quality evidence from a single trial of 99 people with knee osteoarthritis indicated that compared with placebo, Capsicum extract gel probably does not improve pain or knee function, and is commonly associated with treatment-related adverse events including skin irritation and a burning sensation. At four weeks follow-up, mean pain in the placebo group was 46 points on a 100 point scale; treatment with Capsicum extract reduced pain by 1 point (MD -1, 95% CI -6.8 to 4.8), absolute reduction of 1% (7% reduction to 5% increase). Mean knee function in the placebo group was 34.8 points on a 96 point scale at four weeks; treatment with Capsicum extract improved function by a mean of 2.6 points (MD -2.6, 95% CI -9.5 to 4.2), an absolute improvement of 3% (10% improvement to 4% decline). Adverse event rates were greater in the Capsicum extract group (80% compared with 20% in the placebo group, rate ratio 4.12, 95% CI 3.30 to 5.17). The number needed to treat to result in adverse events was 2 (95% CI 1 to 2).\nModerate evidence from a single trial of 220 people with knee osteoarthritis suggested that comfrey extract gel probably improves pain without increasing adverse events. At three weeks, the mean pain in the placebo group was 83.5 points on a 100 point scale. Treatment with comfrey reduced pain by a mean of 41.5 points (MD -41.5, 95% CI -48 to -34), an absolute reduction of 42% (34% to 48% reduction). Function was not reported. Adverse events were similar: 6% (7/110) reported adverse events in the comfrey group compared with 14% (15/110) in the placebo group (RR 0.47, 95% CI 0.20 to 1.10).\nAlthough evidence from a single trial indicated that adhesive patches containing Chinese herbal mixtures FNZG and SJG may improve pain and function, the clinical applicability of these findings are uncertain because participants were only treated and followed up for seven days. We are also uncertain if other topical herbal products (Marhame-Mafasel compress, stinging nettle leaf) improve osteoarthritis symptoms due to the very low quality evidence from single trials.\nNo serious side effects were reported.\nAuthors' conclusions\nAlthough the mechanism of action of the topical medicinal plant products provides a rationale basis for their use in the treatment of osteoarthritis, the quality and quantity of current research studies of effectiveness are insufficient. Arnica gel probably improves symptoms as effectively as a gel containing non-steroidal anti-inflammatory drug, but with no better (and possibly worse) adverse event profile. Comfrey extract gel probably improves pain, and Capsicum extract gel probably will not improve pain or function at the doses examined in this review. Further high quality, fully powered studies are required to confirm the trends of effectiveness identifed in studies so far.\n\nGiven the provided abstract, please respond to the following query: \"Other topical products\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "We are uncertain whether other topical herbal products affect osteoarthritis pain and function because the evidence available from these studies was of low to very low quality. FNZG patches were compared head-to-head with SJG patches. Marhame-Mafasel compress was compared to placebo. Stinging nettle leaf was compared with two placebos in two different studies of people with osteoarthritis of the thumb or of the knee." } ]

[ { "role": "user", "content": "Abstract: Background\nSuicide is a leading cause of death among post-secondary students worldwide. Suicidal thoughts and planning are common among post-secondary students. Previous reviews have examined the effectiveness of interventions for symptomatic individuals; however, many students at high risk of suicide are undiagnosed and untreated.\nObjectives\nWe evaluated the effect on suicide and suicide-related outcomes of primary suicide prevention interventions that targeted students within the post-secondary setting.\nSearch methods\nWe searched the following sources up to June 2011: Specialised Registers of two Cochrane Groups, Cochrane Central Register of Controlled Trials, and nine other databases, trial registers, conference proceedings, and websites of national and international organizations. We screened reference lists and contacted authors of included studies to identify additional studies. We updated the search in November 2013; we will include these results in the review's next update.\nSelection criteria\nWe included studies that tested an intervention for the primary prevention of suicide using a randomized controlled trial (RCT), controlled before-and-after (CBA), controlled interrupted time series (CITS), or interrupted time series (ITS) study design. Interventions targeted students within the post-secondary setting (i.e. college, university, academy, vocational, or any other post-secondary educational institution) without known mental illness, previous suicide attempt or self-harm, or suicidal ideation. Outcomes included suicides, suicide attempts, suicidal ideation, changes in suicide-related knowledge, attitudes and behavior, and availability of means of suicide.\nData collection and analysis\nWe used standardized electronic forms for data extraction, risk of bias and quality of evidence determination, and analysis. We estimated standardised mean differences (SMD) with 95% confidence intervals (CIs). We analysed studies by intervention type and study design. We summarized RCT effect sizes using random-effects models meta-analyses; and analysed statistical heterogeneity using the Chi2 test and I2 statistic. We described narratively the results from studies that used other study designs.\nMain results\nEight studies met inclusion criteria. They were heterogeneous in terms of participants, study designs, and interventions. Five of eight studies had high risk of bias. In 3 RCTs (312 participants), classroom-based didactic and experiential programs increased short-term knowledge of suicide (SMD = 1.51, 95% CI 0.57 to 2.45; moderate quality evidence) and knowledge of suicide prevention (SMD = 0.72, 95% CI 0.36 to 1.07; moderate quality evidence). The effect on suicide prevention self-efficacy in one RCT (152 participants) was uncertain (SMD = 0.20, 95% CI -0.13 to 0.54; low quality evidence). One CBA analysed the effects of an institutional policy that restricted student access to laboratory cyanide and mandated professional assessment for suicidal students. The incidence of student suicide decreased significantly at one university with the policy relative to 11 control universities, 2.00 vs. 8.68 per 100,000 (Z = 5.90; P < 0.05). Four CBAs explored effects of training 'gatekeepers' to recognize and respond to warning signs of emotional crises and suicide risk in students they encountered. The magnitude of effect sizes varied between studies. Gatekeeper training enhanced short-term suicide knowledge in students, peer advisors residing in student accommodation, and faculty and staff, and suicide prevention self-efficacy among peer advisors. There was no evidence of an effect on participants' suicide-related attitudes or behaviors. One CBA found no evidence of effects of gatekeeper training of peer advisors on suicide-related knowledge, self-efficacy, or gatekeeper behaviors measured four to six months after intervention.\nAuthors' conclusions\nWe found insufficient evidence to support widespread implementation of any programs or policies for primary suicide prevention in post-secondary educational settings. As all evaluated interventions combined primary and secondary prevention components, we were unable to determine the independent effects of primary preventive interventions. Classroom instruction and gatekeeper training increased short-term suicide-related knowledge. We found no studies that tested the effects of classroom instruction on suicidal behavior or long-term outcomes. Limited evidence suggested minimal longer-term effects of gatekeeper training on suicide-related knowledge, while no evidence was found evaluating its effect on suicidal behavior. A policy-based suicide intervention reduced student suicide, but findings have not been replicated. Our findings are limited by the overall low quality of the evidence and the lack of studies from middle- and low-income countries. Rigorously designed studies should test the effects of preventive interventions on important health outcomes, including suicidal ideation and behavior, in varying post-secondary settings.\n\nGiven the provided abstract, please respond to the following query: \"Background\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "Worldwide, suicide is a leading cause of death among post-secondary students. Suicidal thoughts and planning are common among such students. However, fewer than half of students who report suicidal thoughts or other serious mental illness have received professional treatment. There is a need for suicide prevention programs that target students who are not already known to be suicidal (\"primary prevention\")." } ]

[ { "role": "user", "content": "Abstract: Background\nImplant overdentures are one of the most common treatment options used to rehabilitate edentulous patients. Attachment systems are used to anchor the overdentures to implants. The plethora of attachment systems available dictates a need for clinicians to understand their prosthodontic and patient-related outcomes.\nObjectives\nTo compare different attachment systems for maxillary and mandibular implant overdentures by assessing prosthodontic success, prosthodontic maintenance, patient preference, patient satisfaction/quality of life and costs.\nSearch methods\nCochrane Oral Health's Information Specialist searched the following databases: Cochrane Oral Health's Trials Register (to 24 January 2018); Cochrane Central Register of Controlled Trials (CENTRAL; 2017, Issue 12) in the Cochrane Library (searched 24 January 2018); MEDLINE Ovid (1946 to 24 January 2018); and Embase Ovid (1980 to 24 January 2018). The US National Institutes of Health Trials Registry (ClinicalTrials.gov) and the World Health Organization International Clinical Trials Registry Platform were searched for ongoing trials on 24 January 2018. No restrictions were placed on the language or date of publication when searching the electronic databases.\nSelection criteria\nAll randomised controlled trials (RCTs), including cross-over trials on maxillary or mandibular implant overdentures with different attachment systems with at least 1 year follow-up.\nData collection and analysis\nFour review authors extracted data independently and assessed risk of bias for each included trial. Several corresponding authors were subsequently contacted to obtain missing information. Fixed-effect meta-analysis was used to combine the outcomes with risk ratios (RR) for dichotomous outcomes and mean differences (MD) for continuous outcomes, with 95% confidence intervals (95% CI). We used the GRADE approach to assess the quality of evidence and create 'Summary of findings' tables.\nMain results\nWe identified six RCTs with a total of 294 mandibular overdentures (including one cross-over trial). No trials on maxillary overdentures were eligible. Due to the poor reporting of the outcomes across the included trials, only limited analyses between mandibular overdenture attachment systems were possible.\nComparing ball and bar attachments, upon pooling the data regarding short-term prosthodontic success, we identified substantial heterogeneity (I2 = 97%) with inconsistency in the direction of effect, which was unexplained by clinical or methodological differences between the studies, and accordingly we did not perform meta-analyses for this outcome. Short-term re-treatment (repair of attachment system) was higher with ball attachments (RR 3.11, 95% CI 1.68 to 5.75; 130 participants; 2 studies; very low-quality evidence), and there was no difference between both attachment systems in short-term re-treatment (replacement of attachment system) (RR 1.18, 95% CI 0.38 to 3.71; 130 participants; 2 studies; very low-quality evidence). It is uncertain whether there is a difference in short-term prosthodontic success when ball attachments are compared with bar attachments.\nComparing ball and magnet attachments, there was no difference between them in medium-term prosthodontic success (RR 0.84, 95% CI 0.64 to 1.10; 69 participants; 1 study; very low-quality evidence), or in medium-term re-treatment (repair of attachment system) (RR 1.75, 95% CI 0.65 to 4.72; 69 participants; 1 study; very low-quality evidence). However, after 5 years, prosthodontic maintenance costs were higher when magnet attachments were used (MD -247.37 EUR, 95% CI -346.32 to -148.42; 69 participants; 1 study; very low-quality evidence). It is uncertain whether there is a difference in medium-term prosthodontic success when ball attachments are compared with magnet attachments.\nOne trial provided data for ball versus telescopic attachments and reported no difference in prosthodontic maintenance between the two systems in short-term patrix replacement (RR 6.00, 95% CI 0.86 to 41.96; 22 participants; 1 study; very low-quality evidence), matrix activation (RR 11.00, 95% CI 0.68 to 177.72; 22 participants; 1 study; very low-quality evidence), matrix replacement (RR 1.75, 95% CI 0.71 to 4.31; 22 participants; 1 study; very low-quality evidence), or in relining of the implant overdenture (RR 2.33, 95% CI 0.81 to 6.76; 22 participants; 1 study; very low-quality evidence). It is uncertain whether there is a difference in short-term prosthodontic maintenance when ball attachments are compared with telescopic attachments.\nIn the only cross-over trial included, patient preference between different attachment systems was assessed after only 3 months and not for the entire trial period of 10 years.\nAuthors' conclusions\nFor mandibular overdentures, there is insufficient evidence to determine the relative effectiveness of different attachment systems on prosthodontic success, prosthodontic maintenance, patient satisfaction, patient preference or costs. In the short term, there is some evidence that is insufficient to show a difference and where there was no evidence was reported. It was not possible to determine any preferred attachment system for mandibular overdentures.\nFor maxillary overdentures, there is no evidence (with no trials identified) to determine the relative effectiveness of different attachment systems on prosthodontic success, prosthodontic maintenance, patient satisfaction, patient preference or costs.\nFurther RCTs on edentulous cohorts must pay attention to trial design specifically using the same number of implants of the same implant system, but with different attachment systems clearly identified in control and test groups. Trials should also determine the longevity of different attachment systems and patient preferences. Trials on the current array of computer-aided designed/computer-assisted manufactured (CAD/CAM) bar attachment systems are encouraged.\n\nGiven the provided abstract, please respond to the following query: \"Key results\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "There is insufficient evidence to determine any significant differences between lower jaw implant denture attachment systems and an absence of evidence for upper jaw implant denture attachment systems. Further randomised controlled trials on people with complete tooth loss wearing dentures must pay specific attention to trial design using the same implant system and the same number of implants, but different attachment systems to determine their longevity and patient preferences." } ]

[ { "role": "user", "content": "Abstract: Background\nThe application of continuous positive airway pressure (CPAP) has been shown to have some benefits in the treatment of preterm infants with respiratory distress. CPAP has the potential to reduce lung damage, particularly if applied early before atelectasis has occurred. Early application may better conserve an infant's own surfactant stores and consequently may be more effective than later application.\nObjectives\n• To determine if early compared with delayed initiation of CPAP results in lower mortality and reduced need for intermittent positive-pressure ventilation in preterm infants in respiratory distress\n○ Subgroup analyses were planned a priori on the basis of weight (with subdivisions at 1000 grams and 1500 grams), gestation (with subdivisions at 28 and 32 weeks), and according to whether surfactant was used\n▫ Sensitivity analyses based on trial quality were also planned\n○ For this update, we have excluded trials using continuous negative pressure\nSearch methods\nWe used the standard search strategy of Cochrane Neonatal to search the Cochrane Central Register of Controlled Trials (CENTRAL; 2020, Issue 6), in the Cochrane Library; Ovid MEDLINE(R) and Epub Ahead of Print, In-Process & Other Non-Indexed Citations Daily and Versions(R); and the Cumulative Index to Nursing and Allied Health Literatue (CINAHL), on 30 June 2020. We also searched clinical trials databases and the reference lists of retrieved articles for randomised controlled trials (RCTs) and quasi-RCTs.\nSelection criteria\nWe included trials that used random or quasi-random allocation to either early or delayed CPAP for spontaneously breathing preterm infants in respiratory distress.\nData collection and analysis\nWe used the standard methods of Cochrane and Cochrane Neonatal, including independent assessment of trial quality and extraction of data by two review authors. We used the GRADE approach to assess the certainty of evidence.\nMain results\nWe found four studies that recruited a total of 119 infants. Two were quasi-randomised, and the other two did not provide details on the method of randomisation or allocation used. None of these studies used blinding of the intervention or the outcome assessor. Evidence showed uncertainty about whether early CPAP has an effect on subsequent use of intermittent positive-pressure ventilation (IPPV) (typical risk ratio (RR) 0.77, 95% confidence interval (CI) 0.43 to 1.38; typical risk difference (RD) -0.08, 95% CI -0.23 to 0.08; I² = 0%, 4 studies, 119 infants; very low-certainty evidence) or mortality (typical RR 0.93, 95% CI 0.43 to 2.03; typical RD -0.02, 95% CI -0.15 to 0.12; I² = 33%, 4 studies, 119 infants; very low-certainty evidence). The outcome 'failed treatment' was not reported in any of these studies. There was an uncertain effect on air leak (pneumothorax) (typical RR 1.09, 95% CI 0.39 to 3.04, I² = 0%, 3 studies, 98 infants; very low-certainty evidence). No trials reported intraventricular haemorrhage or necrotising enterocolitis. No cases of retinopathy of prematurity were reported in one study (21 infants). One case of bronchopulmonary dysplasia was reported in each group in one study involving 29 infants. Long-term outcomes were not reported.\nAuthors' conclusions\nAll four small trials included in this review were performed in the 1970s or the early 1980s, and we are very uncertain whether early application of CPAP confers clinical benefit in the treatment of respiratory distress, or whether it is associated with any adverse effects.\nFurther trials should be directed towards establishing the appropriate level of CPAP and the timing and method of administration of surfactant when used along with CPAP.\n\nGiven the provided abstract, please respond to the following query: \"Review question\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "We wanted to find out whether for preterm infants in respiratory distress, applying continuous positive airway pressure (CPAP) early would result in increased benefit and less harm than if it were applied later." } ]

[ { "role": "user", "content": "Abstract: Background\nRepetitive peripheral magnetic stimulation (rPMS) is a non-invasive treatment method that can penetrate to deeper structures with painless stimulation to improve motor function in people with physical impairment due to brain or nerve disorders. rPMS for people after stroke has proved to be a feasible approach to improving activities of daily living and functional ability. However, the effectiveness and safety of this intervention for people after stroke remain uncertain. This is an update of the review published in 2019.\nObjectives\nTo assess the effects of rPMS for improving activities of daily living and functional ability in people after stroke.\nSearch methods\nWe searched the Cochrane Stroke Specialised Register; the Cochrane Central Register of Controlled Trials (CENTRAL), in the Cochrane Library; MEDLINE; Embase; the Cumulative Index to Nursing and Allied Health Literature (CINAHL); PsycINFO; the Allied and Complementary Medicine Database (AMED); OTseeker: Occupational Therapy Systematic Evaluation of Evidence; the Physiotherapy Evidence Database (PEDro); Ichushi-Web; and six ongoing trial registries on 5 October 2021. We screened reference lists and contacted experts in the field. We placed no restrictions on the language or date of publication when searching the electronic databases.\nSelection criteria\nWe included randomised controlled trials (RCTs) conducted to assess the therapeutic effect of rPMS for people after stroke. The following comparisons were eligible for inclusion: 1) active rPMS only compared with 'sham' rPMS (a very weak form of stimulation or a sound only); 2) active rPMS only compared with no intervention; 3) active rPMS plus rehabilitation compared with sham rPMS plus rehabilitation; and 4) active rPMS plus rehabilitation compared with rehabilitation only.\nData collection and analysis\nTwo review authors independently assessed studies for inclusion in the review. The same review authors assessed methods and risk of bias, undertook data extraction, and evaluated the certainty of the evidence using the GRADE approach. We contacted trial authors to request unpublished information if necessary. Any disagreements were resolved through discussion.\nMain results\nWe included four trials (three parallel-group RCTs and one cross-over trial) involving a total of 139 participants. This result was unchanged from the review published in 2019. Blinding of participants and physicians was well reported in three trials, with no information on whether personnel were blinded in one trial. We judged the overall risk of bias across trials as low. Only two trials (with 63 and 18 participants, respectively) provided sufficient information to be included in the meta-analysis. We found no clear effect of rPMS on activities of daily living at the end of treatment (mean difference (MD) −3.00, 95% confidence interval (CI) −16.35 to 10.35; P = 0.66; 1 trial; 63 participants; low-certainty evidence) and at the end of follow-up (MD −2.00, 95% CI −14.86 to 10.86; P = 0.76; 1 trial; 63 participants; low-certainty evidence) when comparing rPMS plus rehabilitation versus sham rPMS plus rehabilitation. We found no statistical difference in improvement of upper limb function at the end of treatment (MD 2.00, 95% CI −4.91 to 8.91; P = 0.57; 1 trial; 63 participants; low-certainty evidence) and at the end of follow-up (MD 4.00, 95% CI −2.92 to 10.92; P = 0.26; 1 trial; 63 participants; low-certainty evidence) when comparing rPMS plus rehabilitation versus sham rPMS plus rehabilitation. We observed a decrease in spasticity of the elbow at the end of follow-up (MD −0.41, 95% CI −0.89 to 0.07; 1 trial; 63 participants; low-certainty evidence) when comparing rPMS plus rehabilitation versus sham rPMS plus rehabilitation. In terms of muscle strength, rPMS treatment was not associated with improved muscle strength of the ankle dorsiflexors at the end of treatment (MD 3.00, 95% CI −2.44 to 8.44; P = 0.28; 1 trial; 18 participants; low-certainty evidence) when compared with sham rPMS. No studies provided information on lower limb function or adverse events, including death. Based on the GRADE approach, we judged the certainty of evidence related to the primary outcome as low, owing to the small sample size of the studies.\nAuthors' conclusions\nThere is insufficient evidence to permit the drawing of any conclusions about routine use of rPMS for people after stroke. Additional trials with large sample sizes are needed to provide robust evidence for rPMS after stroke.\n\nGiven the provided abstract, please respond to the following query: \"Study characteristics\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "This is an update of the review published in 2019. We examined the evidence from four randomised controlled trials (studies where participants are randomly assigned to one of two or more treatment groups) of rPMS involving a total of 139 participants. Two studies compared rPMS against 'sham' stimulation (a very weak stimulation or a sound only). Two studies compared rPMS plus rehabilitation versus sham plus rehabilitation." } ]

[ { "role": "user", "content": "Abstract: Background\nTardive dyskinesia is a chronic and disabling abnormal movement disorder affecting the muscles of the face, neck, tongue and the limbs. It is a common side effect of long-term antipsychotic medication use in individuals with schizophrenia and other related psychotic disorders. While there are no known effective treatments for tardive dyskinesia to date, some reports suggest that pyridoxal 5 phosphate may be effective in reducing the severity of tardive dyskinesia symptoms.\nObjectives\nTo determine the effectiveness of pyridoxal 5 phosphate (vitamin B6 or Pyridoxine or Pyridoxal phosphate) in the treatment of neuroleptic-induced tardive dyskinesia among people with schizophrenia and other related psychotic disorders.\nSearch methods\nThe Cochrane schizophrenia group's register of clinical trials was searched (January 2013) using the phrase: [*Pyridoxal* OR *Pyridoxine* OR *P5P* OR *PLP* OR *tardoxal* OR *Vitamin B6* O *Vitamin B 6* R in title, abstract or index terms of REFERENCE, or interventions of STUDY. References of relevant identified studies were handsearched and where necessary, the first authors of relevant studies were contacted.\nSelection criteria\nStudies described as randomised controlled trials comparing the effectiveness pyridoxal 5 phosphate with placebo in the treatment of neuroleptic-induced tardive dyskinesia among patients with schizophrenia.\nData collection and analysis\nThe review authors independently extracted data from each selected study. For dichotomous data, we calculated risk ratios (RR) and their 95% confidence intervals (CIs) on an intention-to-treat basis based on a fixed-effect model. For continuous data, we calculated mean differences (MD) with 95% CIs, again based on a fixed-effect model. We assessed risk of bias for each included study and used GRADE (Grading of Recommendations Assessment, Development and Evaluation) approach to rate quality of evidence.\nMain results\nOf the 12 records retrieved by the search, three trials published in 2001, 2003 and 2007, involving 80 inpatients with schizophrenia, aged 18 to 71 years, admitted in a psychiatric facility and followed up for a period nine weeks to 26 weeks, were included. Overall, pyridoxal 5 phosphate produced a significant improvement in tardive dyskinesia symptoms when compared with placebo, assessed by a change in Extrapyramidal Symptoms Rating Scale (ESRS) scores from baseline to the end of the first phase of the included studies (2 RCTs n = 65, RR 19.97, CI 2.87 to 139.19, low quality evidence). The endpoint tardive dyskinesia score (a measure of its severity) assessed with the ESRS, was significantly lower among participants on pyridoxal 5 phosphate compared to those on placebo (2 RCTs n = 60, MD -4.07, CI -6.36 to -1.79, low quality evidence).\nIt was unclear whether pyridoxal 5 phosphate led to more side effects (n = 65, 2 RCTs, RR 3.97, CI 0.20 to 78.59, low quality evidence) or caused deterioration in tardive dyskinesia symptoms when compared to placebo (n = 65, 2 RCTs, RR 0.16, CI 0.01 to 3.14, low quality evidence). Five participants taking pyridoxal 5 phosphate withdrew from the study because they were not willing to take more medications while none of the participants taking placebo discontinued their medications (n = 65, 2 RCTs, RR 8.72, CI 0.51 to 149.75, low quality evidence).\nThere was no significant difference in the endpoint positive and negative psychiatric symptoms scores, measured using the Positive and Negative symptoms Scale (PANSS) between participants taking pyridoxal 5 phosphate and those taking placebo. For the positive symptoms: (n = 15, 1 RCT, MD -1.50, CI -4.80 to 1.80, low quality evidence). For negative the symptoms: (n = 15, 1 RCT, MD -1.10, CI -5.92 to 3.72, low quality evidence).\nAuthors' conclusions\nPyridoxal 5 phosphate may have some benefits in reducing the severity of tardive dyskinesia symptoms among individuals with schizophrenia. However, the quality of evidence supporting the effectiveness of pyridoxal 5 phosphate in treating tardive dyskinesia is low, based on few studies, short follow-up periods, small sample sizes and inadequate adherence to standardised reporting guidelines for randomised controlled trials among the included studies.\n\nGiven the provided abstract, please respond to the following query: \"Quality of the evidence\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": ".\nEvidence is weak. The number of studies and participants is few. The quality of studies is low. Better evidence could be gathered by better designed, conducted and reported trials.\nBen Gray, Senior Peer Researcher, McPin Foundation. http://mcpin.org/." } ]

[ { "role": "user", "content": "Abstract: Background\nUnconditional cash transfers (UCTs; provided without obligation) for reducing poverty and vulnerabilities (e.g. orphanhood, old age, or HIV infection) are a social protection intervention addressing a key social determinant of health (income) in low- and middle-income countries (LMICs). The relative effectiveness of UCTs compared with conditional cash transfers (CCTs; provided only if recipients follow prescribed behaviours, e.g. use a health service or attend school) is unknown.\nObjectives\nTo assess the effects of UCTs on health services use and health outcomes in children and adults in LMICs. Secondary objectives are to assess the effects of UCTs on social determinants of health and healthcare expenditure, and to compare the effects of UCTs versus CCTs.\nSearch methods\nFor this update, we searched 15 electronic academic databases, including CENTRAL, MEDLINE and EconLit, in September 2021. We also searched four electronic grey literature databases, websites of key organisations and reference lists of previous systematic reviews, key journals and included study records.\nSelection criteria\nWe included both parallel-group and cluster-randomised controlled trials (C-RCTs), quasi-RCTs, cohort studies, controlled before-and-after studies (CBAs), and interrupted time series studies of UCT interventions in children (0 to 17 years) and adults (≥ 18 years) in LMICs. Comparison groups received either no UCT, a smaller UCT or a CCT. Our primary outcomes were any health services use or health outcome.\nData collection and analysis\nTwo review authors independently screened potentially relevant records for inclusion, extracted data and assessed the risk of bias. We obtained missing data from study authors if feasible. For C-RCTs, we generally calculated risk ratios for dichotomous outcomes from crude frequency measures in approximately correct analyses. Meta-analyses applied the inverse variance or Mantel-Haenszel method using a random-effects model. Where meta-analysis was impossible, we synthesised results using vote counting based on effect direction. We assessed the certainty of the evidence using GRADE.\nMain results\nWe included 34 studies (25 studies of 20 C-RCTs, six CBAs, and three cohort studies) involving 1,140,385 participants (45,538 children, 1,094,847 adults) and 50,095 households in Africa, the Americas and South-East Asia in our meta-analyses and narrative syntheses. These analysed 29 independent data sets. The 24 UCTs identified, including one basic universal income intervention, were pilot or established government programmes or research experiments. The cash value was equivalent to 1.3% to 81.9% of the annualised gross domestic product per capita. All studies compared a UCT with no UCT; three studies also compared a UCT with a CCT. Most studies carried an overall high risk of bias (i.e. often selection or performance bias, or both). Most studies were funded by national governments or international organisations, or both.\nThroughout the review, we use the words 'probably' to indicate moderate-certainty evidence, 'may/maybe' for low-certainty evidence, and 'uncertain' for very low-certainty evidence.\nHealth services use\nWe assumed greater use of any health services to be beneficial. UCTs may not have impacted the likelihood of having used any health service in the previous 1 to 12 months, when participants were followed up between 12 and 24 months into the intervention (risk ratio (RR) 1.04, 95% confidence interval (CI) 1.00 to 1.09; I2 = 2%; 5 C-RCTs, 4972 participants; low-certainty evidence).\nHealth outcomes\nAt one to two years, UCTs probably led to a clinically meaningful, very large reduction in the likelihood of having had any illness in the previous two weeks to three months (RR 0.79, 95% CI 0.67 to 0.92; I2 = 53%; 6 C-RCTs, 9367 participants; moderate-certainty evidence). UCTs may have increased the likelihood of having been food secure over the previous month, at 13 to 36 months into the intervention (RR 1.25, 95% CI 1.09 to 1.45; I2 = 85%; 5 C-RCTs, 2687 participants; low-certainty evidence). UCTs may have increased participants' level of dietary diversity over the previous week, when assessed with the Household Dietary Diversity Score and followed up 24 months into the intervention (mean difference (MD) 0.59 food categories, 95% CI 0.18 to 1.01; I2 = 79%; 4 C-RCTs, 9347 participants; low-certainty evidence). Despite several studies providing relevant evidence, the effects of UCTs on the likelihood of being moderately stunted and on the level of depression remain uncertain. We found no study on the effect of UCTs on mortality risk.\nSocial determinants of health\nUCTs probably led to a clinically meaningful, moderate increase in the likelihood of currently attending school, when assessed at 12 to 24 months into the intervention (RR 1.06, 95% CI 1.04 to 1.09; I2 = 0%; 8 C-RCTs, 7136 participants; moderate-certainty evidence). UCTs may have reduced the likelihood of households being extremely poor, at 12 to 36 months into the intervention (RR 0.92, 95% CI 0.87 to 0.97; I2 = 63%; 6 C-RCTs, 3805 participants; low-certainty evidence). The evidence was uncertain for whether UCTs impacted livestock ownership, participation in labour, and parenting quality.\nHealthcare expenditure\nEvidence from eight cluster-RCTs on healthcare expenditure was too inconsistent to be combined in a meta-analysis, but it suggested that UCTs may have increased the amount of money spent on health care at 7 to 36 months into the intervention (low-certainty evidence).\nEquity, harms and comparison with CCTs\nThe effects of UCTs on health equity (or unfair and remedial health inequalities) were very uncertain. We did not identify any harms from UCTs. Three cluster-RCTs compared UCTs versus CCTs with regard to the likelihood of having used any health services or had any illness, or the level of dietary diversity, but evidence was limited to one study per outcome and was very uncertain for all three.\nAuthors' conclusions\nThis body of evidence suggests that unconditional cash transfers (UCTs) may not impact a summary measure of health service use in children and adults in LMICs. However, UCTs probably or may improve some health outcomes (i.e. the likelihood of having had any illness, the likelihood of having been food secure, and the level of dietary diversity), two social determinants of health (i.e. the likelihoods of attending school and being extremely poor), and healthcare expenditure. The evidence on the relative effectiveness of UCTs and CCTs remains very uncertain.\n\nGiven the provided abstract, please respond to the following query: \"Review question\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "In some low- and middle-income countries (LMICs), governments and other organisations sometimes give money to poor or vulnerable people (for example, older people or orphans), without requiring them to do anything in particular to receive the money ('unconditional cash transfers'). In other programmes, people can only receive this money if they engage in required behaviours, such as using health services or sending their children to school ('conditional cash transfers'). This review aimed to find out whether receiving unconditional cash transfers would improve people's use of health services and their actual health, compared with not receiving an unconditional cash transfer, receiving a smaller unconditional amount or receiving a conditional cash transfer. It also aimed to assess the effects of unconditional cash transfers on daily living conditions that determine health and healthcare spending, such as attending school, owning livestock, having a job or being extremely poor." } ]

[ { "role": "user", "content": "Abstract: Background\nHepatic encephalopathy is a brain dysfunction with neurological and psychiatric changes associated with liver insufficiency or portal-systemic shunting. The severity ranges from minor symptoms to coma. A Cochrane systematic review including 11 randomised clinical trials on branched-chain amino acids (BCAA) versus control interventions has evaluated if BCAA may benefit people with hepatic encephalopathy.\nObjectives\nTo evaluate the beneficial and harmful effects of BCAA versus any control intervention for people with hepatic encephalopathy.\nSearch methods\nWe identified trials through manual and electronic searches in The Cochrane Hepato-Biliary Group Controlled Trials Register, the Cochrane Central Register of Controlled Trials (CENTRAL), MEDLINE, Embase, Science Citation Index Expanded and Conference Proceedings Citation Index – Science, and LILACS (May 2017).\nSelection criteria\nWe included randomised clinical trials, irrespective of the bias control, language, or publication status.\nData collection and analysis\nThe authors independently extracted data based on published reports and collected data from the primary investigators. We changed our primary outcomes in this update of the review to include mortality (all cause), hepatic encephalopathy (number of people without improved manifestations of hepatic encephalopathy), and adverse events. The analyses included random-effects and fixed-effect meta-analyses. We performed subgroup, sensitivity, regression, and trial sequential analyses to evaluate sources of heterogeneity (including intervention, and participant and trial characteristics), bias (using The Cochrane Hepato-Biliary Group method), small-study effects, and the robustness of the results after adjusting for sparse data and multiplicity. We graded the quality of the evidence using the GRADE approach.\nMain results\nWe found 16 randomised clinical trials including 827 participants with hepatic encephalopathy classed as overt (12 trials) or minimal (four trials). Eight trials assessed oral BCAA supplements and seven trials assessed intravenous BCAA. The control groups received placebo/no intervention (two trials), diets (10 trials), lactulose (two trials), or neomycin (two trials). In 15 trials, all participants had cirrhosis. We classed seven trials as low risk of bias and nine trials as high risk of bias (mainly due to lack of blinding or for-profit funding). In a random-effects meta-analysis of mortality, we found no difference between BCAA and controls (risk ratio (RR) 0.88, 95% confidence interval (CI) 0.69 to 1.11; 760 participants; 15 trials; moderate quality of evidence). We found no evidence of small-study effects. Sensitivity analyses of trials with a low risk of bias found no beneficial or detrimental effect of BCAA on mortality. Trial sequential analysis showed that the required information size was not reached, suggesting that additional evidence was needed. BCAA had a beneficial effect on hepatic encephalopathy (RR 0.73, 95% CI 0.61 to 0.88; 827 participants; 16 trials; high quality of evidence). We found no small-study effects and confirmed the beneficial effect of BCAA in a sensitivity analysis that only included trials with a low risk of bias (RR 0.71, 95% CI 0.52 to 0.96). The trial sequential analysis showed that firm evidence was reached. In a fixed-effect meta-analysis, we found that BCAA increased the risk of nausea and vomiting (RR 5.56; 2.93 to 10.55; moderate quality of evidence). We found no beneficial or detrimental effects of BCAA on nausea or vomiting in a random-effects meta-analysis or on quality of life or nutritional parameters. We did not identify predictors of the intervention effect in the subgroup, sensitivity, or meta-regression analyses. In sensitivity analyses that excluded trials with a lactulose or neomycin control, BCAA had a beneficial effect on hepatic encephalopathy (RR 0.76, 95% CI 0.63 to 0.92). Additional sensitivity analyses found no difference between BCAA and lactulose or neomycin (RR 0.66, 95% CI 0.34 to 1.30).\nAuthors' conclusions\nIn this updated review, we included five additional trials. The analyses showed that BCAA had a beneficial effect on hepatic encephalopathy. We found no effect on mortality, quality of life, or nutritional parameters, but we need additional trials to evaluate these outcomes. Likewise, we need additional randomised clinical trials to determine the effect of BCAA compared with interventions such as non-absorbable disaccharides, rifaximin, or other antibiotics.\n\nGiven the provided abstract, please respond to the following query: \"Key results\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "The analyses found no effect on mortality, but that BCAA had a beneficial effect on symptoms and signs of hepatic encephalopathy. BCAA did not increase the risk of serious adverse events, but was associated with nausea and diarrhoea. When excluding trials on lactulose or neomycin, BCAA had a beneficial effect on hepatic encephalopathy. When analysing trials with a lactulose or neomycin control, we found no beneficial or detrimental effect of BCAA." } ]

[ { "role": "user", "content": "Abstract: Background\nRadical hysterectomy is one of the standard treatments for stage Ia2 to IIa cervical cancer. Bladder dysfunction caused by disruption of the pelvic autonomic nerves is a common complication following standard radical hysterectomy and can affect quality of life significantly. Nerve-sparing radical hysterectomy is a modified radical hysterectomy, developed to permit resection of oncologically relevant tissues surrounding the cervical lesion, while preserving the pelvic autonomic nerves.\nObjectives\nTo evaluate the benefits and harms of nerve-sparing radical hysterectomy in women with stage Ia2 to IIa cervical cancer.\nSearch methods\nWe searched the Cochrane Central Register of Controlled Trials (CENTRAL; 2018, Issue 4), MEDLINE via Ovid (1946 to May week 2, 2018), and Embase via Ovid (1980 to 2018, week 21). We also checked registers of clinical trials, grey literature, reports of conferences, citation lists of included studies, and key textbooks for potentially relevant studies.\nSelection criteria\nWe included randomised controlled trials (RCTs) evaluating the efficacy and safety of nerve-sparing radical hysterectomy compared to standard radical hysterectomy for women with early stage cervical cancer (stage Ia2 to IIa).\nData collection and analysis\nWe applied standard Cochrane methodology for data collection and analysis. Two review authors independently selected potentially relevant RCTs, extracted data, evaluated risk of bias of the included studies, compared results and resolved disagreements by discussion or consultation with a third review author, and assessed the certainty of evidence.\nMain results\nWe identified 1332 records as a result of the search (excluding duplicates). Of the 26 studies that potentially met the review criteria, we included four studies involving 205 women; most of the trials had unclear risks of bias. We identified one ongoing trial.\nThe analysis of overall survival was not feasible, as there were no deaths reported among women allocated to standard radical hysterectomy. However, there were two deaths in among women allocated to the nerve-sparing technique. None of the included studies reported rates of intermittent self-catheterisation over one month following surgery. We could not analyse the relative effect of the two surgical techniques on quality of life due to inconsistent data reported. Nerve-sparing radical hysterectomy reduced postoperative bladder dysfunctions in terms of a shorter time to postvoid residual volume of urine ≤ 50 mL (mean difference (MD) -13.21 days; 95% confidence interval (CI) -24.02 to -2.41; 111 women; 2 studies; low-certainty evidence) and lower volume of postvoid residual urine measured one month following operation (MD -9.59 days; 95% CI -16.28 to -2.90; 58 women; 2 study; low-certainty evidence). There were no clear differences in terms of perioperative complications (RR 0.55; 95% CI 0.24 to 1.26; 180 women; 3 studies; low-certainty evidence) and disease-free survival (HR 0.63; 95% CI 0.00 to 106.95; 86 women; one study; very low-certainty evidence) between the comparison groups.\nAuthors' conclusions\nNerve-sparing radical hysterectomy may lessen the risk of postoperative bladder dysfunction compared to the standard technique, but the certainty of this evidence is low. The very low-certainty evidence for disease-free survival and lack of information for overall survival indicate that the oncological safety of nerve-sparing radical hysterectomy for women with early stage cervical cancer remains unclear. Further large, high-quality RCTs are required to determine, if clinically meaningful differences of survival exist between these two surgical treatments.\n\nGiven the provided abstract, please respond to the following query: \"The issue\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "Radical hysterectomy is one of the standard treatments for early stage cervical cancer. In this operation, the uterus (womb), cervix, upper vagina and tissues surrounding the cervix and upper vagina are removed. Because of the extent of this operation, women may experience problems with urinating which impacts on quality of life." } ]

[ { "role": "user", "content": "Abstract: Background\nVentilator-associated pneumonia (VAP) is common in intensive care units (ICUs). Some evidence indicates that probiotics may reduce the incidence of VAP. Several additional published studies have demonstrated that probiotics are safe and efficacious in preventing VAP in ICUs. We aimed to systematically summarise the results of all available data to generate the best evidence for the prevention of VAP.\nObjectives\nTo evaluate the effectiveness and safety of probiotics for preventing VAP.\nSearch methods\nWe searched CENTRAL (2014, Issue 8), MEDLINE (1948 to September week 1, 2014) and EMBASE (2010 to September 2014).\nSelection criteria\nRandomised controlled trials (RCTs) comparing probiotics with placebo or another control (excluding RCTs that use probiotics in both study groups) to prevent VAP.\nData collection and analysis\nTwo review authors independently assessed eligibility and the quality of trials, and extracted data.\nMain results\nWe included eight RCTs, with 1083 participants. All studies compared a form of probiotic (Lactobacillus casei rhamnosus; Lactobacillus plantarum; Synbiotic 2000FORTE; Ergyphilus; combination Bifidobacterium longum + Lactobacillus bulgaricus + Streptococcus thermophilus) versus a control group (placebo; glutamine; fermentable fibre; peptide; chlorhexidine). The analysis of all RCTs showed that the use of probiotics decreased the incidence of VAP (odds ratio (OR) 0.70, 95% confidence interval (CI) 0.52 to 0.95, low quality evidence). However, the aggregated results were uncertain for ICU mortality (OR 0.84, 95% CI 0.58 to 1.22 very low quality evidence), in-hospital mortality (OR 0.78, 95% CI 0.54 to 1.14, very low quality evidence), incidence of diarrhoea (OR 0.72, 95% CI 0.47 to 1.09, very low quality evidence), length of ICU stay (mean difference (MD) -1.60, 95% CI -6.53 to 3.33, very low quality evidence), duration of mechanical ventilation (MD -6.15, 95% CI -18.77 to 6.47, very low quality evidence) and antibiotic use (OR 1.23, 95% CI 0.51 to 2.96, low quality evidence). Antibiotics for VAP were used for a shorter duration (in days) when participants received probiotics in one small study (MD -3.00, 95% CI -6.04 to 0.04). However, the CI of the estimated effect was too wide to exclude no difference with probiotics. There were no reported events of nosocomial probiotic infections in any included study.\nThe overall methodological quality of the included studies, based on our 'Risk of bias' assessments, was moderate with half of the included studies rated as a 'low' risk of bias; however, we rated four included studies as a 'high' risk of bias across one or more of the domains. The study limitations, differences in probiotics administered and participants, and small sample sizes across the included studies mean that the power to detect a trend of overall effect may be limited and chance findings cannot be excluded.\nTo explore the influence of some potential confounding factors in the studies, we conducted an intention-to-treat (ITT) analysis, which did not change the inference of per-protocol analysis. However, our sensitivity analysis did not indicate a significant difference between groups for instances of VAP.\nAuthors' conclusions\nEvidence suggests that use of probiotics is associated with a reduction in the incidence of VAP. However, the quality of the evidence is low and the exclusion of the one study that did not provide a robust definition of VAP increased the uncertainty in this finding. The available evidence is not clear regarding a decrease in ICU or hospital mortality with probiotic use. Three trials reported on the incidence of diarrhoea and the pooled results indicate no clear evidence of a difference. The results of this meta-analysis do not provide sufficient evidence to draw conclusions on the efficacy and safety of probiotics for the prevention of VAP in ICU patients.\n\nGiven the provided abstract, please respond to the following query: \"Study characteristics\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "We identified eight studies with 1083 participants comparing probiotics versus placebo for preventing VAP. The studies were conducted between 2006 and 2011 in China, France, Greece, Slovenia, Sweden, the UK and the USA, with funding from various sources including hospital/National Health Service, pharmaceuticals and the National Institutes of Health. In the studies that stated the gender ratios, there were 611 males and 378 females. The evidence is current to September 2014." } ]

[ { "role": "user", "content": "Abstract: Background\nLand-based exercise therapy is recommended in clinical guidelines for hip or knee osteoarthritis. Adjunctive non-pharmacological therapies are commonly used alongside exercise in hip or knee osteoarthritis management, but cumulative evidence for adjuncts to land-based exercise therapy is lacking.\nObjectives\nTo evaluate the benefits and harms of adjunctive therapies used in addition to land-based exercise therapy compared with placebo adjunctive therapy added to land-based exercise therapy, or land-based exercise therapy only for people with hip or knee osteoarthritis.\nSearch methods\nWe searched CENTRAL, MEDLINE, PsycINFO, EMBASE, CINAHL, Physiotherapy Evidence Database (PEDro) and clinical trials registries up to 10 June 2021.\nSelection criteria\nWe included randomised controlled trials (RCTs) or quasi-RCTs of people with hip or knee osteoarthritis comparing adjunctive therapies alongside land-based exercise therapy (experimental group) versus placebo adjunctive therapies alongside land-based exercise therapy, or land-based exercise therapy (control groups). Exercise had to be identical in both groups. Major outcomes were pain, physical function, participant-reported global assessment, quality of life (QOL), radiographic joint structural changes, adverse events and withdrawals due to adverse events. We evaluated short-term (6 months), medium-term (6 to 12 months) and long-term (12 months onwards) effects.\nData collection and analysis\nTwo review authors independently assessed study eligibility, extracted data, and assessed risk of bias and certainty of evidence for major outcomes using GRADE.\nMain results\nWe included 62 trials (60 RCTs and 2 quasi-RCTs) totalling 6508 participants. One trial included people with hip osteoarthritis, one hip or knee osteoarthritis and 60 included people with knee osteoarthritis only. Thirty-six trials evaluated electrophysical agents, seven manual therapies, four acupuncture or dry needling, or taping, three psychological therapies, dietary interventions or whole body vibration, two spa or peloid therapy and one foot insoles. Twenty-two trials included a placebo adjunctive therapy. We presented the effects stratified by different adjunctive therapies along with the overall results. We judged most trials to be at risk of bias, including 55% at risk of selection bias, 74% at risk of performance bias and 79% at risk of detection bias. Adverse events were reported in 11 (18%) trials.\nComparing adjunctive therapies plus land-based exercise therapy against placebo therapies plus exercise up to six months (short-term), we found low-certainty evidence for reduced pain and function, which did not meet our prespecified threshold for a clinically important difference. Mean pain intensity was 5.4 in the placebo group on a 0 to 10 numerical pain rating scale (NPRS) (lower scores represent less pain), and 0.77 points lower (0.48 points better to 1.16 points better) in the adjunctive therapy and exercise therapy group; relative improvement 10% (6% to 15% better) (22 studies; 1428 participants). Mean physical function on the Western Ontario and McMaster (WOMAC) 0 to 68 physical function (lower scores represent better function) subscale was 32.5 points in the placebo group and reduced by 5.03 points (2.57 points better to 7.61 points better) in the adjunctive therapy and exercise therapy group; relative improvement 12% (6% better to 18% better) (20 studies; 1361 participants). Moderate-certainty evidence indicates that adjunctive therapies did not improve QOL (SF-36 0 to 100 scale, higher scores represent better QOL). Placebo group mean QOL was 81.8 points, and 0.75 points worse (4.80 points worse to 3.39 points better) in the placebo adjunctive therapy group; relative improvement 1% (7% worse to 5% better) (two trials; 82 participants). Low-certainty evidence (two trials; 340 participants) indicates adjunctive therapies plus exercise may not increase adverse events compared to placebo therapies plus exercise (31% versus 13%; risk ratio (RR) 2.41, 95% confidence interval (CI) 0.27 to 21.90). Participant-reported global assessment was not measured in any studies.\nCompared with land-based exercise therapy, low-certainty evidence indicates that adjunctive electrophysical agents alongside exercise produced short-term (0 to 6 months) pain reduction of 0.41 points (0.17 points better to 0.63 points better); mean pain in the exercise-only group was 3.8 points and 0.41 points better in the adjunctive therapy plus exercise group (0 to 10 NPRS); relative improvement 7% (3% better to 11% better) (41 studies; 3322 participants). Mean physical function (0 to 68 WOMAC subscale) was 18.2 points in the exercise group and 2.83 points better (1.62 points better to 4.04 points better) in the adjunctive therapy plus exercise group; relative improvement 9% (5% better to 13% better) (41 studies; 3323 participants). These results are not clinically important. Mean QOL in the exercise group was 56.1 points and 1.04 points worse in the adjunctive therapies plus exercise therapy group (1.04 points worse to 3.12 points better); relative improvement 2% (2% worse to 5% better) (11 studies; 1483 participants), indicating no benefit (low-certainty evidence). Moderate-certainty evidence indicates that adjunctive therapies plus exercise probably result in a slight increase in participant-reported global assessment (short-term), with success reported by 45% in the exercise therapy group and 17% more individuals receiving adjunctive therapies and exercise (RR 1.37, 95% CI 1.15 to 1.62) (5 studies; 840 participants). One study (156 participants) showed little difference in radiographic joint structural changes (0.25 mm less, 95% CI -0.32 to -0.18 mm); 12% relative improvement (6% better to 18% better). Low-certainty evidence (8 trials; 1542 participants) indicates that adjunctive therapies plus exercise may not increase adverse events compared with exercise only (8.6% versus 6.5%; RR 1.33, 95% CI 0.78 to 2.27).\nAuthors' conclusions\nModerate- to low-certainty evidence showed no difference in pain, physical function or QOL between adjunctive therapies and placebo adjunctive therapies, or in pain, physical function, QOL or joint structural changes, compared to exercise only. Participant-reported global assessment was not reported for placebo comparisons, but there is probably a slight clinical benefit for adjunctive therapies plus exercise compared with exercise, based on a small number of studies. This may be explained by additional constructs captured in global measures compared with specific measures. Although results indicate no increased adverse events for adjunctive therapies used with exercise, these were poorly reported. Most studies evaluated short-term effects, with limited medium- or long-term evaluation. Due to a preponderance of knee osteoarthritis trials, we urge caution in extrapolating the findings to populations with hip osteoarthritis.\n\nGiven the provided abstract, please respond to the following query: \"What did we find?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "We found 62 randomised controlled trials with 6508 participants, mostly women, from 24 countries. The average age was between 52 and 83 years, with symptoms present from 9 months to 12 years. Sixty studies enrolled people with knee osteoarthritis, one enrolled people with hip osteoarthritis and one enrolled people with knee or hip osteoarthritis. Twenty-two trials compared additional therapies plus exercise therapy to sham additional therapies plus exercise therapy, and 41 compared to exercise therapy. Thirty-eight trials studied electrophysical agents, seven studied manual therapies, four studied acupuncture/dry needling or use of tape, three studied psychological or dietary interventions, whole body vibration (this involves standing on a vibration platform), or spa/mud therapy, and one studied foot orthotics (shoe insoles)." } ]

[ { "role": "user", "content": "Abstract: Background\nTrauma is the fifth leading cause of death worldwide, and in people younger than 40 years of age, it is the leading cause of death. During the resuscitation of trauma patients at the emergency department, there are two different commonly used diagnostic strategies. Conventionally, there is the use of physical examination and conventional diagnostic imaging, potentially followed by selective use of computed tomography (CT). Alternatively, there is the use of physical examination and conventional diagnostics, followed by a routine (instead of selective) use of thoracoabdominal CT. It is currently unknown which of the two strategies is the better diagnostic strategy for patients with blunt high-energy trauma.\nObjectives\nTo assess the effects of routine thoracoabdominal CT compared with selective thoracoabdominal CT on mortality in blunt high-energy trauma patients.\nSearch methods\nWe searched the Cochrane Injuries Group's Specialised Register, Cochrane Central Register of Controlled Trials (Issue 4, 2013); MEDLINE (OvidSP), EMBASE (OvidSP) and CINAHL for all published randomised controlled trials (RCTs). We did not restrict the searches by language, date or publication status. We conducted the search on the 9 May 2013.\nSelection criteria\nWe included RCTs of trauma resuscitation algorithms using routine thoracoabdominal CT versus algorithms using selective CT in this review. We included all blunt high-energy trauma patients (including blast or barotrauma).\nData collection and analysis\nTwo authors independently evaluated the search results.\nMain results\nThe systematic search identified 481 references; after removal of duplicates, 396 remained. We found no RCTs comparing routine versus selective thoracoabdominal CT in blunt high-energy trauma patients. We excluded 381 studies based on the abstracts of the publications because of irrelevance to the review topic, and a further 15 studies after full-text evaluation.\nAuthors' conclusions\nWe found no RCTs of routine versus selective thoracoabdominal CT in patients with blunt high-energy trauma. Based on the lack of evidence from RCTs, it is not possible to say which approach is better in reducing deaths.\n\nGiven the provided abstract, please respond to the following query: \"Study characteristics\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "We searched medical databases for publications of randomised controlled trials (a clinical study where participants are randomly allocated into treatment groups) comparing the usual approach versus selected use of CT scanning. We included studies of all types of blunt trauma and excluded studies with people with penetrating injuries (e.g. gunshot or knife wounds) and pregnant women. The searches are up-to-date to May 2013." } ]

[ { "role": "user", "content": "Abstract: Background\nTuberculosis is an infectious bacterial disease that is spread via respiratory droplets from infected individuals to susceptible contacts. To eliminate this disease from low- and medium-incidence settings, people who are most likely to be infected (contacts) must be identified. Recently, study authors have examined alternate approaches to contact tracing methods that demonstrate improved detection and prioritization of contacts. The comparative benefit of these methods has not been established.\nObjectives\nTo assess the effectiveness of novel methods of contact tracing versus current standard of care to identify latent and active cases in low- to moderate-incidence settings.\nSearch methods\nWe searched CENTRAL, MEDLINE, Embase, LILACS, Web of Science, and CINAHL up to 15 July 2019. We also searched for clinical trials and examined reference lists and conference proceedings.\nSelection criteria\nRandomized controlled trials (RCTs) and cluster-RCTs of contact tracing strategies that included alternate approaches (other than standard practice).\nData collection and analysis\nTwo review authors independently assessed identified articles for eligibility and quality using prespecified criteria.\nMain results\nNo trials met the inclusion criteria of this review. Several study authors described an alternate method for examining contacts and performing social network analysis but did not compare this with the current contact tracing approach.\nAuthors' conclusions\nThis Cochrane Review highlights the lack of research in support of the current contact tracing method and the need for RCTs to compare new methods such as social network analysis to improve contact tracing processes.\n\nGiven the provided abstract, please respond to the following query: \"How up-to-date is this review\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "We searched for studies published up to 15 July 2019." } ]

[ { "role": "user", "content": "Abstract: Background\nTobacco use is estimated to kill 7 million people a year. Nicotine is highly addictive, but surveys indicate that almost 70% of US and UK smokers would like to stop smoking. Although many smokers attempt to give up on their own, advice from a health professional increases the chances of quitting. As of 2016 there were 3.5 billion Internet users worldwide, making the Internet a potential platform to help people quit smoking.\nObjectives\nTo determine the effectiveness of Internet-based interventions for smoking cessation, whether intervention effectiveness is altered by tailoring or interactive features, and if there is a difference in effectiveness between adolescents, young adults, and adults.\nSearch methods\nWe searched the Cochrane Tobacco Addiction Group Specialised Register, which included searches of MEDLINE, Embase and PsycINFO (through OVID). There were no restrictions placed on language, publication status or publication date. The most recent search was conducted in August 2016.\nSelection criteria\nWe included randomised controlled trials (RCTs). Participants were people who smoked, with no exclusions based on age, gender, ethnicity, language or health status. Any type of Internet intervention was eligible. The comparison condition could be a no-intervention control, a different Internet intervention, or a non-Internet intervention. To be included, studies must have measured smoking cessation at four weeks or longer.\nData collection and analysis\nTwo review authors independently assessed and extracted data. We extracted and, where appropriate, pooled smoking cessation outcomes of six-month follow-up or more, reporting short-term outcomes narratively where longer-term outcomes were not available. We reported study effects as a risk ratio (RR) with a 95% confidence interval (CI).\nWe grouped studies according to whether they (1) compared an Internet intervention with a non-active control arm (e.g. printed self-help guides), (2) compared an Internet intervention with an active control arm (e.g. face-to-face counselling), (3) evaluated the addition of behavioural support to an Internet programme, or (4) compared one Internet intervention with another. Where appropriate we grouped studies by age.\nMain results\nWe identified 67 RCTs, including data from over 110,000 participants. We pooled data from 35,969 participants.\nThere were only four RCTs conducted in adolescence or young adults that were eligible for meta-analysis.\nResults for trials in adults: Eight trials compared a tailored and interactive Internet intervention to a non-active control. Pooled results demonstrated an effect in favour of the intervention (RR 1.15, 95% CI 1.01 to 1.30, n = 6786). However, statistical heterogeneity was high (I2 = 58%) and was unexplained, and the overall quality of evidence was low according to GRADE. Five trials compared an Internet intervention to an active control. The pooled effect estimate favoured the control group, but crossed the null (RR 0.92, 95% CI 0.78 to 1.09, n = 3806, I2 = 0%); GRADE quality rating was moderate. Five studies evaluated an Internet programme plus behavioural support compared to a non-active control (n = 2334). Pooled, these studies indicated a positive effect of the intervention (RR 1.69, 95% CI 1.30 to 2.18). Although statistical heterogeneity was substantial (I2 = 60%) and was unexplained, the GRADE rating was moderate. Four studies evaluated the Internet plus behavioural support compared to active control. None of the studies detected a difference between trial arms (RR 1.00, 95% CI 0.84 to 1.18, n = 2769, I2 = 0%); GRADE rating was moderate. Seven studies compared an interactive or tailored Internet intervention, or both, to an Internet intervention that was not tailored/interactive. Pooled results favoured the interactive or tailored programme, but the estimate crossed the null (RR 1.10, 95% CI 0.99 to 1.22, n = 14,623, I2 = 0%); GRADE rating was moderate. Three studies compared tailored with non-tailored Internet-based messages, compared to non-tailored messages. The tailored messages produced higher cessation rates compared to control, but the estimate was not precise (RR 1.17, 95% CI 0.97 to 1.41, n = 4040), and there was evidence of unexplained substantial statistical heterogeneity (I2 = 57%); GRADE rating was low.\nResults should be interpreted with caution as we judged some of the included studies to be at high risk of bias.\nAuthors' conclusions\nThe evidence from trials in adults suggests that interactive and tailored Internet-based interventions with or without additional behavioural support are moderately more effective than non-active controls at six months or longer, but there was no evidence that these interventions were better than other active smoking treatments. However some of the studies were at high risk of bias, and there was evidence of substantial statistical heterogeneity. Treatment effectiveness in younger people is unknown.\n\nGiven the provided abstract, please respond to the following query: \"Key results\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "In combined results, Internet programmes that were interactive and tailored to individual responses led to higher quit rates than usual care or written self-help at six months or longer." } ]

[ { "role": "user", "content": "Abstract: Background\nVenous thromboembolism (VTE) is a leading cause of morbidity and mortality in hospitalized patients. While numerous randomized controlled trials (RCTs) have shown that the appropriate use of thromboprophylaxis in hospitalized patients at risk for VTE is safe, effective, and cost-effective, thromboprophylaxis remains underused or inappropriately used. Our previous review suggested that system-wide interventions, such as education, alerts, and multifaceted interventions were more effective at improving the prescribing of thromboprophylaxis than relying on individual providers’ behaviors. However, 47 of the 55 included studies in our previous review were observational in design. Thus, an update to our systematic review, focused on the higher level of evidence of RCTs only, was warranted.\nObjectives\nTo assess the effects of system-wide interventions designed to increase the implementation of thromboprophylaxis and decrease the incidence of VTE in hospitalized adult medical and surgical patients at risk for VTE, focusing on RCTs only.\nSearch methods\nOur research librarian conducted a systematic literature search of MEDLINE Ovid, and subsequently translated it to CENTRAL, PubMed, Embase Ovid, BIOSIS Previews Ovid, CINAHL, Web of Science, the Database of Abstracts of Reviews of Effects (DARE; in the Cochrane Library), NHS Economic Evaluation Database (EED; in the Cochrane Library), LILACS, and clinicaltrials.gov from inception to 7 January 2017. We also screened reference lists of relevant review articles. We identified 12,920 potentially relevant records.\nSelection criteria\nWe included all types of RCTs, with random or quasi-random methods of allocation of interventions, which either randomized individuals (e.g. parallel group, cross-over, or factorial design RCTs), or groups of individuals (cluster RCTs (CRTs)), which aimed to increase the use of prophylaxis or appropriate prophylaxis, or decrease the occurrence of VTE in hospitalized adult patients. We excluded observational studies, studies in which the intervention was simply distribution of published guidelines, and studies whose interventions were not clearly described. Studies could be in any language.\nData collection and analysis\nWe collected data on the following outcomes: the number of participants who received prophylaxis or appropriate prophylaxis (as defined by study authors), the occurrence of any VTE (symptomatic or asymptomatic), mortality, and safety outcomes, such as bleeding. We categorized the interventions into alerts (computer or human alerts), multifaceted interventions (combination of interventions that could include an alert component), educational interventions (e.g. grand rounds, courses), and preprinted orders (written predefined orders completed by the physician on paper or electronically). We meta-analyzed data across RCTs using a random-effects model. For CRTs, we pooled effect estimates (risk difference (RD) and risk ratio (RR), with 95% confidence interval (CI), adjusted for clustering, when possible. We pooled results if three or more trials were available for a particular intervention. We assessed the certainty of the evidence according to the GRADE approach.\nMain results\nFrom the 12,920 records identified by our search, we included 13 RCTs (N = 35,997 participants) in our qualitative analysis and 11 RCTs (N = 33,207 participants) in our meta-analyses.\nPrimary outcome: Alerts were associated with an increase in the proportion of participants who received prophylaxis (RD 21%, 95% CI 15% to 27%; three studies; 5057 participants; I² = 75%; low-certainty evidence). The substantial statistical heterogeneity may be in part explained by patient types, type of hospital, and type of alert. Subgroup analyses were not feasible due to the small number of studies included in the meta-analysis.\nMultifaceted interventions were associated with a small increase in the proportion of participants who received prophylaxis (cluster-adjusted RD 4%, 95% CI 2% to 6%; five studies; 9198 participants; I² = 0%; moderate-certainty evidence). Multifaceted interventions with an alert component were found to be more effective than multifaceted interventions that did not include an alert, although there were not enough studies to conduct a pooled analysis.\nSecondary outcomes: Alerts were associated with an increase in the proportion of participants who received appropriate prophylaxis (RD 16%, 95% CI 12% to 20%; three studies; 1820 participants; I² = 0; moderate-certainty evidence). Alerts were also associated with a reduction in the rate of symptomatic VTE at three months (RR 64%, 95% CI 47% to 86%; three studies; 5353 participants; I² = 15%; low-certainty evidence). Computer alerts were associated with a reduction in the rate of symptomatic VTE, although there were not enough studies to pool computer alerts and human alerts results separately.\nAuthors' conclusions\nWe reviewed RCTs that implemented a variety of system-wide strategies aimed at improving thromboprophylaxis in hospitalized patients. We found increased prescription of prophylaxis associated with alerts and multifaceted interventions, and increased prescription of appropriate prophylaxis associated with alerts. While multifaceted interventions were found to be less effective than alerts, a multifaceted intervention with an alert was more effective than one without an alert. Alerts, particularly computer alerts, were associated with a reduction in symptomatic VTE at three months, although there were not enough studies to pool computer alerts and human alerts results separately.\nOur analysis was underpowered to assess the effect on mortality and safety outcomes, such as bleeding.\nThe incomplete reporting of relevant study design features did not allow complete assessment of the certainty of the evidence. However, the certainty of the evidence for improvement in outcomes was judged to be better than for our previous review (low- to moderate-certainty evidence, compared to very low-certainty evidence for most outcomes). The results of our updated review will help physicians, hospital administrators, and policy makers make practical decisions about adopting specific system-wide measures to improve prescription of thromboprophylaxis, and ultimately prevent VTE in hospitalized patients.\n\nGiven the provided abstract, please respond to the following query: \"How up to date is the review?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "We searched for studies that had been published up to 7 January 2017." } ]

[ { "role": "user", "content": "Abstract: Background\nChronic kidney disease (CKD) is defined as reduced function of the kidneys present for 3 months or longer with adverse implications for health and survival. For several decades low protein diets have been proposed for participants with CKD with the aim of slowing the progression to end-stage kidney disease (ESKD) and delaying the onset of renal replacement therapy. However the relative benefits and harms of dietary protein restriction for preventing progression of CKD have not been resolved. This is an update of a systematic review first published in 2000 and updated in 2006, 2009, and 2018.\nObjectives\nTo determine the efficacy of low protein diets in preventing the natural progression of CKD towards ESKD and in delaying the need for commencing dialysis treatment in non-diabetic adults.\nSearch methods\nWe searched the Cochrane Kidney and Transplant Register of Studies up to 7 September 2020 through contact with the Information Specialist using search terms relevant to this review. Studies in the Register are identified through searches of CENTRAL, MEDLINE, and EMBASE, conference proceedings, the International Clinical Trials Register (ICTRP) Search Portal and ClinicalTrials.gov.\nSelection criteria\nWe included randomised controlled trials (RCTs) or quasi RCTs in which adults with non-diabetic CKD (stages 3 to 5) not on dialysis were randomised to receive a very low protein intake (0.3 to 0.4 g/kg/day) compared with a low protein intake (0.5 to 0.6 g/kg/day) or a low protein intake compared with a normal protein intake (≥ 0.8 g/kg/day) for 12 months or more.\nData collection and analysis\nTwo authors independently selected studies and extracted data. For dichotomous outcomes (death, all causes), requirement for dialysis, adverse effects) the risk ratios (RR) with 95% confidence intervals (CI) were calculated and summary statistics estimated using the random effects model. Where continuous scales of measurement were used (glomerular filtration rate (GFR), weight), these data were analysed as the mean difference (MD) or standardised mean difference (SMD) if different scales had been used. The certainty of the evidence was assessed using GRADE.\nMain results\nWe identified 17 studies with 2996 analysed participants (range 19 to 840). Four larger multicentre studies were subdivided according to interventions so that the review included 21 separate data sets. Mean duration of participant follow-up ranged from 12 to 50 months.\nRandom sequence generation and allocation concealment were considered at low risk of bias in eleven and nine studies respectively. All studies were considered at high risk for performance bias as they were open-label studies. We assessed detection bias for outcome assessment for GFR and ESKD separately. As GFR measurement was a laboratory outcome all studies were assessed at low risk of detection bias. For ESKD, nine studies were at low risk of detection bias as the need to commence dialysis was determined by personnel independent of the study investigators. Five studies were assessed at high risk of attrition bias with eleven studies at low risk. Ten studies were at high risk for reporting bias as they did not include data which could be included in a meta-analysis. Eight studies reported funding from government bodies while the remainder did not report on funding.\nTen studies compared a low protein diet with a normal protein diet in participants with CKD categories 3a and b (9 studies) or 4 (one study). There was probably little or no difference in the numbers of participants who died (5 studies 1680 participants: RR 0.77, 95% CI 0.51 to 1.18; 13 fewer deaths per 1000; moderate certainty evidence). A low protein diet may make little or no difference in the number of participants who reached ESKD compared with a normal protein diet (6 studies, 1814 participants: RR 1.05, 95% CI 0.73 to 1.53; 7 more per 1000 reached ESKD; low certainty evidence). It remains uncertain whether a low protein diet compared with a normal protein intake impacts on the outcome of final or change in GFR (8 studies, 1680 participants: SMD -0.18, 95% CI -0.75 to 0.38; very low certainty evidence).\nEight studies compared a very low protein diet with a low protein diet and two studies compared a very low protein diet with a normal protein diet. A very low protein intake compared with a low protein intake probably made little or no difference to death (6 studies, 681 participants: RR 1.26, 95% CI 0.62 to 2.54; 10 more deaths per 1000; moderate certainty evidence). However it probably reduces the number who reach ESKD (10 studies, 1010 participants: RR 0.65, 95% CI 0.49 to 0.85; 165 per 1000 fewer reached ESKD; moderate certainty evidence). It remains uncertain whether a very low protein diet compared with a low or normal protein intake influences the final or change in GFR (6 studies, 456 participants: SMD 0.12, 95% CI -0.27 to 0.52; very low certainty evidence).\nFinal body weight was reported in only three studies. It is uncertain whether the intervention alters final body weight (3 studies, 89 participants: MD -0.40 kg, 95% CI -6.33 to 5.52; very low certainty evidence).Twelve studies reported no evidence of protein energy wasting (malnutrition) in their study participants while three studies reported small numbers of participants in each group with protein energy wasting. Most studies reported that adherence to diet was satisfactory. Quality of life was not formally assessed in any studies.\nAuthors' conclusions\nThis review found that very low protein diets probably reduce the number of people with CKD 4 or 5, who progress to ESKD. In contrast low protein diets may make little difference to the number of people who progress to ESKD. Low or very low protein diets probably do not influence death. However there are limited data on adverse effects such as weight differences and protein energy wasting. There are no data on whether quality of life is impacted by difficulties in adhering to protein restriction. Studies evaluating the adverse effects and the impact on quality of life of dietary protein restriction are required before these dietary approaches can be recommended for widespread use.\n\nGiven the provided abstract, please respond to the following query: \"Conclusions\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "In people with advanced kidney failure, a very low protein intake probably slows the progress to kidney failure. However we need more information on the side effects of low protein diets and on whether quality of life is reduced because of difficulties in keeping to such a diet." } ]

[ { "role": "user", "content": "Abstract: Background\nComplex regional pain syndrome (CRPS) is a painful and disabling condition that usually manifests in response to trauma or surgery and is associated with significant pain and disability. CRPS can be classified into two types: type I (CRPS I) in which a specific nerve lesion has not been identified and type II (CRPS II) where there is an identifiable nerve lesion. Guidelines recommend the inclusion of a variety of physiotherapy interventions as part of the multimodal treatment of people with CRPS. This is the first update of the review originally published in Issue 2, 2016.\nObjectives\nTo determine the effectiveness of physiotherapy interventions for treating pain and disability associated with CRPS types I and II in adults.\nSearch methods\nFor this update we searched CENTRAL (the Cochrane Library), MEDLINE, Embase, CINAHL, PsycINFO, LILACS, PEDro, Web of Science, DARE and Health Technology Assessments from February 2015 to July 2021 without language restrictions, we searched the reference lists of included studies and we contacted an expert in the field. We also searched additional online sources for unpublished trials and trials in progress.\nSelection criteria\nWe included randomised controlled trials (RCTs) of physiotherapy interventions compared with placebo, no treatment, another intervention or usual care, or other physiotherapy interventions in adults with CRPS I and II. Primary outcomes were pain intensity and disability. Secondary outcomes were composite scores for CRPS symptoms, health-related quality of life (HRQoL), patient global impression of change (PGIC) scales and adverse effects.\nData collection and analysis\nTwo review authors independently screened database searches for eligibility, extracted data, evaluated risk of bias and assessed the certainty of evidence using the GRADE system.\nMain results\nWe included 16 new trials (600 participants) along with the 18 trials from the original review totalling 34 RCTs (1339 participants). Thirty-three trials included participants with CRPS I and one trial included participants with CRPS II. Included trials compared a diverse range of interventions including physical rehabilitation, electrotherapy modalities, cortically directed rehabilitation, electroacupuncture and exposure-based approaches. Most interventions were tested in small, single trials. Most were at high risk of bias overall (27 trials) and the remainder were at 'unclear' risk of bias (seven trials). For all comparisons and outcomes where we found evidence, we graded the certainty of the evidence as very low, downgraded due to serious study limitations, imprecision and inconsistency. Included trials rarely reported adverse effects.\nPhysiotherapy compared with minimal care for adults with CRPS I\nOne trial (135 participants) of multimodal physiotherapy, for which pain data were unavailable, found no between-group differences in pain intensity at 12-month follow-up. Multimodal physiotherapy demonstrated a small between-group improvement in disability at 12 months follow-up compared to an attention control (Impairment Level Sum score, 5 to 50 scale; mean difference (MD) -3.7, 95% confidence interval (CI) -7.13 to -0.27) (very low-certainty evidence). Equivalent data for pain were not available. Details regarding adverse events were not reported.\nPhysiotherapy compared with minimal care for adults with CRPS II\nWe did not find any trials of physiotherapy compared with minimal care for adults with CRPS II.\nAuthors' conclusions\nThe evidence is very uncertain about the effects of physiotherapy interventions on pain and disability in CRPS. This conclusion is similar to our 2016 review. Large-scale, high-quality RCTs with longer-term follow-up are required to test the effectiveness of physiotherapy-based interventions for treating pain and disability in adults with CRPS I and II.\n\nGiven the provided abstract, please respond to the following query: \"How up to date is the evidence?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "The evidence is up to date to July 2021." } ]

[ { "role": "user", "content": "Abstract: Background\nNeonatal sepsis is a major cause of morbidity and mortality. It is the third leading cause of neonatal mortality globally constituting 13% of overall neonatal mortality. Despite the high burden of neonatal sepsis, high-quality evidence in diagnosis and treatment is scarce. Due to the diagnostic challenges of sepsis and the relative immunosuppression of the newborn, many neonates receive antibiotics for suspected sepsis. Antibiotics have become the most used therapeutics in neonatal intensive care units, and observational studies in high-income countries suggest that 83% to 94% of newborns treated with antibiotics for suspected sepsis have negative blood cultures. The last Cochrane Review was updated in 2005. There is a need for an updated systematic review assessing the effects of different antibiotic regimens for late-onset neonatal sepsis.\nObjectives\nTo assess the beneficial and harmful effects of different antibiotic regimens for late-onset neonatal sepsis.\nSearch methods\nWe searched the following electronic databases: CENTRAL (2021, Issue 3); Ovid MEDLINE; Embase Ovid; CINAHL; LILACS; Science Citation Index EXPANDED and Conference Proceedings Citation Index – Science on 12 March 2021. We also searched clinical trials databases and the reference lists of retrieved articles for randomised controlled trials (RCTs) and quasi-RCTs.\nSelection criteria\nWe included RCTs comparing different antibiotic regimens for late-onset neonatal sepsis. We included participants older than 72 hours of life at randomisation, suspected or diagnosed with neonatal sepsis, meningitis, osteomyelitis, endocarditis, or necrotising enterocolitis. We excluded trials that assessed treatment of fungal infections.\nData collection and analysis\nThree review authors independently assessed studies for inclusion, extracted data, and assessed risk of bias. We used the GRADE approach to assess the certainty of evidence. Our primary outcome was all-cause mortality, and our secondary outcomes were: serious adverse events, respiratory support, circulatory support, nephrotoxicity, neurological developmental impairment, necrotising enterocolitis, and ototoxicity. Our primary time point of interest was at maximum follow-up.\nMain results\nWe included five RCTs (580 participants). All trials were at high risk of bias, and had very low-certainty evidence.\nThe five included trials assessed five different comparisons of antibiotics.\nWe did not conduct a meta-analysis due to lack of relevant data.\nOf the five included trials one trial compared cefazolin plus amikacin with vancomycin plus amikacin; one trial compared ticarcillin plus clavulanic acid with flucloxacillin plus gentamicin; one trial compared cloxacillin plus amikacin with cefotaxime plus gentamicin; one trial compared meropenem with standard care (ampicillin plus gentamicin or cefotaxime plus gentamicin); and one trial compared vancomycin plus gentamicin with vancomycin plus aztreonam.\nNone of the five comparisons found any evidence of a difference when assessing all-cause mortality, serious adverse events, circulatory support, nephrotoxicity, neurological developmental impairment, or necrotising enterocolitis; however, none of the trials were near an information size that could contribute significantly to the evidence of the comparative benefits and risks of any particular antibiotic regimen.\nNone of the trials assessed respiratory support or ototoxicity.\nThe benefits and harms of different antibiotic regimens remain unclear due to the lack of well-powered trials and the high risk of systematic errors.\nAuthors' conclusions\nCurrent evidence is insufficient to support any antibiotic regimen being superior to another. RCTs assessing different antibiotic regimens in late-onset neonatal sepsis with low risks of bias are warranted.\n\nGiven the provided abstract, please respond to the following query: \"Key results\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "We included five trials: one trial compared cefazolin plus amikacin with vancomycin plus amikacin; one trial compared ticarcillin plus clavulanic acid with flucloxacillin plus gentamicin; one trial compared cloxacillin plus amikacin with cefotaxime plus gentamicin; one trial compared meropenem with standard care (ampicillin plus gentamicin or cefotaxime plus gentamicin); and one trial compared vancomycin plus gentamicin with vancomycin plus aztreonam.\nNone of the five antibiotic comparisons showed that the choice of antibiotics influenced the effects on death from all-causes, serious adverse events (i.e. major complications), circulatory support, nephrotoxicity (toxicity in the kidneys), neurological developmental impairment (disabilities in the functioning of the brain that affect a child's behaviour, memory, or ability to learn), or necrotising enterocolitis (tissues in the gut become inflamed and start to die). Current evidence cannot confirm or reject, one antibiotic regimen being superior to another due to scarce data." } ]

[ { "role": "user", "content": "Abstract: Background\nInadvertent perioperative hypothermia occurs because of interference with normal temperature regulation by anaesthetic drugs and exposure of skin for prolonged periods. A number of different interventions have been proposed to maintain body temperature by reducing heat loss. Thermal insulation, such as extra layers of insulating material or reflective blankets, should reduce heat loss through convection and radiation and potentially help avoid hypothermia.\nObjectives\nTo assess the effects of pre- or intraoperative thermal insulation, or both, in preventing perioperative hypothermia and its complications during surgery in adults.\nSearch methods\nWe searched the Cochrane Central Register of Controlled Trials (CENTRAL) (The Cochrane Library 2014, Issue 2), MEDLINE, OvidSP (1956 to 4 February 2014), EMBASE, OvidSP (1982 to 4 February 2014), ISI Web of Science (1950 to 4 February 2014), and CINAHL, EBSCOhost (1980 to 4 February 2014), and reference lists of articles. We also searched Current Controlled Trials and ClinicalTrials.gov.\nSelection criteria\nRandomized controlled trials of thermal insulation compared to standard care or other interventions aiming to maintain normothermia.\nData collection and analysis\nTwo authors extracted data and assessed risk of bias for each included study, with a third author checking details. We contacted some authors to ask for additional details. We only collected adverse events if reported in the trials.\nMain results\nWe included 22 trials, with 16 trials providing data for some analyses. The trials varied widely in the type of patients and operations, the timing and measurement of temperature, and particularly in the types of co-interventions used. The risk of bias was largely unclear, but with a high risk of performance bias in most studies and a low risk of attrition bias. The largest comparison of extra insulation versus standard care had five trials with 353 patients at the end of surgery and showed a weighted mean difference (WMD) of 0.12 ºC (95% CI -0.07 to 0.31; low quality evidence). Comparing extra insulation with forced air warming at the end of surgery gave a WMD of -0.67 ºC (95% CI -0.95 to -0.39; very low quality evidence) indicating a higher temperature with forced air warming. Major cardiovascular outcomes were not reported and so were not analysed. There were no clear effects on bleeding, shivering or length of stay in post-anaesthetic care for either comparison. No other adverse effects were reported.\nAuthors' conclusions\nThere is no clear benefit of extra thermal insulation compared with standard care. Forced air warming does seem to maintain core temperature better than extra thermal insulation, by between 0.5 ºC and 1 ºC, but the clinical importance of this difference is unclear.\n\nGiven the provided abstract, please respond to the following query: \"Review question\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "We wanted to find out the effects of extra insulation on preventing hypothermia and its complications for adults having an operation." } ]

[ { "role": "user", "content": "Abstract: Background\nRetinoblastoma is the most common primary intraocular malignancy of childhood. Systemic chemotherapy is a common treatment for intraocular retinoblastoma, and laser treatment is used as adjuvant therapy during or immediately after chemotherapy courses in selected cases.\nObjectives\nTo compare the effectiveness and safety of adding focal laser therapy to systemically-delivered chemotherapy in treating intraocular retinoblastoma.\nSearch methods\nWe searched the Cochrane Central Register of Controlled Trials (CENTRAL) (which contains the Cochrane Eyes and Vision Trials Register) (2016, Issue 9), MEDLINE Ovid (1946 to 20 October 2016), Embase Ovid (1980 to 20 October 2016), LILACS (Latin American and Caribbean Health Sciences Literature Database) (1982 to 20 October 2016), the ISRCTN registry (www.isrctn.com/editAdvancedSearch); searched 20 October 2016, ClinicalTrials.gov (www.clinicaltrials.gov); searched 20 October 2016, and the World Health Organization (WHO) International Clinical Trials Registry Platform (ICTRP) (www.who.int/ictrp/search/en); searched 20 October 2016. We did not use any date or language restrictions in the electronic searches for trials.\nSelection criteria\nWe searched for randomised controlled trials (RCTs) of systemic chemotherapy with versus without adjuvant laser therapy for postequatorial retinoblastoma.\nData collection and analysis\nWe planned to use standard methodological procedures expected by Cochrane. We planned to meta-analyse the primary outcome, that is the proportion of eyes with recurrence of tumours within three years from treatment\nMain results\nNo studies met the inclusion criteria for this review.\nAuthors' conclusions\nNo evidence from randomised controlled trials was found to support or refute laser therapy in addition to systemic chemotherapy for postequatorial retinoblastoma.\n\nGiven the provided abstract, please respond to the following query: \"What was the aim of this review?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "The aim of this Cochrane Review was to find out if focal laser therapy in addition to treatment by systemic chemotherapy for retinoblastoma reduces the risk of tumour recurrence." } ]

[ { "role": "user", "content": "Abstract: Background\nMultinodular goitre is common in women. Treatments for non-toxic multinodular goitre include surgery, levothyroxine suppressive therapy, and radioiodine. Radioiodine therapy is the only non-surgical alternative for non-toxic multinodular goitre. However, a high amount of radioiodine is needed to enable the thyroid nodules to adequately take up the radioiodine, because the multinodular goitre takes up a low amount of iodine. Recombinant human thyrotropin (rhTSH) has been used to increase radioiodine uptake and reduce thyroid volume of the multinodular goitre. Whether the improved reduction of the goitre resulting from rhTSH-stimulated radioiodine therapy is beneficial to the person remains controversial.\nObjectives\nTo assess the effects of recombinant human thyrotropin-aided radioiodine treatment for non-toxic multinodular goitre.\nSearch methods\nWe searched the CENTRAL, MEDLINE, Scopus as well as ICTRP Search Portal and ClinicalTrials.gov. The date of the last search of all databases was 18 December 2020.\nSelection criteria\nWe included randomised controlled clinical trials (RCTs) comparing the effects of rhTSH-aided radioiodine treatment compared with radioiodine alone for non-toxic multinodular goitre, with at least 12 months of follow-up.\nData collection and analysis\nTwo review authors independently screened titles and abstracts for relevance. Screening for inclusion, data extraction, and risk of bias assessment were carried out by one review author and checked by a second. Our main outcomes were health-related quality of life (QoL), hypothyroidism, adverse events, thyroid volume, all-cause mortality, and costs. We used a random-effects model to perform meta-analyses, and calculated risk ratios (RRs) for dichotomous outcomes, and mean differences (MDs) for continuous outcomes, using 95% confidence intervals (CIs) for effect estimates. We evaluated the certainty of the evidence using the GRADE approach.\nMain results\nWe included six RCTs. A total of 197 participants were allocated to rhTSh-aided radioiodine therapy, and 124 participants were allocated to radioiodine. A single dose of radioiodine was administered 24 hours after the intramuscular injection of a single dose of rhTSH. The duration of follow-up ranged between 12 and 36 months.\nLow-certainty evidence from one study, with 85 participants, showed uncertain effects for QoL for either intervention. RhTSH-aided radioiodine increased hypothyroidism compared with radioiodine alone (64/197 participants (32.5%) in the rhTSH-aided radioiodine group versus 15/124 participants (12.1%) in the radioiodine alone group; RR 2.53, 95% CI 1.52 to 4.20; 6 studies, 321 participants; moderate-certainty evidence in favour of radioiodine alone). A total of 118/197 participants (59.9%) in the rhTSH-aided radioiodine group compared with 60/124 participants (48.4%) in the radioiodine alone group experienced adverse events (random-effects RR 1.24, 95% CI 0.94 to 1.63; 6 studies, 321 participants; fixed-effect RR 1.23, 95% CI 1.02 to 1.49 in favour of radioiodine only; low-certainty evidence).\nRhTSH-aided radioiodine reduced thyroid volume with a MD of 11.9% (95% CI 4.4 to 19.4; 6 studies, 268 participants; moderate-certainty evidence). One study with 28 participants reported one death in the radioiodine alone group (very-low certainty evidence). No study reported on costs.\nAuthors' conclusions\nRhTSH-aided radioiodine treatment for non-toxic multinodular goitre, compared to radioiodine alone, probably increased the risk of hypothyroidism but probably led to a greater reduction in thyroid volume. Data on QoL and costs were sparse or missing.\n\nGiven the provided abstract, please respond to the following query: \"What did we look for?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "We searched medical databases for studies that:\n— were randomised controlled trials (medical studies where participants are put randomly into one of the treatment groups);\n— included people with non-toxic multinodular goitre;\n— compared rhTSH-aided radioiodine treatment with radioiodine treatment alone;\n— tracked participants (follow-up) for at least one year." } ]

[ { "role": "user", "content": "Abstract: Background\nHepatocellular carcinoma occurs mostly in people with chronic liver disease and ranks sixth in terms of global incidence of cancer, and fourth in terms of cancer deaths. In clinical practice, computed tomography (CT) is used as a second-line diagnostic imaging modality to confirm the presence of focal liver lesions suspected as hepatocellular carcinoma on prior diagnostic test such as abdominal ultrasound or alpha-foetoprotein, or both, either in surveillance programmes or in clinical settings. According to current guidelines, a single contrast-enhanced imaging study CT or magnetic resonance imaging (MRI) showing typical hallmarks of hepatocellular carcinoma in people with cirrhosis is valid to diagnose hepatocellular carcinoma. However, a significant number of hepatocellular carcinomas do not show typical hallmarks on imaging modalities, and hepatocellular carcinoma is, therefore, missed. There is no clear evidence of the benefit of surveillance programmes in terms of overall survival: the conflicting results can be a consequence of inaccurate detection, ineffective treatment, or both. Assessing the diagnostic accuracy of CT may clarify whether the absence of benefit could be related to underdiagnosis. Furthermore, an assessment of the accuracy of CT in people with chronic liver disease, who are not included in surveillance programmes is needed for either ruling out or diagnosing hepatocellular carcinoma.\nObjectives\nPrimary: to assess the diagnostic accuracy of multidetector, multiphasic contrast-enhanced CT for the diagnosis of hepatocellular carcinoma of any size and at any stage in adults with chronic liver disease, either in a surveillance programme or in a clinical setting.\nSecondary: to assess the diagnostic accuracy of CT for the diagnosis of resectable hepatocellular carcinoma in adults with chronic liver disease.\nSearch methods\nWe searched the Cochrane Hepato-Biliary Trials Register, Cochrane Hepato-Biliary Diagnostic-Test-Accuracy Studies Register, the Cochrane Library, MEDLINE, Embase, LILACS, Science Citation Index Expanded, and Conference Proceedings Citation Index – Science until 4 May 2021. We applied no language or document-type restrictions.\nSelection criteria\nStudies assessing the diagnostic accuracy of CT for the diagnosis of hepatocellular carcinoma in adults with chronic liver disease, with cross-sectional designs, using one of the acceptable reference standards, such as pathology of the explanted liver and histology of resected or biopsied focal liver lesion with at least a six-month follow-up.\nData collection and analysis\nAt least two review authors independently screened studies, extracted data, and assessed the risk of bias and applicability concerns, using the QUADAS-2 checklist. We presented the results of sensitivity and specificity, using paired forest plots, and tabulated the results. We used a hierarchical meta-analysis model where appropriate. We presented uncertainty of the accuracy estimates using 95% confidence intervals (CIs). We double-checked all data extractions and analyses.\nMain results\nWe included 21 studies, with a total of 3101 participants. We judged all studies to be at high risk of bias in at least one domain because most studies used different reference standards, often inappropriate to exclude the presence of the target condition, and the time-interval between the index test and the reference standard was rarely defined. Regarding applicability in the patient selection domain, we judged 14% (3/21) of studies to be at low concern and 86% (18/21) of studies to be at high concern owing to characteristics of the participants who were on waiting lists for orthotopic liver transplantation.\nCT for hepatocellular carcinoma of any size and stage: sensitivity 77.5% (95% CI 70.9% to 82.9%) and specificity 91.3% (95% CI 86.5% to 94.5%) (21 studies, 3101 participants; low-certainty evidence).\nCT for resectable hepatocellular carcinoma: sensitivity 71.4% (95% CI 60.3% to 80.4%) and specificity 92.0% (95% CI 86.3% to 95.5%) (10 studies, 1854 participants; low-certainty evidence).\nIn the three studies at low concern for applicability (861 participants), we found sensitivity 76.9% (95% CI 50.8% to 91.5%) and specificity 89.2% (95% CI 57.0% to 98.1%).\nThe observed heterogeneity in the results remains mostly unexplained. The sensitivity analyses, which included only studies with clearly prespecified positivity criteria and only studies in which the reference standard results were interpreted without knowledge of the results of the index test, showed no variation in the results.\nAuthors' conclusions\nIn the clinical pathway for the diagnosis of hepatocellular carcinoma in adults with chronic liver disease, CT has roles as a confirmatory test for hepatocellular carcinoma lesions, and for staging assessment. We found that using CT in detecting hepatocellular carcinoma of any size and stage, 22.5% of people with hepatocellular carcinoma would be missed, and 8.7% of people without hepatocellular carcinoma would be unnecessarily treated. For resectable hepatocellular carcinoma, we found that 28.6% of people with resectable hepatocellular carcinoma would improperly not be resected, while 8% of people without hepatocellular carcinoma would undergo inappropriate surgery. The uncertainty resulting from the high risk of bias in the included studies and concerns regarding their applicability limit our ability to confidently draw conclusions based on our results.\n\nGiven the provided abstract, please respond to the following query: \"What did we find?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "We found a total of 21 studies with 3101 people.\nBased on the studies, around 520 (52%) out of 1000 adults with chronic liver disease have confirmed liver cancer. Of these 1000 people, CT may:\n· correctly detect liver cancer in 403 people\n· miss liver cancer in 117 people\n· incorrectly detect liver cancer in 42 cancer-free people\n· correctly detect no liver cancer in 438 people.\nBased on the studies, around 350 (35%) out of 1000 adults with chronic liver disease have confirmed resectable liver cancer. Of these 1000 people, CT may:\n· correctly detect resectable liver cancer in 250 people\n· miss resectable liver cancer in 100 people\n· incorrectly detect resectable liver cancer in 50 people; and\n· correctly detect no resectable liver cancer in 600 people." } ]

[ { "role": "user", "content": "Abstract: Background\nPuerarin, a form of herbal medicine, is widely used in the treatment of ischaemic stroke in China.\nObjectives\nTo assess the effects of puerarin in people with ischaemic stroke.\nSearch methods\nWe searched the Cochrane Stroke Group Trials Register and the Chinese Stroke Trials Register (last searched August 2015). In addition, we searched the Cochrane Central Register of Controlled Trials (CENTRAL) (2015, Issue 7), MEDLINE (1948 to August 2015), EMBASE (1980 to August 2015), AMED (the Allied and Complementary Medicine Database, 1985 to August 2015) and the China Biological Medicine Database (CBM-disc 1979 to August 2015). We searched reference lists, relevant clinical trials and research registers and contacted pharmaceutical companies and researchers in an effort to identify further published and unpublished studies.\nSelection criteria\nRandomised controlled trials (RCTs) or quasi-randomised controlled clinical trials comparing puerarin with placebo or open control (no placebo) in people with ischaemic stroke.\nData collection and analysis\nTwo review authors independently applied the inclusion criteria, assessed trial quality and risk of bias, and extracted the data.\nMain results\nWe included 20 RCTs with 1574 participants in this updated review. All trials were published in Chinese language journals. We included 14 trials that we had excluded in the previous version of the review after we added a new outcome in this update. Time windows within which the participants were randomised ranged from 4.5 hours to 10 days. Ischaemic stroke was confirmed by computerised tomography (CT) or magnetic resonance imaging (MRI) in 18 trials. Meta-analysis of two trials with 164 participants showed that treatment with puerarin did not reduce death or dependency at final follow-up (RR 0.79, 95% CI 0.45 to 1.36). One trial with 83 participants reported that the mean value of the Barthel Index in the puerarin group was below that in the control group. Meta-analysis of 16 trials with 1305 participants showed that puerarin reduced the proportion of participants without improvement of neurological deficit at the end of follow-up (RR 0.42, 95% CI 0.33 to 0.55). None of the included trials reported serious adverse effects.The quality of evidence was low due to incomplete reporting of the methods and short-term follow-up.\nAuthors' conclusions\nThere is not enough evidence to evaluate the effect of puerarin on survival or dependency in people with ischaemic stroke. High quality and large-scale RCTs with long-term follow-up are needed to assess its efficacy.\n\nGiven the provided abstract, please respond to the following query: \"Key results\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "We included 20 RCTs with 1574 participants in this updated review; five trials were new. Treatment with puerarin did not reduce death or dependency at final follow-up. Puerain improved neurological deficit at the end of treatment. The included trials did not report serious adverse effects." } ]

[ { "role": "user", "content": "Abstract: Background\nEczema is a common and chronic, relapsing, inflammatory skin disorder. It seriously impacts quality of life and economic outcomes, especially for those with moderate to severe eczema. Various treatments allow sustained control of the disease; however, their relative benefit remains unclear due to the limited number of trials directly comparing treatments.\nObjectives\nTo assess the comparative efficacy and safety of different types of systemic immunosuppressive treatments for moderate to severe eczema using NMA and to generate rankings of available systemic immunosuppressive treatments for eczema according to their efficacy and safety.\nSearch methods\nWe searched the following databases up to August 2019: the Cochrane Skin Specialised Register, CENTRAL, MEDLINE, and Embase.\nSelection criteria\nAll randomised controlled trials (RCTs) of systemic immunosuppressive agents for moderate to severe atopic eczema when compared against placebo or any other eligible eczema treatment.\nData collection and analysis\nWe synthesised data using pair-wise analysis and NMA to compare treatments and rank them according to their effectiveness.\nEffectiveness was assessed primarily by determining the proportion of participants who achieved at least 75% improvement in the Eczema Area and Severity Index (EASI75) and improvement in the Patient-Oriented Eczema Measure (POEM). Safety was evaluated primarily by considering the proportion of participants with serious adverse events (SAEs) and infection.\nWe deemed short-term follow-up as ≤ 16 weeks and long-term follow-up as > 16 weeks.\nWe assessed the certainty of the body of evidence from the NMA for these primary outcomes using six domains of CiNEMA grading.\nMain results\nWe included a total of 74 studies, with 8177 randomised participants. Approximately 55% of participants were male, with average age of 32 years (range 2 to 84 years), although age and gender were unreported for 419 and 902 participants, respectively. Most of the included trials were placebo controlled (65%), 34% were head-to-head studies (15% assessed the effects of different doses of the same drug), and 1% were multi-armed studies with both an active comparator and a placebo.\nAll trials included participants with moderate to severe eczema, but 62% of studies did not separate data by severity; 38% of studies assessed only severe eczema. The total duration of included trials ranged from 2 weeks to 60 months, whereas treatment duration varied from a single dose (CIM331, KPL-716) to 60 months (methotrexate (MTX)).\nSeventy studies were available for quantitative synthesis; this review assessed 29 immunosuppressive agents from three classes of interventions. These included (1) conventional treatments, with ciclosporin assessed most commonly; (2) small molecule treatments, including phosphodiesterase (PDE)-4 inhibitors, tyrosine kinase inhibitors, and Janus kinase (JAK) inhibitors; and (3) biological treatments, including anti-CD31 receptors, anti-interleukin (IL)-22, anti-IL-31, anti-IL-13, anti-IL-12/23p40, anti-OX40, anti-TSLP, anti-CRTH2, and anti-immunoglobulin E (IgE) monoclonal antibodies, but most commonly dupilumab.\nMost trials (73) assessed outcomes at a short-term duration ranging from 2 to 16 weeks, whereas 33 trials assessed long-term outcomes, with duration ranging from 5 to 60 months. All participants were from a hospital setting. Fifty-two studies declared a source of funding, and of these, pharmaceutical companies funded 88%. We rated 37 studies as high risk; 21, unclear risk, and 16, low risk of bias, with studies most commonly at high risk of attrition bias.\nNetwork meta-analysis suggests that dupilumab ranks first for effectiveness when compared with other biological treatments. Dupilumab is more effective than placebo in achieving EASI75 (risk ratio (RR) 3.04, 95% confidence interval (CI) 2.51 to 3.69) and improvement in POEM score (mean difference 7.30, 95% CI 6.61 to 8.00) at short-term follow-up (high-certainty evidence).\nVery low-certainty evidence means we are uncertain of the effects of dupilumab when compared with placebo, in terms of the proportion of participants who achieve EASI75 (RR 2.59, 95% CI 1.87 to 3.60) at longer-term follow-up.\nLow-certainty evidence indicates that tralokinumab may be more effective than placebo in achieving short-term EASI75 (RR 2.54, 95% CI 1.21 to 5.34), but there was no evidence for tralokinumab to allow us to assess short-term follow-up of POEM or long-term follow-up of EASI75.\nWe are uncertain of the effect of ustekinumab compared with placebo in achieving EASI75 (long-term follow-up: RR 1.17, 95% CI 0.40 to 3.45; short-term follow-up: RR 0.91, 95% CI 0.28 to 2.97; both very low certainty). We found no evidence on ustekinumab for the POEM outcome.\nWe are uncertain whether other immunosuppressive agents that targeted our key outcomes influence the achievement of short-term EASI75 compared with placebo due to low- or very low-certainty evidence.\nDupilumab and ustekinumab were the only immunosuppressive agents evaluated for longer-term EASI75. Dupilumab was the only agent evaluated for improvement in POEM during short-term follow-up.\nLow- to moderate-certainty evidence indicates a lower proportion of participants with SAEs after treatment with QAW039 and dupilumab compared to placebo during short-term follow-up, but low- to very low-certainty evidence suggests no difference in SAEs during short-term follow-up of other immunosuppressive agents compared to placebo.\nEvidence for effects of immunosuppressive agents on risk of any infection during short-term follow-up and SAEs during long-term follow-up compared with placebo was of low or very low certainty but did not indicate a difference.\nWe did not identify differences in other adverse events (AEs), but dupilumab is associated with specific AEs, including eye inflammation and eosinophilia.\nAuthors' conclusions\nOur findings indicate that dupilumab is the most effective biological treatment for eczema. Compared to placebo, dupilumab reduces eczema signs and symptoms in the short term for people with moderate to severe atopic eczema. Short-term safety outcomes from clinical trials did not reveal new safety concerns with dupilumab. Overall, evidence for the efficacy of most other immunosuppressive treatments for moderate to severe atopic eczema is of low or very low certainty.\nGiven the lack of data comparing conventional with newer biological treatments for the primary outcomes, there remains high uncertainty for ranking the efficacy and safety of conventional treatments such as ciclosporin and biological treatments such as dupilumab.\nMost studies were placebo-controlled and assessed only short-term efficacy of immunosuppressive agents. Further adequately powered head-to-head RCTs should evaluate comparative long-term efficacy and safety of available treatments for moderate to severe eczema.\n\nGiven the provided abstract, please respond to the following query: \"How we identified and assessed the evidence\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "First, we searched the medical literature for randomised controlled studies (studies where people are randomly divided into different treatment groups) because these studies provide the most robust evidence about the effects of a treatment. We then compared study results and summarised the evidence from all studies. Finally, we assessed how certain the evidence was. To do this, we considered factors such as the way studies were conducted, the size of studies, and the consistency of findings across studies. Based on our assessments, we categorised the evidence as being of very low, low, moderate, or high certainty." } ]

[ { "role": "user", "content": "Abstract: Background\nThere is inconclusive evidence from observational studies to suggest that people who eat a diet rich in antioxidant vitamins (carotenoids, vitamins C, and E) or minerals (selenium and zinc) may be less likely to develop age-related macular degeneration (AMD).\nObjectives\nTo determine whether or not taking antioxidant vitamin or mineral supplements, or both, prevent the development of AMD.\nSearch methods\nWe searched the Cochrane Central Register of Controlled Trials (CENTRAL) (which contains the Cochrane Eyes and Vision Trials Register) (2017, Issue 2), MEDLINE Ovid (1946 to 29 March 2017), Embase Ovid (1947 to 29 March 2017), AMED (Allied and Complementary Medicine Database) (1985 to 29 March 2017), OpenGrey (System for Information on Grey Literature in Europe) (www.opengrey.eu/); searched 29 March 2017, the ISRCTN registry (www.isrctn.com/editAdvancedSearch); searched 29 March 2017, ClinicalTrials.gov (www.clinicaltrials.gov); searched 29 March 2017 and the WHO International Clinical Trials Registry Platform (ICTRP) (www.who.int/ictrp/search/en); searched 29 March 2017. We did not use any date or language restrictions in the electronic searches for trials.\nSelection criteria\nWe included all randomised controlled trials (RCTs) comparing an antioxidant vitamin or mineral supplement (alone or in combination) to control.\nData collection and analysis\nBoth review authors independently assessed risk of bias in the included studies and extracted data. One author entered data into RevMan 5; the other author checked the data entry. We pooled data using a fixed-effect model. We graded the certainty of the evidence using GRADE.\nMain results\nWe included a total of five RCTs in this review with data available for 76,756 people. The trials were conducted in Australia, Finland, and the USA, and investigated vitamin C, vitamin E, beta-carotene, and multivitamin supplements. All trials were judged to be at low risk of bias.\nFour studies reported the comparison of vitamin E with placebo. Average treatment and follow-up duration ranged from 4 to 10 years. Data were available for a total of 55,614 participants. There was evidence that vitamin E supplements do not prevent the development of any AMD (risk ratio (RR) 0.97, 95% confidence interval (CI) 0.90 to 1.06; high-certainty evidence), and may slightly increase the risk of late AMD (RR 1.22, 95% CI 0.89 to 1.67; moderate-certainty evidence) compared with placebo. Only one study (941 participants) reported data separately for neovascular AMD and geographic atrophy. There were 10 cases of neovascular AMD (RR 3.62, 95% CI 0.77 to 16.95; very low-certainty evidence), and four cases of geographic atrophy (RR 2.71, 95% CI 0.28 to 26.0; very low-certainty evidence). Two trials reported similar numbers of adverse events in the vitamin E and placebo groups. Another trial reported excess of haemorrhagic strokes in the vitamin E group (39 versus 23 events, hazard ratio 1.74, 95% CI 1.04 to 2.91, low-certainty evidence).\nTwo studies reported the comparison of beta-carotene with placebo. These studies took place in Finland and the USA. Both trials enrolled men only. Average treatment and follow-up duration was 6 years and 12 years. Data were available for a total of 22,083 participants. There was evidence that beta-carotene supplements did not prevent any AMD (RR 1.00, 95% CI 0.88 to 1.14; high-certainty evidence) nor have an important effect on late AMD (RR 0.90, 95% CI 0.65 to 1.24; moderate-certainty evidence). Only one study (941 participants) reported data separately for neovascular AMD and geographic atrophy. There were 10 cases of neovascular AMD (RR 0.61, 95% CI 0.17 to 2.15; very low-certainty evidence) and 4 cases of geographic atrophy (RR 0.31 95% CI 0.03 to 2.93; very low-certainty evidence). Beta-carotene was associated with increased risk of lung cancer in people who smoked.\nOne study reported the comparison of vitamin C with placebo, and multivitamin (Centrum Silver) versus placebo. This was a study in men in the USA with average treatment duration and follow-up of 8 years for vitamin C and 11 years for multivitamin. Data were available for a total of 14,236 participants. AMD was assessed by self-report followed by medical record review. There was evidence that vitamin C supplementation did not prevent any AMD (RR 0.96, 95% CI 0.79 to 1.18; high-certainty evidence) or late AMD (RR 0.94, 0.61 to 1.46; moderate-certainty evidence). There was a slight increased risk of any AMD (RR 1.21, 95% CI 1.02 to 1.43; moderate-certainty evidence) and late AMD (RR 1.22, 95% CI 0.88 to 1.69; moderate-certainty evidence) in the multivitamin group. Neovascular AMD and geographic atrophy were not reported separately. Adverse effects were not reported but there was possible increased risk of skin rashes in the multivitamin group.\nAdverse effects were not consistently reported in these eye studies, but there is evidence from other large studies that beta-carotene increases the risk of lung cancer in people who smoke or who have been exposed to asbestos.\nNone of the studies reported quality of life or resource use and costs.\nAuthors' conclusions\nTaking vitamin E or beta-carotene supplements will not prevent or delay the onset of AMD. The same probably applies to vitamin C and the multivitamin (Centrum Silver) investigated in the one trial reported to date. There is no evidence with respect to other antioxidant supplements, such as lutein and zeaxanthin. Although generally regarded as safe, vitamin supplements may have harmful effects, and clear evidence of benefit is needed before they can be recommended. People with AMD should see the related Cochrane Review on antioxidant vitamin and mineral supplements for slowing the progression of AMD, written by the same review team.\n\nGiven the provided abstract, please respond to the following query: \"What are the main results of the review?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "The Cochrane researchers found five relevant studies. The studies were large and included a total of 76,756 people. They took place in Australia, Finland, and the USA. The studies compared vitamin C, vitamin E, beta-carotene, and multivitamin supplements with placebo.\nThe review showed that, compared with taking a placebo:\n∙ Taking vitamin E supplements made little or no difference to the chances of developing AMD (high-certainty evidence).\n∙ Taking vitamin E supplements made little difference, or slightly increased, the chances of developing late AMD (moderate-certainty evidence).\n∙ Taking beta-carotene made little or no difference to the chances of developing any AMD (high-certainty evidence) or late AMD (moderate-certainty evidence).\n∙ Taking vitamin C made little or no difference to the chances of developing any AMD (high-certainty evidence) or late AMD (moderate-certainty evidence).\n∙ Taking multivitamin tablets may slightly increase the chances of developing any AMD or late AMD (moderate-certainty evidence).\n∙ Adverse effects were not consistently reported in these eye studies, but there is evidence from other large studies that beta-carotene increases the risk of lung cancer in people who smoke, or who have been exposed to asbestos.\nNone of the studies reported quality of life or resource use and costs." } ]

[ { "role": "user", "content": "Abstract: Background\nEpidural analgesia in labour prolongs the second stage and increases instrumental delivery. It has been suggested that a more upright maternal position during all or part of the second stage may counteract these adverse effects. This is an update of a Cochrane Review published in 2017.\nObjectives\nTo assess the effects of different birthing positions (upright or recumbent) during the second stage of labour, on maternal and fetal outcomes for women with epidural analgesia.\nSearch methods\nWe searched Cochrane Pregnancy and Childbirth’s Trials Register, ClinicalTrials.gov, the WHO International Clinical Trials Registry Platform (ICTRP) (5 June 2018), and the reference lists of retrieved studies.\nSelection criteria\nAll randomised or quasi-randomised trials including pregnant women (primigravidae or multigravidae) in the second stage of induced or spontaneous labour receiving epidural analgesia of any kind. Cluster-randomised controlled trials would have been eligible for inclusion but we found none. Studies published in abstract form only were also eligible.\nWe assumed the experimental intervention to be maternal use of any upright position during the second stage of labour, compared with the control condition of remaining in any recumbent position.\nData collection and analysis\nTwo review authors independently assessed trials for inclusion, assessed risks of bias, and extracted data. We contacted study authors to obtain missing data. We assessed the quality of the evidence using the GRADE approach.\nWe carried out a planned sensitivity analysis of the three studies with low risks of bias for allocation concealment and incomplete outcome data reporting, and further excluded one study with a co-intervention (this was not prespecified).\nMain results\nWe include eight randomised controlled trials, involving 4464 women, comparing upright positions versus recumbent positions in this update. Five were conducted in the UK, one in France and two in Spain.\nThe largest UK trial accounted for three-quarters of all review participants, and we judged it to have low risk of bias. We assessed two other trials as being at low risk of selection and attrition bias. We rated four studies at unclear or high risk of bias for both selection and attrition bias and one study as high risk of bias due to a co-intervention. The trials varied in their comparators, with five studies comparing different positions (upright and recumbent), two comparing ambulation with (recumbent) non-ambulation, and one study comparing postural changes guided by a physiotherapist to a recumbent position.\nOverall, there may be little or no difference between upright and recumbent positions for our combined primary outcome of operative birth (caesarean or instrumental vaginal): average risk ratio (RR) 0.86, 95% confidence interval (CI) 0.70 to 1.07; 8 trials, 4316 women; I2 = 78%; low-quality evidence. It is uncertain whether the upright position has any impact on caesarean section (RR 0.94, 95% CI 0.61 to 1.46; 8 trials, 4316 women; I2 = 47%; very low-quality evidence), instrumental vaginal birth (RR 0.90, 95% CI 0.72 to 1.12; 8 trials, 4316 women; I2 = 69%) and the duration of the second stage of labour (mean difference (MD) 6.00 minutes, 95% CI −37.46 to 49.46; 3 trials, 456 women; I2 = 96%), because we rated the quality of the evidence as very low for these outcomes. Maternal position in the second stage of labour probably makes little or no difference to postpartum haemorrhage (PPH), (PPH requiring blood transfusion): RR 1.20, 95% CI 0.83 to 1.72; 1 trial, 3093 women; moderate-quality evidence. Maternal satisfaction with the overall childbirth experience was slightly lower in the upright group: RR 0.95, 95% CI 0.92 to 0.99; 1 trial, 2373 women. Fewer babies were born with low cord pH in the upright group: RR 0.43, 95% CI 0.20 to 0.90; 2 trials, 3159 infants; moderate-quality evidence.\nThe results were less clear for other maternal or fetal outcomes, including trauma to the birth canal requiring suturing (average RR 1.00, 95% CI 0.89 to 1.13; 3 trials, 3266 women; I2 = 46%; low-quality evidence), abnormal fetal heart patterns requiring intervention (RR 1.69, 95% CI 0.32 to 8.84; 1 trial, 107 women; very low-quality evidence), or admission to neonatal intensive care unit (RR 0.54, 95% CI 0.02 to 12.73; 1 trial, 66 infants; very low-quality evidence). However, the CIs around some of these estimates were wide, and we cannot rule out clinically important effects.\nIn our sensitivity analysis of studies at low risk of bias, upright positions increase the chance of women having an operative birth: RR 1.11, 95% CI 1.03 to 1.20; 3 trials, 3609 women; high-quality evidence. In absolute terms, this equates to 63 more operative births per 1000 women (from 17 more to 115 more). This increase appears to be due to the increase in caesarean section in the upright group (RR 1.29; 95% CI 1.05 to 1.57; 3 trials, 3609 women; high-quality evidence), which equates to 25 more caesarean sections per 1000 women (from 4 more to 49 more). In the sensitivity analysis there was no clear impact on instrumental vaginal births: RR 1.08, 95% CI 0.91 to 1.30; 3 trials, 3609 women; low-quality evidence.\nAuthors' conclusions\nThere may be little or no difference in operative birth between women who adopt recumbent or supine positions during the second stage of labour with an epidural analgesia. However, the studies are heterogeneous, probably related to differing study designs and interventions, differing adherence to the allocated intervention and possible selection and attrition bias. Sensitivity analysis of studies at low risk of bias indicated that recumbent positions may reduce the need for operative birth and caesarean section, without increasing instrumental delivery. Mothers may be more satisfied with their experience of childbirth by adopting a recumbent position. The studies in this review looked at left or right lateral and semi-recumbent positions. Recumbent positions such as flat on the back or lithotomy are not generally used due to the possibility of aorto-caval compression, although we acknowledge that these recumbent positions were not the focus of trials included in this review.\n\nGiven the provided abstract, please respond to the following query: \"What is the issue?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "Late labour, sometimes called the second stage, is made up of a latent or passive phase where the mother is fully dilated and the baby’s head descends without the mother pushing, and an active phase when the mother has an urge to push and the baby is born.\nWe wanted to find out whether different birthing positions (upright or lying down) during the second stage of labour could change birth outcomes both for women who have used an epidural for pain relief and for their babies. Outcomes included caesarean section, instrumental birth, excessive bleeding or stitches following tears to the vagina during the birth. For babies, we looked at whether they coped well with labour or needed admission to a special care baby unit. We also wanted to determine women's views on the experience of childbirth and their satisfaction with the labour. This is an update of a review first published in 2013." } ]

[ { "role": "user", "content": "Abstract: Background\nCurrent guidelines recommend oral anticoagulation therapy for patients with atrial fibrillation (AF) with one or more risk factors for stroke; however, anticoagulation control (time in therapeutic range (TTR)) with vitamin K antagonists (VKAs) is dependent on many factors. Educational and behavioural interventions may impact patients' ability to maintain their international normalised ratio (INR) control. This is an updated version of the original review first published in 2013.\nObjectives\nTo evaluate the effects of educational and behavioural interventions for oral anticoagulation therapy (OAT) on TTR in patients with AF.\nSearch methods\nWe updated searches from the previous review by searching the Cochrane Central Register of Controlled Trials (CENTRAL) and the Database of Abstracts of Reviews of Effects (DARE) in The Cochrane Library (January 2016, Issue 1), MEDLINE Ovid (1949 to February week 1 2016), EMBASE Classic + EMBASE Ovid (1980 to Week 7 2016), PsycINFO Ovid (1806 to Week 1 February 2016) and CINAHL Plus with Full Text EBSCO (1937 to 16/02/2016). We applied no language restrictions.\nSelection criteria\nWe included randomised controlled trials evaluating the effect of any educational and behavioural intervention compared with usual care, no intervention, or intervention in combination with other self-management techniques among adults with AF who were eligible for, or currently receiving, OAT.\nData collection and analysis\nTwo of the review authors independently selected studies and extracted data. Risk of bias was assessed using the Cochrane 'Risk of bias' tool. We included outcome data on TTR, decision conflict (patient's uncertainty in making health-related decisions), percentage of INRs in the therapeutic range, major bleeding, stroke and thromboembolic events, patient knowledge, patient satisfaction, quality of life (QoL), beliefs about medication, illness perceptions, and anxiety and depression. We pooled data for three outcomes - TTR, anxiety and depression, and decision conflict - and reported mean differences (MD). Where insufficient data were present to conduct a meta-analysis, we reported effect sizes and confidence intervals (CI) from the included studies. We evaluated the quality of evidence using the Grading of Recommendations Assessment, Development and Evaluation (GRADE) framework.\nMain results\nEleven trials with a total of 2246 AF patients (ranging from 14 to 712 by study) were included within the review. Studies included education, decision aids, and self-monitoring plus education interventions. The effect of self-monitoring plus education on TTR was uncertain compared with usual care (MD 6.31, 95% CI -5.63 to 18.25, I2 = 0%, 2 trials, 69 participants, very low-quality evidence). We found small but positive effects of education on anxiety (MD -0.62, 95% CI -1.21 to -0.04, I2 = 0%, 2 trials, 587 participants, low-quality evidence) and depression (MD -0.74, 95% CI -1.34 to -0.14, I2 = 0%, 2 trials, 587 participants, low-quality evidence) compared with usual care. The effect of decision aids on decision conflict favoured usual care (MD -0.1, 95% CI -0.17 to -0.02, I2 = 0%, 2 trials, 721 participants, low-quality evidence).\nAuthors' conclusions\nThis review demonstrates that there is insufficient evidence to draw definitive conclusions regarding the impact of educational or behavioural interventions on TTR in AF patients receiving OAT. Thus, more trials are needed to examine the impact of interventions on anticoagulation control in AF patients and the mechanisms by which they are successful. It is also important to explore the psychological implications for patients suffering from this long-term chronic condition.\n\nGiven the provided abstract, please respond to the following query: \"Review question\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "We reviewed the evidence about the effects of educational and behavioural interventions in patients with atrial fibrillation who are taking oral anticoagulant medication." } ]

[ { "role": "user", "content": "Abstract: Background\nIntestinal dysbiosis may contribute to the pathogenesis of necrotising enterocolitis (NEC) in very preterm or very low birth weight (VLBW) infants. Dietary supplementation with synbiotics (probiotic micro-organisms combined with prebiotic oligosaccharides) to modulate the intestinal microbiome has been proposed as a strategy to reduce the risk of NEC and associated mortality and morbidity.\nObjectives\nTo assess the effect of enteral supplementation with synbiotics (versus placebo or no treatment, or versus probiotics or prebiotics alone) for preventing NEC and associated morbidity and mortality in very preterm or VLBW infants.\nSearch methods\nWe searched the Cochrane Central Register of Controlled Trials, MEDLINE, Embase, the Maternity and Infant Care database and CINAHL, from earliest records to 17 June 2021. We searched clinical trials databases and conference proceedings, and examined the reference lists of retrieved articles.\nSelection criteria\nWe included randomised controlled trials (RCTs) and quasi-RCTs comparing prophylactic synbiotics supplementation with placebo or no synbiotics in very preterm (< 32 weeks' gestation) or very low birth weight (< 1500 g) infants.\nData collection and analysis\nTwo review authors separately performed the screening and selection process,  evaluated risk of bias of the trials, extracted data, and synthesised effect estimates using risk ratio (RR), risk difference (RD), and mean difference, with associated 95% confidence intervals (CIs). We used the GRADE approach to assess the level of certainty for effects on NEC, all-cause mortality, late-onset invasive infection, and neurodevelopmental impairment.\nMain results\nWe included six trials in which a total of 925 infants participated. Most trials were small (median sample size 200). Lack of clarity on methods used to conceal allocation and mask caregivers or investigators were potential sources of bias in four of the trials. The studied synbiotics preparations contained lactobacilli or bifidobacteria (or both) combined with fructo- or galacto-oligosaccharides (or both).\nMeta-analyses suggested that synbiotics may reduce the risk of NEC (RR 0.18, 95% CI 0.09 to 0.40; RD 70 fewer per 1000, 95% CI 100 fewer to 40 fewer; number needed to treat for an additional beneficial outcome (NNTB) 14, 95% CI 10 to 25; six trials (907 infants); low certainty evidence); and all-cause mortality prior to hospital discharge (RR 0.53, 95% CI 0.33 to 0.85; RD 50 fewer per 1000, 95% CI 120 fewer to 100 fewer; NNTB 20, 95% CI 8 to 100; six trials (925 infants); low-certainty evidence). Synbiotics may have little or no effect on late-onset invasive infection, but the evidence is very uncertain (RR 0.84, 95% CI 0.58 to 1.21; RD 20 fewer per 1000, 95% CI 70 fewer to 30 more; five trials (707 infants); very low-certainty evidence). None of the trials assessed neurodevelopmental outcomes. In the absence of high levels of heterogeneity, we did not undertake any subgroup analysis (including the type of feeding).\nAuthors' conclusions\nThe available trial data provide only low-certainty evidence about the effects of synbiotics on the risk of NEC and associated morbidity and mortality for very preterm or very low birth weight infants. Our confidence in the effect estimates is limited; the true effects may be substantially different from these estimates. Large, high-quality trials would be needed to provide evidence of sufficient validity and applicability to inform policy and practice.\n\nGiven the provided abstract, please respond to the following query: \"What did we want to find out?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "One way to help prevent necrotising enterocolitis may be to add synbiotics (combinations of probiotic bacteria or yeasts plus non-digestible sugars to support probiotic growth and colonisation) to milk feeds. We wanted to find out whether synbiotics might benefit very preterm and very low birth weight infants. Our outcomes of interest included necrotising enterocolitis, death from any cause, serious infection, duration of hospitalisation since birth and neurodevelopmental outcomes." } ]

[ { "role": "user", "content": "Abstract: Background\nMalabsorption and deficiency of fat-soluble vitamins K may occur in cystic fibrosis, a genetic disorder affecting multiple organs. Vitamin K is known to play an important role in both blood coagulation and bone formation, hence the role of supplementation of vitamin K in this category needs to be reviewed. This is an updated version of the review.\nObjectives\nTo assess the effects of vitamin K supplementation in people with cystic fibrosis and to investigate the hypotheses that vitamin K will decrease deficiency-related coagulopathy, increase bone mineral density, decrease risk of fractures and improve quality of life in people with CF. Also to determine the optimal dose and route of administration of vitamin K for people with CF (for both routine and therapeutic use).\nSearch methods\nWe searched the Cochrane Cystic Fibrosis and Genetic Disorders Group's Trials Register comprising references identified from comprehensive electronic database searches and handsearches of relevant journals and abstract books of conference proceedings.\nMost recent search: 12 August 2019.\nSelection criteria\nRandomised controlled trials of all preparations of vitamin K used as a supplement compared to either no supplementation (or placebo) at any dose or route and for any duration, in patients with cystic fibrosis.\nData collection and analysis\nTwo authors independently screened papers, extracted trial details and assessed their risk of bias. The quality of the evidence was assessed using the GRADE criteria.\nMain results\nThree trials (total 70 participants, aged 8 to 46 years) assessed as having a moderate risk of bias were included. One trial compared vitamin K to placebo, a second to no supplementation and the third compared two doses of vitamin K. No trial in either comparison reported our primary outcomes of coagulation and quality of life or the secondary outcomes of nutritional parameters and adverse events.\nVitamin K versus control\nTwo trials compared vitamin K to control, but data were not available for analysis. One 12-month trial (n = 38) compared 10 mg vitamin K daily or placebo in a parallel design and one trial (n = 18) was of cross-over design with no washout period and compared 5 mg vitamin K/week for four-weeks to no supplementation for four-weeks. Only the 12-month trial reported on the primary outcome of bone formation; we are very uncertain whether vitamin K supplementation has any effect on bone mineral density at the femoral hip or lumbar spine (very low-quality evidence). Both trials reported an increase in serum vitamin K levels and a decrease in undercarboxylated osteocalcin levels. The cross-over trial also reported that levels of proteins induced by vitamin K absence (PIVKA) showed a decrease and a return to normal following supplementation, but due to the very low-quality evidence we are not certain that this is due to the intervention.\nHigh-dose versus low-dose vitamin K\nOne parallel trial (n = 14) compared 1 mg vitamin K/day to 5 mg vitamin K/day for four weeks. The trial did report that there did not appear to be any difference in serum undercarboxylated osteocalcin or vitamin K levels (very low-quality evidence). While the trial reported that serum vitamin K levels improved with supplementation, there was no difference between the high-dose and low-dose groups.\nAuthors' conclusions\nThere is very low-quality evidence of any effect of vitamin K in people with cystic fibrosis. While there is no evidence of harm, until better evidence is available the ongoing recommendations by national CF guidelines should be followed.\n\nGiven the provided abstract, please respond to the following query: \"Key results\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "No trial in either comparison reported our primary outcomes of blood clotting and quality of life or the secondary measures of nutrition and adverse events.\nVitamin K versus control\nOnly the 12-month trial reported on the primary outcome of bone formation; we are very uncertain whether vitamin K supplementation has any effect on bone mineral density measured at the hip or lower back (very low-quality evidence). Both trials reported an increase in vitamin K levels in the blood and a decrease in undercarboxylated osteocalcin levels (this is an indicator of the risk of hip fracture). The four-week trial also reported that levels of proteins induced by vitamin K absence (PIVKA) dropped and returned to normal levels, but due to the very low-quality evidence we are not certain that this is due to supplementation.\nHigh-dose versus low-dose vitamin K\nThe trial reported that while vitamin K levels improved there did not seem to be any difference between the high-dose and low-dose groups. There also did not seem to be any difference in undercarboxylated osteocalcin levels (very low-quality evidence)." } ]

[ { "role": "user", "content": "Abstract: Background\nOverweight and obesity are increasing worldwide and are considered to be a major public health issue of the 21st century. Introducing taxation of the fat content in foods is considered a potentially powerful policy tool to reduce consumption of foods high in fat or saturated fat, or both.\nObjectives\nTo assess the effects of taxation of the fat content in food on consumption of total fat and saturated fat, energy intake, overweight, obesity, and other adverse health outcomes in the general population.\nSearch methods\nWe searched CENTRAL, Cochrane Database of Systematic Reviews, MEDLINE, Embase, and 15 other databases and trial registers on 12 September 2019. We handsearched the reference lists of all records of included studies, searched websites of international organizations and institutions (14 October 2019), and contacted review advisory group members to identify planned, ongoing, or unpublished studies (26 February 2020).\nSelection criteria\nIn line with Cochrane Effective Practice and Organisation of Care Group (EPOC) criteria, we included the following study types: randomized controlled trials (RCTs), cluster-randomized controlled trials (cRCTs), non-randomized controlled trials (nRCTs), controlled before-after (CBA) studies, and interrupted time series studies. We included studies that evaluated the effects of taxes on the fat content in foods. Such a tax could be expressed as sales, excise, or special value added tax (VAT) on the final product or an intermediary product. Eligible interventions were taxation at any level, with no restriction on the duration or the implementation level (i.e. local, regional, national, or multinational). Eligible study populations were children (zero to 17 years) and adults (18 years or older) from any country and setting. We excluded studies that focused on specific subgroups only (e.g. people receiving pharmaceutical intervention; people undergoing a surgical intervention; ill people who are overweight or obese as a side effect, such as those with thyroiditis and depression; and people with chronic illness). Primary outcomes were total fat consumption, consumption of saturated fat, energy intake through fat, energy intake through saturated fat, total energy intake, and incidence/prevalence of overweight or obesity. We did not exclude studies based on country, setting, comparison, or population.\nData collection and analysis\nWe used standard Cochrane methods for all phases of the review. Risk of bias of the included studies was assessed using the criteria of Cochrane’s ‘Risk of bias’ tool and the EPOC Group’s guidance. Results of the review are summarized narratively and the certainty of the evidence was assessed using the GRADE approach. These steps were done by two review authors, independently.\nMain results\nWe identified 23,281 records from searching electronic databases and 1173 records from other sources, leading to a total of 24,454 records. Two studies met the criteria for inclusion in the review. Both included studies investigated the effect the Danish tax on saturated fat contained in selected food items between 2011 and 2012. Both studies used an interrupted time series design. Neither included study had a parallel control group from another geographic area. The included studies investigated an unbalanced panel of approximately 2000 households in Denmark and the sales data from a specific Danish supermarket chain (1293 stores). Therefore, the included studies did not address individual participants, and no restriction regarding age, sex, and socioeconomic characteristics were defined. We judged the overall risk of bias of the two included studies as unclear.\nFor the outcome total consumption of fat, a reduction of 41.8 grams per week per person in a household (P < 0.001) was estimated. For the consumption of saturated fat, one study reported a reduction of 4.2% from minced beef sales, a reduction of 5.8% from cream sales, and an increase of 0.5% to sour cream sales (no measures of statistical precision were reported for these estimates). These estimates are based on a restricted number of food types and derived from sales data; they do not measure individual intake. Moreover, these estimates do not account for other relevant sources of fat intake (e.g. packaged or processed food) or other food outlets (e.g. restaurants or cafeterias); hence, we judged the evidence on the effect of taxation on total fat consumption or saturated fat consumption to be very uncertain. We did not identify evidence on the effect of the intervention on energy intake or the incidence or prevalence of overweight or obesity.\nAuthors' conclusions\nGiven the very low quality of the evidence currently available, we are unable to reliably establish whether a tax on total fat or saturated fat is effective or ineffective in reducing consumption of total fat or saturated fat. There is currently no evidence on the effect of a tax on total fat or saturated fat on total energy intake or energy intake through saturated fat or total fat, or preventing the incidence or reducing the prevalence of overweight or obesity.\n\nGiven the provided abstract, please respond to the following query: \"Search date\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "we included evidence published up to September 2019." } ]

[ { "role": "user", "content": "Abstract: Background\nViral epidemics or pandemics of acute respiratory infections (ARIs) pose a global threat. Examples are influenza (H1N1) caused by the H1N1pdm09 virus in 2009, severe acute respiratory syndrome (SARS) in 2003, and coronavirus disease 2019 (COVID-19) caused by SARS-CoV-2 in 2019. Antiviral drugs and vaccines may be insufficient to prevent their spread. This is an update of a Cochrane Review last published in 2020. We include results from studies from the current COVID-19 pandemic.\nObjectives\nTo assess the effectiveness of physical interventions to interrupt or reduce the spread of acute respiratory viruses.\nSearch methods\nWe searched CENTRAL, PubMed, Embase, CINAHL, and two trials registers in October 2022, with backwards and forwards citation analysis on the new studies.\nSelection criteria\nWe included randomised controlled trials (RCTs) and cluster-RCTs investigating physical interventions (screening at entry ports, isolation, quarantine, physical distancing, personal protection, hand hygiene, face masks, glasses, and gargling) to prevent respiratory virus transmission.\nData collection and analysis\nWe used standard Cochrane methodological procedures.\nMain results\nWe included 11 new RCTs and cluster-RCTs (610,872 participants) in this update, bringing the total number of RCTs to 78. Six of the new trials were conducted during the COVID-19 pandemic; two from Mexico, and one each from Denmark, Bangladesh, England, and Norway. We identified four ongoing studies, of which one is completed, but unreported, evaluating masks concurrent with the COVID-19 pandemic.\nMany studies were conducted during non-epidemic influenza periods. Several were conducted during the 2009 H1N1 influenza pandemic, and others in epidemic influenza seasons up to 2016. Therefore, many studies were conducted in the context of lower respiratory viral circulation and transmission compared to COVID-19. The included studies were conducted in heterogeneous settings, ranging from suburban schools to hospital wards in high-income countries; crowded inner city settings in low-income countries; and an immigrant neighbourhood in a high-income country. Adherence with interventions was low in many studies.\nThe risk of bias for the RCTs and cluster-RCTs was mostly high or unclear.\nMedical/surgical masks compared to no masks\nWe included 12 trials (10 cluster-RCTs) comparing medical/surgical masks versus no masks to prevent the spread of viral respiratory illness (two trials with healthcare workers and 10 in the community). Wearing masks in the community probably makes little or no difference to the outcome of influenza-like illness (ILI)/COVID-19 like illness compared to not wearing masks (risk ratio (RR) 0.95, 95% confidence interval (CI) 0.84 to 1.09; 9 trials, 276,917 participants; moderate-certainty evidence. Wearing masks in the community probably makes little or no difference to the outcome of laboratory-confirmed influenza/SARS-CoV-2 compared to not wearing masks (RR 1.01, 95% CI 0.72 to 1.42; 6 trials, 13,919 participants; moderate-certainty evidence). Harms were rarely measured and poorly reported (very low-certainty evidence).\nN95/P2 respirators compared to medical/surgical masks\nWe pooled trials comparing N95/P2 respirators with medical/surgical masks (four in healthcare settings and one in a household setting). We are very uncertain on the effects of N95/P2 respirators compared with medical/surgical masks on the outcome of clinical respiratory illness (RR 0.70, 95% CI 0.45 to 1.10; 3 trials, 7779 participants; very low-certainty evidence). N95/P2 respirators compared with medical/surgical masks may be effective for ILI (RR 0.82, 95% CI 0.66 to 1.03; 5 trials, 8407 participants; low-certainty evidence). Evidence is limited by imprecision and heterogeneity for these subjective outcomes. The use of a N95/P2 respirators compared to medical/surgical masks probably makes little or no difference for the objective and more precise outcome of laboratory-confirmed influenza infection (RR 1.10, 95% CI 0.90 to 1.34; 5 trials, 8407 participants; moderate-certainty evidence). Restricting pooling to healthcare workers made no difference to the overall findings. Harms were poorly measured and reported, but discomfort wearing medical/surgical masks or N95/P2 respirators was mentioned in several studies (very low-certainty evidence).\nOne previously reported ongoing RCT has now been published and observed that medical/surgical masks were non-inferior to N95 respirators in a large study of 1009 healthcare workers in four countries providing direct care to COVID-19 patients.\nHand hygiene compared to control\nNineteen trials compared hand hygiene interventions with controls with sufficient data to include in meta-analyses. Settings included schools, childcare centres and homes. Comparing hand hygiene interventions with controls (i.e. no intervention), there was a 14% relative reduction in the number of people with ARIs in the hand hygiene group (RR 0.86, 95% CI 0.81 to 0.90; 9 trials, 52,105 participants; moderate-certainty evidence), suggesting a probable benefit. In absolute terms this benefit would result in a reduction from 380 events per 1000 people to 327 per 1000 people (95% CI 308 to 342). When considering the more strictly defined outcomes of ILI and laboratory-confirmed influenza, the estimates of effect for ILI (RR 0.94, 95% CI 0.81 to 1.09; 11 trials, 34,503 participants; low-certainty evidence), and laboratory-confirmed influenza (RR 0.91, 95% CI 0.63 to 1.30; 8 trials, 8332 participants; low-certainty evidence), suggest the intervention made little or no difference. We pooled 19 trials (71, 210 participants) for the composite outcome of ARI or ILI or influenza, with each study only contributing once and the most comprehensive outcome reported. Pooled data showed that hand hygiene may be beneficial with an 11% relative reduction of respiratory illness (RR 0.89, 95% CI 0.83 to 0.94; low-certainty evidence), but with high heterogeneity. In absolute terms this benefit would result in a reduction from 200 events per 1000 people to 178 per 1000 people (95% CI 166 to 188). Few trials measured and reported harms (very low-certainty evidence).\nWe found no RCTs on gowns and gloves, face shields, or screening at entry ports.\nAuthors' conclusions\nThe high risk of bias in the trials, variation in outcome measurement, and relatively low adherence with the interventions during the studies hampers drawing firm conclusions. There were additional RCTs during the pandemic related to physical interventions but a relative paucity given the importance of the question of masking and its relative effectiveness and the concomitant measures of mask adherence which would be highly relevant to the measurement of effectiveness, especially in the elderly and in young children.\nThere is uncertainty about the effects of face masks. The low to moderate certainty of evidence means our confidence in the effect estimate is limited, and that the true effect may be different from the observed estimate of the effect. The pooled results of RCTs did not show a clear reduction in respiratory viral infection with the use of medical/surgical masks. There were no clear differences between the use of medical/surgical masks compared with N95/P2 respirators in healthcare workers when used in routine care to reduce respiratory viral infection. Hand hygiene is likely to modestly reduce the burden of respiratory illness, and although this effect was also present when ILI and laboratory-confirmed influenza were analysed separately, it was not found to be a significant difference for the latter two outcomes. Harms associated with physical interventions were under-investigated.\nThere is a need for large, well-designed RCTs addressing the effectiveness of many of these interventions in multiple settings and populations, as well as the impact of adherence on effectiveness, especially in those most at risk of ARIs.\n\nGiven the provided abstract, please respond to the following query: \"What did we do?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "We searched for randomised controlled studies that looked at physical measures to stop people acquiring a respiratory virus infection.\nWe were interested in how many people in the studies caught a respiratory virus infection, and whether the physical measures had any unwanted effects." } ]

[ { "role": "user", "content": "Abstract: Background\nHand osteoarthritis (OA) is a prevalent joint disease that may lead to pain, stiffness and problems in performing hand-related activities of daily living. Currently, no cure for OA is known, and non-pharmacological modalities are recommended as first-line care. A positive effect of exercise in hip and knee OA has been documented, but the effect of exercise on hand OA remains uncertain.\nObjectives\nTo assess the benefits and harms of exercise compared with other interventions, including placebo or no intervention, in people with hand OA. Main outcomes are hand pain and hand function.\nSearch methods\nWe searched six electronic databases up until September 2015.\nSelection criteria\nAll randomised and controlled clinical trials comparing therapeutic exercise versus no exercise or comparing different exercise programmes.\nData collection and analysis\nTwo review authors independently selected trials, extracted data, assessed risk of bias and assessed the quality of the body of evidence using the GRADE approach. Outcomes consisted of both continuous (hand pain, physical function, finger joint stiffness and quality of life) and dichotomous outcomes (proportions of adverse events and withdrawals).\nMain results\nWe included seven studies in the review. Most studies were free from selection and reporting bias, but one study was available only as a congress abstract. It was not possible to blind participants to treatment allocation, and although most studies reported blinded outcome assessors, some outcomes (pain, function, stiffness and quality of life) were self-reported. The results may be vulnerable to performance and detection bias owing to unblinded participants and self-reported outcomes. Two studies with high drop-out rates may be vulnerable to attrition bias. We downgraded the overall quality of the body of evidence to low owing to potential detection bias (lack of blinding of participants on self-reported outcomes) and imprecision (studies were few, the number of participants was limited and confidence intervals were wide for the outcomes pain, function and joint stiffness). For quality of life, adverse events and withdrawals due to adverse events, we further downgraded the overall quality of the body of evidence to very low because studies were very few and confidence intervals were very wide.\nLow-quality evidence from five trials (381 participants) indicated that exercise reduced hand pain (standardised mean difference (SMD) -0.27, 95% confidence interval (CI) -0.47 to -0.07) post intervention. The absolute reduction in pain for the exercise group, compared with the control group, was 5% (1% to 9%) on a 0 to 10 point scale. Pain was estimated to be 3.9 points on this scale (0 = no pain) in the control group, and exercise reduced pain by 0.5 points (95% CI 0.1 to 0.9; number needed to treat for an additional beneficial outcome (NNTB) 9).\nFour studies (369 participants) indicated that exercise improved hand function (SMD -0.28, 95% CI -0.58 to 0.02) post intervention. The absolute improvement in function noted in the exercise group, compared with the control group, was 6% (0.4% worsening to 13% improvement). Function was estimated at 14.5 points on a 0 to 36 point scale (0 = no physical disability) in the control group, and exercise improved function by 2.2 points (95% CI -0.2 to 4.6; NNTB 9).\nOne study (113 participants) evaluated quality of life, and the effect of exercise on quality of life is currently uncertain (mean difference (MD) 0.30, 95% CI -3.72 to 4.32). The absolute improvement in quality of life for the exercise group, compared with the control group, was 0.3% (4% worsening to 4% improvement). Quality of life was 50.4 points on a 0 to 100 point scale (100 = maximum quality of life) in the control group, and the mean score in the exercise group was 0.3 points higher (3.5 points lower to 4.1 points higher).\nFour studies (369 participants) indicated that exercise reduced finger joint stiffness (SMD -0.36, 95% CI -0.58 to -0.15) post intervention. The absolute reduction in finger joint stiffness for the exercise group, compared with the control group, was 7% (3% to 10%). Finger joint stiffness was estimated at 4.5 points on a 0 to 10 point scale (0 = no stiffness) in the control group, and exercise improved stiffness by 0.7 points (95% CI 0.3 to 1.0; NNTB 7).\nThree studies reported intervention-related adverse events and withdrawals due to adverse events. The few reported adverse events consisted of increased finger joint inflammation and hand pain. Low-quality evidence from the three studies showed an increased likelihood of adverse events (risk ratio (RR) 4.55, 95% CI 0.53 to 39.31) and of withdrawals due to adverse events in the exercise group compared with the control group (RR 2.88, 95% CI 0.30 to 27.18), but the effect is uncertain and further research may change the estimates.\nIncluded studies did not measure radiographic joint structure changes. Two studies provided six-month follow-up data (220 participants), and one (102 participants) provided 12-month follow-up data. The positive effect of exercise on pain, function and joint stiffness was not sustained at medium- and long-term follow-up.\nThe exercise intervention varied largely in terms of dosage, content and number of supervised sessions. Participants were instructed to exercise two to three times a week in four studies, daily in two studies and three to four times daily in another study. Exercise interventions in all seven studies aimed to improve muscle strength and joint stability or function, but the numbers and types of exercises varied largely across studies. Four studies reported adherence to the exercise programme; in three studies, this was self-reported. Self-reported adherence to the recommended frequency of exercise sessions ranged between 78% and 94%. In the fourth study, 67% fulfilled at least 16 of the 18 scheduled exercise sessions.\nAuthors' conclusions\nWhen we pooled results from five studies, we found low-quality evidence showing small beneficial effects of exercise on hand pain, function and finger joint stiffness. Estimated effect sizes were small, and whether they represent a clinically important change may be debated. One study reported quality of life, and the effect is uncertain. Three studies reported on adverse events, which were very few and were not severe.\n\nGiven the provided abstract, please respond to the following query: \"Background - What is hand osteoarthritis and what is exercise?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "Osteoarthritis (OA) is a disease of the joints that causes joint pain, stiffness and swelling. It may hinder people from doing what they want and need to do. Usually, symptoms come on slowly but get worse over time. OA may occur in any joint but is most commonly seen in the hip, knee and small joints of the hand. No cure for OA is known, but available treatment alternatives may reduce pain and stiffness, increase function and improve self-management of the disease.\nExercise is an activity done to improve or maintain your fitness, ability or performance. A period of planned exercise often aims to improve or maintain muscle strength, physical fitness, joint mobility and overall health." } ]

[ { "role": "user", "content": "Abstract: Background\nPostpartum haemorrhage (PPH) - heaving bleeding within the first 24 hours after giving birth - is one of the main causes of death of women after childbirth. Antifibrinolytics, primarily tranexamic acid (TXA), have been shown to reduce bleeding in surgery and safely reduces mortality in trauma patients with bleeding without increasing the risk of adverse events.\nAn earlier Cochrane review on treatments for primary PPH covered all the various available treatments - that review has now been split by types of treatment. This new review concentrates only on the use of antifibrinolytic drugs for treating primary PPH.\nObjectives\nTo determine the effectiveness and safety of antifibrinolytic drugs for treating primary PPH.\nSearch methods\nWe searched Cochrane Pregnancy and Childbirth’s Trials Register, ClinicalTrials.gov, the WHO International Clinical Trials Registry Platform (ICTRP) (28 May 2017) and reference lists of retrieved studies.\nSelection criteria\nRandomised controlled trials (RCTs), including cluster-randomised trials of antifibrinolytic drugs (aprotinin, TXA, epsilon-aminocaproic acid (EACA) and aminomethylbenzoic acid, administered by whatever route) for primary PPH in women.\nParticipants in the trials were women after birth following a pregnancy of at least 24 weeks' gestation with a diagnosis of PPH, regardless of mode of birth (vaginal or caesarean section) or other aspects of third stage management.\nWe have not included quasi-randomised trials, or cross-over studies. Studies reported as abstracts have not been included if there was insufficient information to allow assessment of risk of bias.\nIn this review we only identified studies looking at TXA.\nData collection and analysis\nTwo review authors independently extracted data from each study using an agreed form. We entered data into Review Manager software and checked for accuracy.\nFor key review outcomes, we rated the quality of the evidence as 'high', 'moderate', 'low' or 'very low' according to the GRADE approach.\nMain results\nThree trials (20,412 women) met our inclusion criteria. Two trials (20,212 women) compared intravenous (IV) TXA with placebo or standard care and were conducted in acute hospital settings (labour ward, emergency department) (in high-, middle- and low-income countries).\nOne other trial (involving 200 women) was conducted in Iran and compared IV TXA with rectal misoprostol, but did not report on any of this review's primary or GRADE outcomes. There were no trials that assessed EACA, aprotinin or aminomethylbenzoic acid.\nStandard care plus IV TXA for the treatment of primary PPH compared with placebo or standard care alone\nTwo trials (20,212 women) assessed the effect of TXA for the treatment of primary PPH compared with placebo or standard care alone. The larger of these (The WOMAN trial) contributed over 99% of the data and was assessed as being at low risk of bias. The quality of the evidence varied for different outcomes, Overall, evidence was mainly graded as moderate to high quality.\nThe data show that IV TXA reduces the risk of maternal death due to bleeding (risk ratio (RR) 0.81, 95% confidence interval (CI) 0.65 to 1.00; two trials, 20,172 women; quality of evidence: moderate). The quality of evidence was rated as moderate due to imprecision of effect estimate. The effect was more evident in women given treatment between one and three hours after giving birth with no apparent reduction when given after three hours (< one hour = RR 0.80, 95% CI 0.55 to 1.16; one to three hours = RR 0.60, 95% CI 0.41 to 0.88; > three hours = RR 1.07, 95% 0.76 to 1.51; test for subgroup differences: Chi² = 4.90, df = 2 (P = 0.09), I² = 59.2%). There was no heterogeneity in the effect by mode of birth (test for subgroup differences: Chi² = 0.01, df = 1 (P = 0.91), I² = 0%). There were fewer deaths from all causes in women receiving TXA, although the 95% CI for the effect estimate crosses the line of no effect (RR 0.88, 95% CI 0.74 to 1.05; two trials, 20,172 women, quality of evidence: moderate). Results from one trial with 151 women suggest that blood loss of ≥ 500 mL after randomisation may be reduced (RR 0.50, 95% CI 0.27 to 0.93; one trial, 151 women; quality of evidence: low). TXA did not reduce the risk of serious maternal morbidity (RR 0.99, 95% CI 0.83 to 1.19; one trial, 20,015 women; quality of evidence: high), hysterectomy to control bleeding (RR 0.95, 95% CI 0.81 to 1.12; one trial, 20,017 women; quality of evidence: high) receipt of blood transfusion (any) (RR 1.00, 95% CI 0.97 to 1.03; two trials, 20,167 women; quality of evidence: moderate) or maternal vascular occlusive events (any), although results were imprecise for this latter outcome (RR 0.88, 95% CI 0.54 to 1.43; one trial, 20,018 women; quality of evidence: moderate). There was an increase in the use of brace sutures in the TXA group (RR 1.19, 95% CI 1.01, 1.41) and a reduction in the need for laparotomy for bleeding (RR 0.64, 95% CI 0.49, 0.85).\nAuthors' conclusions\nTXA when administered intravenously reduces mortality due to bleeding in women with primary PPH, irrespective of mode of birth, and without increasing the risk of thromboembolic events. Taken together with the reliable evidence of the effect of TXA in trauma patients, the evidence suggests that TXA is effective if given as early as possible.\nFacilities for IV administration may not be available in non-hospital settings therefore, alternative routes to IV administration need to be investigated.\n\nGiven the provided abstract, please respond to the following query: \"What does this mean?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "TXA when administered intravenously was effective in reducing mortality due to bleeding when given within three hours in women with primary postpartum haemorrhage without increasing the risk of other complications.\nFacilities for IV administration is not available in some settings so future research could look at whether TXA is effective and safe if given by other methods." } ]

[ { "role": "user", "content": "Abstract: Background\nHyperkalaemia is a common electrolyte abnormality caused by reduced renal potassium excretion in patients with chronic kidney diseases (CKD). Potassium binders, such as sodium polystyrene sulfonate and calcium polystyrene sulfonate, are widely used but may lead to constipation and other adverse gastrointestinal (GI) symptoms, reducing their tolerability. Patiromer and sodium zirconium cyclosilicate are newer ion exchange resins for treatment of hyperkalaemia which may cause fewer GI side-effects. Although more recent studies are focusing on clinically-relevant endpoints such as cardiac complications or death, the evidence on safety is still limited. Given the recent expansion in the available treatment options, it is appropriate to review the evidence of effectiveness and tolerability of all potassium exchange resins among people with CKD, with the aim to provide guidance to consumers, practitioners, and policy-makers.\nObjectives\nTo assess the benefits and harms of potassium binders for treating chronic hyperkalaemia among adults and children with CKD.\nSearch methods\nWe searched the Cochrane Kidney and Transplant Register of Studies up to 10 March 2020 through contact with the Information Specialist using search terms relevant to this review. Studies in the Register are identified through searches of CENTRAL, MEDLINE, and EMBASE, conference proceedings, the International Clinical Trials Register (ICTRP) Search Portal and ClinicalTrials.gov.\nSelection criteria\nRandomised controlled trials (RCTs) and quasi-randomised controlled studies (quasi-RCTs) evaluating potassium binders for chronic hyperkalaemia administered in adults and children with CKD.\nData collection and analysis\nTwo authors independently assessed risks of bias and extracted data. Treatment estimates were summarised by random effects meta-analysis and expressed as relative risk (RR) or mean difference (MD), with 95% confidence interval (CI). Evidence certainty was assessed using GRADE processes.\nMain results\nFifteen studies, randomising 1849 adult participants were eligible for inclusion. Twelve studies involved participants with CKD (stages 1 to 5) not requiring dialysis and three studies were among participants treated with haemodialysis. Potassium binders included calcium polystyrene sulfonate, sodium polystyrene sulfonate, patiromer, and sodium zirconium cyclosilicate. A range of routes, doses, and timing of drug administration were used. Study duration varied from 12 hours to 52 weeks (median 4 weeks). Three were cross-over studies. The mean study age ranged from 53.1 years to 73 years. No studies evaluated treatment in children.\nSome studies had methodological domains that were at high or unclear risks of bias, leading to low certainty in the results. Studies were not designed to measure treatment effects on cardiac arrhythmias or major GI symptoms.\nTen studies (1367 randomised participants) compared a potassium binder to placebo. The certainty of the evidence was low for all outcomes. We categorised treatments in newer agents (patiromer or sodium zirconium cyclosilicate) and older agents (calcium polystyrene sulfonate and sodium polystyrene sulfonate). Patiromer or sodium zirconium cyclosilicate may make little or no difference to death (any cause) (4 studies, 688 participants: RR 0.69, 95% CI 0.11, 4.32; I2 = 0%; low certainty evidence) in CKD. The treatment effect of older potassium binders on death (any cause) was unknown. One cardiovascular death was reported with potassium binder in one study, showing that there was no difference between patiromer or sodium zirconium cyclosilicate and placebo for cardiovascular death in CKD and HD. There was no evidence of a difference between patiromer or sodium zirconium cyclosilicate and placebo for health-related quality of life (HRQoL) at the end of treatment (one study) in CKD or HD. Potassium binders had uncertain effects on nausea (3 studies, 229 participants: RR 2.10, 95% CI 0.65, 6.78; I2 = 0%; low certainty evidence), diarrhoea (5 studies, 720 participants: RR 0.84, 95% CI 0.47, 1.48; I2 = 0%; low certainty evidence), and vomiting (2 studies, 122 participants: RR 1.72, 95% CI 0.35 to 8.51; I2 = 0%; low certainty evidence) in CKD. Potassium binders may lower serum potassium levels (at the end of treatment) (3 studies, 277 participants: MD -0.62 mEq/L, 95% CI -0.97, -0.27; I2 = 92%; low certainty evidence) in CKD and HD. Potassium binders had uncertain effects on constipation (4 studies, 425 participants: RR 1.58, 95% CI 0.71, 3.52; I2 = 0%; low certainty evidence) in CKD. Potassium binders may decrease systolic blood pressure (BP) (2 studies, 369 participants: MD -3.73 mmHg, 95%CI -6.64 to -0.83; I2 = 79%; low certainty evidence) and diastolic BP (one study) at the end of the treatment. No study reported outcome data for cardiac arrhythmias or major GI events.\nCalcium polystyrene sulfonate may make little or no difference to serum potassium levels at end of treatment, compared to sodium polystyrene sulfonate (2 studies, 117 participants: MD 0.38 mEq/L, 95% CI -0.03 to 0.79; I2 = 42%, low certainty evidence). There was no evidence of a difference in systolic BP (one study), diastolic BP (one study), or constipation (one study) between calcium polystyrene sulfonate and sodium polystyrene sulfonate.\nThere was no difference between high-dose and low-dose patiromer for death (sudden death) (one study), stroke (one study), myocardial infarction (one study), or constipation (one study).\nThe comparative effects whether potassium binders were administered with or without food, laxatives, or sorbitol, were very uncertain with insufficient data to perform meta-analysis.\nAuthors' conclusions\nEvidence supporting clinical decision-making for different potassium binders to treat chronic hyperkalaemia in adults with CKD is of low certainty; no studies were identified in children. Available studies have not been designed to measure treatment effects on clinical outcomes such as cardiac arrhythmias or major GI symptoms. This review suggests the need for a large, adequately powered study of potassium binders versus placebo that assesses clinical outcomes of relevance to patients, clinicians and policy-makers. This data could be used to assess cost-effectiveness, given the lack of definitive studies and the clinical importance of potassium binders for chronic hyperkalaemia in people with CKD.\n\nGiven the provided abstract, please respond to the following query: \"What did we do?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "We searched for all the research trials that have assessed the potassium-lowering treatments for children and adults with chronic kidney diseases. We evaluated how certain we could be about the overall findings using a system called \"GRADE\"." } ]

[ { "role": "user", "content": "Abstract: Background\nNeonatal hypoglycaemia, a common condition, can be associated with brain injury. It is frequently managed by providing infants with an alternative source of glucose, often given enterally with milk-feeding or intravenously with dextrose solution, which may decrease breastfeeding success. Intravenous dextrose also often requires that mother and baby are cared for in separate environments. Oral dextrose gel is simple and inexpensive, and can be administered directly to the buccal mucosa for rapid correction of hypoglycaemia, in association with continued breastfeeding and maternal care.\nThis is an update of a previous review published in 2016.\nObjectives\nTo assess the effectiveness of oral dextrose gel in correcting hypoglycaemia in newborn infants from birth to discharge home and reducing long-term neurodevelopmental impairment.\nSearch methods\nWe searched the Cochrane Central Register of Controlled Trials, MEDLINE, and Embase from database inception to October 2021.  We also searched international clinical trials networks, the reference lists of included trials, and relevant systematic reviews identified in the search.\nSelection criteria\nWe included randomised controlled trials (RCTs) and quasi-RCTs comparing oral dextrose gel versus placebo, no treatment, or other therapies for the treatment of neonatal hypoglycaemia in newborn infants from birth to discharge home.\nData collection and analysis\nTwo review authors independently assessed study quality and extracted data; they did not assess publications for which they were study authors. We contacted investigators to obtain additional information. We used fixed-effect models and the GRADE approach to assess the certainty of evidence.\nMain results\nWe included two studies conducted in high-income countries, involving 312 late preterm and at-risk term infants and comparing oral dextrose gel (40% concentration) to placebo gel. One study was at low risk of bias, and the other (an abstract) was at unclear to high risk of bias. Oral dextrose gel compared with placebo gel probably increases correction of hypoglycaemic events (rate ratio 1.08, 95% confidence interval (CI) 0.98 to 1.20; rate difference 66 more per 1000, 95% CI 17 fewer to 166 more; 1 study; 237 infants; moderate-certainty evidence), and may result in a slight reduction in the risk of major neurological disability at age two years or older, but the evidence is uncertain (risk ratio (RR) 0.46, 95% CI 0.09 to 2.47; risk difference (RD) 24 fewer per 1000, 95% CI 41 fewer to 66 more; 1 study, 185 children; low-certainty evidence). The evidence is very uncertain about the effect of oral dextrose gel compared with placebo gel or no gel on the need for intravenous treatment for hypoglycaemia (RR 0.78, 95% CI 0.46 to 1.32; RD 37 fewer per 1000, 95% CI 91 fewer to 54 more; 2 studies, 312 infants; very low-certainty evidence). Investigators in one study of 237 infants reported no adverse events (e.g. choking or vomiting at the time of administration) in the oral dextrose gel or placebo gel group (low-certainty evidence).\nOral dextrose gel compared with placebo gel probably reduces the incidence of separation from the mother for treatment of hypoglycaemia (RR 0.54, 95% CI 0.31 to 0.93; RD 116 fewer per 1000, 95% CI 174 fewer to 18 fewer; 1 study, 237 infants; moderate-certainty evidence), and increases the likelihood of exclusive breastfeeding after discharge (RR 1.10, 95% CI 1.01 to 1.18; RD 87 more per 1000, 95% CI 9 more to 157 more; 1 study, 237 infants; moderate-certainty evidence).\nAuthors' conclusions\nOral dextrose gel (specifically 40% dextrose concentration) used to treat hypoglycaemia in newborn infants (specifically at-risk late preterm and term infants) probably increases correction of hypoglycaemic events, and may result in a slight reduction in the risk of major neurological disability at age two years or older. Oral dextrose gel treatment probably reduces the incidence of separation from the mother for treatment and increases the likelihood of exclusive breastfeeding after discharge. No adverse events have been reported.\nOral dextrose gel is probably an effective and safe first-line treatment for infants with neonatal hypoglycaemia in high-income settings.\nMore evidence is needed about the effects of oral dextrose gel treatment on later neurological disability and the need for other treatments for hypoglycaemia. Future studies should be conducted in low-and middle-income settings, in extremely and moderately preterm infants, and compare oral dextrose gel with other therapies such as intravenous dextrose. There are two ongoing studies that may alter the conclusions of this review when published.\n\nGiven the provided abstract, please respond to the following query: \"Study characteristics\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "" } ]

[ { "role": "user", "content": "Abstract: Background\nPreterm birth interferes with brain maturation, and subsequent clinical events and interventions may have additional deleterious effects. Music as therapy is offered increasingly in neonatal intensive care units aiming to improve health outcomes and quality of life for both preterm infants and the well-being of their parents. Systematic reviews of mixed methodological quality have demonstrated ambiguous results for the efficacy of various types of auditory stimulation of preterm infants. A more comprehensive and rigorous systematic review is needed to address controversies arising from apparently conflicting studies and reviews.\nObjectives\nWe assessed the overall efficacy of music and vocal interventions for physiological and neurodevelopmental outcomes in preterm infants (< 37 weeks' gestation) compared to standard care. In addition, we aimed to determine specific effects of various interventions for physiological, anthropometric, social-emotional, neurodevelopmental short- and long-term outcomes in the infants, parental well-being, and bonding.\nSearch methods\nWe searched Cochrane Central Register of Controlled Trials (CENTRAL), MEDLINE, Embase, CINAHL, PsycINFO, Web of Science, RILM Abstracts, and ERIC in November 2021; and Proquest Dissertations in February 2019. We searched the reference lists of related systematic reviews, and of studies selected for inclusion and clinical trial registries.\nSelection criteria\nWe included parallel, and cluster-randomised controlled trials with preterm infants < 37 weeks` gestation during hospitalisation, and parents when they were involved in the intervention. Interventions were any music or vocal stimulation provided live or via a recording by a music therapist, a parent, or a healthcare professional compared to standard care. The intervention duration was greater than five minutes and needed to occur more than three times.\nData collection and analysis\nThree review authors independently extracted data. We analysed the treatment effects of the individual trials using RevMan Web using a fixed-effects model to combine the data. Where possible, we presented results in meta-analyses using mean differences with 95% CI. We performed heterogeneity tests. When the I2 statistic was higher than 50%, we assessed the source of the heterogeneity by sensitivity and subgroup analyses. We used GRADE to assess the certainty of the evidence.\nMain results\nWe included 25 trials recruiting 1532 infants and 691 parents (21 parallel-group RCTs, four cross-over RCTs). The infants gestational age at birth varied from 23 to 36 weeks, taking place in NICUs (level 1 to 3) around the world. Within the trials, the intervention varied widely in type, delivery, frequency, and duration. Music and voice were mainly characterised by calm, soft, musical parameters in lullaby style, often integrating the sung mother's voice live or recorded, defined as music therapy or music medicine. The general risk of bias in the included studies varied from low to high risk of bias.\nMusic and vocal interventions compared to standard care\nMusic/vocal interventions do not increase oxygen saturation in the infants during the intervention (mean difference (MD) 0.13, 95% CI -0.33 to 0.59; P = 0.59; 958 infants, 10 studies; high-certainty evidence). Music and voice probably do not increase oxygen saturation post-intervention either (MD 0.63, 95% CI -0.01 to 1.26; P = 0.05; 800 infants, 7 studies; moderate-certainty evidence). The intervention may not increase infant development (Bayley Scales of Infant and Toddler Development (BSID)) with the cognitive composition score (MD 0.35, 95% CI -4.85 to 5.55; P = 0.90; 69 infants, 2 studies; low-certainty evidence); the motor composition score (MD -0.17, 95% CI -5.45 to 5.11; P = 0.95; 69 infants, 2 studies; low-certainty evidence); and the language composition score (MD 0.38, 95% CI -5.45 to 6.21; P = 0.90; 69 infants, 2 studies; low-certainty evidence). Music therapy may not reduce parental state-trait anxiety (MD -1.12, 95% CI -3.20 to 0.96; P = 0.29; 97 parents, 4 studies; low-certainty evidence).\nThe intervention probably does not reduce respiratory rate during the intervention (MD 0.42, 95% CI -1.05 to 1.90; P = 0.57; 750 infants; 7 studies; moderate-certainty evidence) and post-intervention (MD 0.51, 95% CI -1.57 to 2.58; P = 0.63; 636 infants, 5 studies; moderate-certainty evidence). However, music/vocal interventions probably reduce heart rates in preterm infants during the intervention (MD -1.38, 95% CI -2.63 to -0.12; P = 0.03; 1014 infants; 11 studies; moderate-certainty evidence). This beneficial effect was even stronger after the intervention. Music/vocal interventions reduce heart rate post-intervention (MD -3.80, 95% CI -5.05 to -2.55; P < 0.00001; 903 infants, 9 studies; high-certainty evidence) with wide CIs ranging from medium to large beneficial effects. Music therapy may not reduce postnatal depression (MD 0.50, 95% CI -1.80 to 2.81; P = 0.67; 67 participants; 2 studies; low-certainty evidence). The evidence is very uncertain about the effect of music therapy on parental state anxiety (MD -0.15, 95% CI -2.72 to 2.41; P = 0.91; 87 parents, 3 studies; very low-certainty evidence). We are uncertain about any further effects regarding all other secondary short- and long-term outcomes on the infants, parental well-being, and bonding/attachment. Two studies evaluated adverse effects as an explicit outcome of interest and reported no adverse effects from music and voice.\nAuthors' conclusions\nMusic/vocal interventions do not increase oxygen saturation during and probably not after the intervention compared to standard care. The evidence suggests that music and voice do not increase infant development (BSID) or reduce parental state-trait anxiety. The intervention probably does not reduce respiratory rate in preterm infants. However, music/vocal interventions probably reduce heart rates in preterm infants during the intervention, and this beneficial effect is even stronger after the intervention, demonstrating that music/vocal interventions reduce heart rates in preterm infants post-intervention. We found no reports of adverse effects from music and voice. Due to low-certainty evidence for all other outcomes, we could not draw any further conclusions regarding overall efficacy nor the possible impact of different intervention types, frequencies, or durations. Further research with more power, fewer risks of bias, and more sensitive and clinically relevant outcomes are needed.\n\nGiven the provided abstract, please respond to the following query: \"How up-to-date is this evidence?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "The evidence is up-to-date to 12 November 2021." } ]

[ { "role": "user", "content": "Abstract: Background\nSouvenaid is a dietary supplement with a patented composition (Fortasyn Connect™)which is intended to be used by people with Alzheimer's disease (AD). It has been designed to support the formation and function of synapses in the brain, which are thought to be strongly correlated with cognitive function. If effective, it might improve symptoms of Alzheimer's disease and also prevent the progression from prodromal Alzheimer's disease to dementia. We sought in this review to examine the evidence for this proposition.\nObjectives\nTo assess the effects of Souvenaid on incidence of dementia, cognition, functional performance, and safety in people with Alzheimer's disease.\nSearch methods\nWe searched ALOIS, i.e. the specialised register of the Cochrane Dementia and Cognitive Improvement Group, MEDLINE (Ovid SP), Embase (Ovid SP), PsycINFO (Ovid SP), Web of Science (ISI Web of Science), Cinahl (EBSCOhost), Lilacs (BIREME), and clinical trials registries up to 24 June 2020. We also reviewed citations of reference lists of landmark papers, reviews, and included studies for additional studies and assessed their suitability for inclusion in the review.\nSelection criteria\nWe included randomised, placebo-controlled trials which evaluated Souvenaid in people diagnosed with mild cognitive impairment (MCI) due to AD (also termed prodromal AD) or with dementia due to AD, and with a treatment duration of at least 16 weeks.\nData collection and analysis\nOur primary outcome measures were incidence of dementia, global and specific cognitive function, functional performance, combined cognitive-functional outcomes and adverse events. We selected studies, extracted data, assessed the quality of trials and intended to conduct meta-analyses according to the Cochrane Handbook for Systematic Reviews of Interventions. We rated the quality of the evidence using the GRADE approach. We present all outcomes grouped by stage of AD.\nMain results\nWe included three randomised, placebo-controlled trials investigating Souvenaid in 1097 community-dwelling participants with Alzheimer's disease. One study each included participants with prodromal AD, mild AD dementia and mild-to-moderate AD dementia. We rated the risks of bias of all trials as low. One study (in prodromal AD) was funded by European grants. The other two studies were funded by the manufacturer of Souvenaid.\nOne trial investigated the incidence of dementia in people with prodromal AD at baseline, and found little to no difference between the Souvenaid group and the placebo group after 24 months (RR 1.09, 95% CI 0.82 to 1.43; 1 trial, 311 participants; moderate quality of evidence).\nIn prodromal AD, and in mild and mild-to-moderate Alzheimer's disease dementia, Souvenaid probably results in little or no difference in global or specific cognitive functions (moderate quality of evidence). Everyday function, or the ability to perform activities of daily living, were measured in mild and mild-to-moderate AD dementia. Neither study found evidence of a difference between the groups after 24 weeks of treatment (moderate quality of evidence). Two studies investigated combined cognitive-functional outcomes with the Clinical Dementia Rating Sum of Boxes and observed conflicting results. Souvenaid probably results in slight improvement, which is below estimates of meaningful change, in participants with prodromal Alzheimer's disease after 24 months (moderate quality of evidence), but probably has little to no effect in mild-to-moderate Alzheimer's disease dementia after 24 weeks (moderate quality of evidence).\nAdverse effects observed were low in all trials, and the available data were insufficient to determine any connection with Souvenaid.\nAuthors' conclusions\nTwo years of treatment with Souvenaid probably does not reduce the risk of progression to dementia in people with prodromal AD. There is no convincing evidence that Souvenaid affects other outcomes important to people with AD in the prodromal stage or mild-to-moderate stages of dementia. Conflicting evidence on combined cognitive-functional outcomes in prodromal AD and mild AD dementia warrants further investigation. Adverse effects of Souvenaid seem to be uncommon, but the evidence synthesised in this review does not permit us to make a definitive statement on the long-term tolerability of Souvenaid. The effects of Souvenaid in more severe AD dementia or in people with AD at risk of nutritional deficiencies remain unclear.\n\nGiven the provided abstract, please respond to the following query: \"Background\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "Alzheimer's disease is a brain disease. It is the commonest cause of dementia among older people. A person is said to have dementia when there has been a decline in their memory and thinking skills which is severe enough to stop them being fully independent in all their daily activities. Because AD develops slowly, it is also possible to pick up symptoms before dementia is fully developed. This pre-dementia stage, when people with AD have a detectable decline in memory and thinking skills but are still able to manage their usual activities independently, is known as mild cognitive impairment due to AD, or 'prodromal' AD.\nSouvenaid is a patented mix of vitamins and minerals (Fortasyn Connect™) which was designed to improve brain function in AD. It is a drink which is to be taken once a day. It is intended to be consumed under medical supervision, in addition to the usual diet." } ]

[ { "role": "user", "content": "Abstract: Background\nChronic pain is common in adults, and often has a detrimental impact upon physical ability, well-being, and quality of life. Previous reviews have shown that certain antidepressants may be effective in reducing pain with some benefit in improving patients’ global impression of change for certain chronic pain conditions. However, there has not been a network meta-analysis (NMA) examining all antidepressants across all chronic pain conditions.\nObjectives\nTo assess the comparative efficacy and safety of antidepressants for adults with chronic pain (except headache).\nSearch methods\nWe searched CENTRAL, MEDLINE, Embase, CINAHL, LILACS, AMED and PsycINFO databases, and clinical trials registries, for randomised controlled trials (RCTs) of antidepressants for chronic pain conditions in January 2022.\nSelection criteria\nWe included RCTs that examined antidepressants for chronic pain against any comparator. If the comparator was placebo, another medication, another antidepressant, or the same antidepressant at different doses, then we required the study to be double-blind. We included RCTs with active comparators that were unable to be double-blinded (e.g. psychotherapy) but rated them as high risk of bias. We excluded RCTs where the follow-up was less than two weeks and those with fewer than 10 participants in each arm.\nData collection and analysis\nTwo review authors separately screened, data extracted, and judged risk of bias. We synthesised the data using Bayesian NMA and pairwise meta-analyses for each outcome and ranked the antidepressants in terms of their effectiveness using the surface under the cumulative ranking curve (SUCRA). We primarily used Confidence in Meta-Analysis (CINeMA) and Risk of Bias due to Missing Evidence in Network meta-analysis (ROB-MEN) to assess the certainty of the evidence. Where it was not possible to use CINeMA and ROB-MEN due to the complexity of the networks, we used GRADE to assess the certainty of the evidence.\nOur primary outcomes were substantial (50%) pain relief, pain intensity, mood, and adverse events. Our secondary outcomes were moderate pain relief (30%), physical function, sleep, quality of life, Patient Global Impression of Change (PGIC), serious adverse events, and withdrawal.\nMain results\nThis review and NMA included 176 studies with a total of 28,664 participants. The majority of studies were placebo-controlled (83), and parallel−armed (141). The most common pain conditions examined were fibromyalgia (59 studies); neuropathic pain (49 studies) and musculoskeletal pain (40 studies). The average length of RCTs was 10 weeks. Seven studies provided no useable data and were omitted from the NMA. The majority of studies measured short-term outcomes only and excluded people with low mood and other mental health conditions.\nAcross efficacy outcomes, duloxetine was consistently the highest-ranked antidepressant with moderate- to high-certainty evidence. In duloxetine studies, standard dose was equally efficacious as high dose for the majority of outcomes. Milnacipran was often ranked as the next most efficacious antidepressant, although the certainty of evidence was lower than that of duloxetine. There was insufficient evidence to draw robust conclusions for the efficacy and safety of any other antidepressant for chronic pain.\nPrimary efficacy outcomes\nDuloxetine standard dose (60 mg) showed a small to moderate effect for substantial pain relief (odds ratio (OR) 1.91, 95% confidence interval (CI) 1.69 to 2.17; 16 studies, 4490 participants; moderate-certainty evidence) and continuous pain intensity (standardised mean difference (SMD) −0.31, 95% CI −0.39 to −0.24; 18 studies, 4959 participants; moderate-certainty evidence). For pain intensity, milnacipran standard dose (100 mg) also showed a small effect (SMD −0.22, 95% CI −0.39 to 0.06; 4 studies, 1866 participants; moderate-certainty evidence). Mirtazapine (30 mg) had a moderate effect on mood (SMD −0.5, 95% CI −0.78 to −0.22; 1 study, 406 participants; low-certainty evidence), while duloxetine showed a small effect (SMD −0.16, 95% CI −0.22 to −0.1; 26 studies, 7952 participants; moderate-certainty evidence); however it is important to note that most studies excluded participants with mental health conditions, and so average anxiety and depression scores tended to be in the 'normal' or 'subclinical' ranges at baseline already.\nSecondary efficacy outcomes\nAcross all secondary efficacy outcomes (moderate pain relief, physical function, sleep, quality of life, and PGIC), duloxetine and milnacipran were the highest-ranked antidepressants with moderate-certainty evidence, although effects were small. For both duloxetine and milnacipran, standard doses were as efficacious as high doses.\nSafety\nThere was very low-certainty evidence for all safety outcomes (adverse events, serious adverse events, and withdrawal) across all antidepressants. We cannot draw any reliable conclusions from the NMAs for these outcomes.\nAuthors' conclusions\nOur review and NMAs show that despite studies investigating 25 different antidepressants, the only antidepressant we are certain about for the treatment of chronic pain is duloxetine. Duloxetine was moderately efficacious across all outcomes at standard dose. There is also promising evidence for milnacipran, although further high-quality research is needed to be confident in these conclusions. Evidence for all other antidepressants was low certainty. As RCTs excluded people with low mood, we were unable to establish the effects of antidepressants for people with chronic pain and depression. There is currently no reliable evidence for the long-term efficacy of any antidepressant, and no reliable evidence for the safety of antidepressants for chronic pain at any time point.\n\nGiven the provided abstract, please respond to the following query: \"What did we do?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "We searched for studies that compared any antidepressant with any other treatment for any type of chronic pain (except headache). We compared all the treatments against each other using a statistical method called network meta-analysis. This method allows us to rank the effectiveness of the different antidepressants from best to worst." } ]

[ { "role": "user", "content": "Abstract: Background\nPressure ulcers (also known as pressure injuries) are localised injuries to the skin or underlying soft tissue, or both, caused by unrelieved pressure, shear or friction. Foam surfaces (beds, mattresses or overlays) are widely used with the aim of preventing pressure ulcers.\nObjectives\nTo assess the effects of foam beds, mattresses or overlays compared with any support surface on the incidence of pressure ulcers in any population in any setting.\nSearch methods\nIn November 2019, we searched the Cochrane Wounds Specialised Register; the Cochrane Central Register of Controlled Trials (CENTRAL); Ovid MEDLINE (including In-Process & Other Non-Indexed Citations); Ovid Embase and EBSCO CINAHL Plus. We also searched clinical trials registries for ongoing and unpublished studies, and scanned reference lists of relevant included studies as well as reviews, meta-analyses and health technology reports to identify additional studies. There were no restrictions with respect to language, date of publication or study setting.\nSelection criteria\nWe included randomised controlled trials that allocated participants of any age to foam beds, mattresses or overlays. Comparators were any beds, mattresses or overlays.\nData collection and analysis\nAt least two review authors independently assessed studies using predetermined inclusion criteria. We carried out data extraction, 'Risk of bias' assessment using the Cochrane 'Risk of bias' tool, and the certainty of the evidence assessment according to Grading of Recommendations, Assessment, Development and Evaluations methodology. If a foam surface was compared with surfaces that were not clearly specified, then the included study was recorded and described but not considered further in any data analyses.\nMain results\nWe included 29 studies (9566 participants) in the review. Most studies were small (median study sample size: 101 participants). The average age of participants ranged from 47.0 to 85.3 years (median: 76.0 years). Participants were mainly from acute care settings. We analysed data for seven comparisons in the review: foam surfaces compared with: (1) alternating pressure air surfaces, (2) reactive air surfaces, (3) reactive fibre surfaces, (4) reactive gel surfaces, (5) reactive foam and gel surfaces, (6) reactive water surfaces, and (7) another type of foam surface. Of the 29 included studies, 17 (58.6%) presented findings which were considered at high overall risk of bias.\nPrimary outcome: pressure ulcer incidence\nLow-certainty evidence suggests that foam surfaces may increase the risk of developing new pressure ulcers compared with (1) alternating pressure (active) air surfaces (risk ratio (RR) 1.59, 95% confidence interval (CI) 0.86 to 2.95; I2 = 63%; 4 studies, 2247 participants), and (2) reactive air surfaces (RR 2.40, 95% CI 1.04 to 5.54; I2 = 25%; 4 studies, 229 participants).\nWe are uncertain regarding the difference in pressure ulcer incidence in people treated with foam surfaces and the following surfaces: (1) reactive fibre surfaces (1 study, 68 participants); (2) reactive gel surfaces (1 study, 135 participants); (3) reactive gel and foam surfaces (1 study, 91 participants); and (4) another type of foam surface (6 studies, 733 participants). These had very low-certainty evidence.\nIncluded studies have data on time to pressure ulcer development for two comparisons. When time to ulcer development is considered using hazard ratios, the difference in the risk of having new pressure ulcers, over 90 days' follow-up, between foam surfaces and alternating pressure air surfaces is uncertain (2 studies, 2105 participants; very low-certainty evidence). Two further studies comparing different types of foam surfaces also reported time-to-event data, suggesting that viscoelastic foam surfaces with a density of 40 to 60 kg/m3 may decrease the risk of having new pressure ulcers over 11.5 days' follow-up compared with foam surfaces with a density of 33 kg/m3 (1 study, 62 participants); and solid foam surfaces may decrease the risk of having new pressure ulcers over one month's follow-up compared with convoluted foam surfaces (1 study, 84 participants). Both had low-certainty evidence.\nThere was no analysable data for the comparison of foam surfaces with reactive water surfaces (one study with 117 participants).\nSecondary outcomes\nSupport-surface-associated patient comfort: the review contains data for three comparisons for this outcome. It is uncertain if there is a difference in patient comfort measure between foam surfaces and alternating pressure air surfaces (1 study, 76 participants; very low-certainty evidence); foam surfaces and reactive air surfaces (1 study, 72 participants; very low-certainty evidence); and different types of foam surfaces (4 studies, 669 participants; very low-certainty evidence).\nAll reported adverse events: the review contains data for two comparisons for this outcome. We are uncertain about differences in adverse effects between foam surfaces and alternating pressure (active) air surfaces (3 studies, 2181 participants; very low-certainty evidence), and between foam surfaces and reactive air surfaces (1 study, 72 participants; very low-certainty evidence).\nHealth-related quality of life: only one study reported data on this outcome. It is uncertain if there is a difference (low-certainty evidence) between foam surfaces and alternating pressure (active) air surfaces in health-related quality of life measured with two different questionnaires, the EQ-5D-5L (267 participants) and the PU-QoL-UI (233 participants).\nCost-effectiveness: one study reported trial-based cost-effectiveness evaluations. Alternating pressure (active) air surfaces are probably more cost-effective than foam surfaces in preventing pressure ulcer incidence (2029 participants; moderate-certainty evidence).\nAuthors' conclusions\nCurrent evidence suggests uncertainty about the differences in pressure ulcer incidence, patient comfort, adverse events and health-related quality of life between using foam surfaces and other surfaces (reactive fibre surfaces, reactive gel surfaces, reactive foam and gel surfaces, or reactive water surfaces). Foam surfaces may increase pressure ulcer incidence compared with alternating pressure (active) air surfaces and reactive air surfaces. Alternating pressure (active) air surfaces are probably more cost-effective than foam surfaces in preventing new pressure ulcers.\nFuture research in this area should consider evaluation of the most important support surfaces from the perspective of decision-makers. Time-to-event outcomes, careful assessment of adverse events and trial-level cost-effectiveness evaluation should be considered in future studies. Trials should be designed to minimise the risk of detection bias; for example, by using digital photography and by blinding adjudicators of the photographs to group allocation. Further review using network meta-analysis adds to the findings reported here.\n\nGiven the provided abstract, please respond to the following query: \"What did we find?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "We found 29 studies (9566 people, average age: 76 years) that lasted between five days and one year (average: 15 days). The studies compared foam with active and reactive surfaces made of gel, air cells, water bags and other foam types.\nPressure ulcer prevention\nThe evidence suggests that:\n- foam surfaces may increase the risk of developing pressure ulcers when compared with active or reactive air-filled surfaces (8 studies);\n- denser memory foam (foam that adapts to a person’s body shape) may be better than lighter memory foam for preventing pressure ulcers if the data on the time it takes to develop a new ulcer is looked at (1 study, duration: 11.5 days);\n- flat foam surfaces may be better than ridged foam surfaces for preventing pressure ulcers if the data on the time it takes to develop a new ulcer is looked at (1 study, duration: 1 month).\nIt is unclear if foam has an effect on pressure ulcers compared to water or gel surfaces.\nOther effects\nEvidence from one study suggests that foam is probably less cost-effective than active, air-filled surfaces.\nWe did not find sufficiently robust and clear evidence to determine how foam affects comfort, quality of life and unwanted effects." } ]

[ { "role": "user", "content": "Abstract: Background\nPouchitis occurs in approximately 50% of patients following ileal pouch-anal anastomosis (IPAA) for chronic ulcerative colitis (UC).\nObjectives\nThe primary objective was to determine the efficacy and safety of medical therapies for prevention or treatment of acute or chronic pouchitis.\nSearch methods\nWe searched MEDLINE, Embase and CENTRAL from inception to 25 July 2018. We also searched references, trials registers, and conference proceedings.\nSelection criteria\nRandomized controlled trials of prevention or treatment of acute or chronic pouchitis in adults who underwent IPAA for UC were considered for inclusion.\nData collection and analysis\nTwo authors independently screened studies for eligibility, extracted data and assessed the risk of bias. The certainty of the evidence was evaluated using GRADE. The primary outcome was clinical improvement or remission in participants with acute or chronic pouchitis, or the proportion of participants with no episodes of pouchitis after IPAA. Adverse events (AEs) was a secondary outcome. We calculated the risk ratio (RR) and corresponding 95% confidence interval (CI) for each dichotomous outcome.\nMain results\nFifteen studies (547 participants) were included. Four studies assessed treatment of acute pouchitis. Five studies assessed treatment of chronic pouchitis. Six studies assessed prevention of pouchitis. Three studies were low risk of bias. Three studies were high risk of bias and the other studies were unclear.\nAcute pouchitis: All ciprofloxacin participants (7/7) achieved remission at two weeks compared to 33% (3/9) of metronidazole participants (RR 2.68, 95% CI 1.13 to 6.35, very low certainty evidence). No ciprofloxacin participants (0/7) had an AE compared to 33% (3/9) of metronidazole participants (RR 0.18, 95% CI 0.01 to 2.98; very low certainty evidence). AEs included vomiting, dysgeusia or transient peripheral neuropathy. Forty-three per cent (6/14) of metronidazole participants achieved remission at 6 weeks compared to 50% (6/12) of budesonide enema participants (RR 0.86, 95% CI 0.37 to 1.96, very low certainty evidence). Fifty per cent (7/14) of metronidazole participants improved clinically at 6 weeks compared to 58% (7/12) of budesonide enema participants (RR 0.86, 95% CI 0.42 to 1.74, very low certainty evidence). Fifty-seven per cent (8/14) of metronidazole participants had an AE compared to 25% (3/12) of budesonide enema participants (RR 2.29, 95% CI 0.78 to 6.73, very low certainty evidence). AEs included anorexia, nausea, headache, asthenia, metallic taste, vomiting, paraesthesia, and depression. Twenty-five per cent (2/8) of rifaximin participants achieved remission at 4 weeks compared to 0% (0/10) of placebo participants (RR 6.11, 95% CI 0.33 to 111.71, very low certainty evidence). Thirty-eight per cent (3/8) of rifaximin participants improved clinically at 4 weeks compared to 30% (3/10) of placebo participants (RR 1.25, 95% CI 0.34 to 4.60, very low certainty evidence). Seventy-five per cent (6/8) of rifaximin participants had an AE compared to 50% (5/10) of placebo participants (RR 1.50, 95% CI 0.72 to 3.14, very low certainty evidence). AEs included diarrhea, flatulence, nausea, proctalgia, vomiting, thirst, candida, upper respiratory tract infection, increased hepatic enzyme, and cluster headache. Ten per cent (1/10) of Lactobacillus GG participants improved clinically at 12 weeks compared to 0% (0/10) of placebo participants (RR 3.00, 95% CI 0.14 to 65.90, very low certainty evidence).\nChronic pouchitis: Eighty-five per cent (34/40) of De Simone Formulation (a probiotic formulation) participants maintained remission at 9 to 12 months compared to 3% (1/36) of placebo participants (RR 20.24, 95% CI 4.28 to 95.81, 2 studies; low certainty evidence). Two per cent (1/40) of De Simone Formulation participants had an AE compared to 0% (0/36) of placebo participants (RR 2.43, 95% CI 0.11 to 55.89; low certainty evidence). AEs included abdominal cramps, vomiting and diarrhea. Fifty per cent (3/6) of adalimumab patients achieved clinical improvement at 4 weeks compared to 43% (3/7) of placebo participants (RR, 1.17, 95% CI 0.36 to 3.76, low certainty evidence). Sixty per cent (6/10) of glutamine participants maintained remission at 3 weeks compared to 33% (3/9) of butyrate participants (RR 1.80, 95% CI 0.63 to 5.16, very low certainty evidence). Forty-five per cent (9/20) of patients treated with bismuth carbomer foam enema improved clinically at 3 weeks compared to 45% (9/20) of placebo participants (RR 1.00, 95% CI 0.50 to 1.98, very low certainty evidence). Twenty-five per cent (5/20) of participants in the bismuth carbomer foam enema group had an AE compared to 35% (7/20) of placebo participants (RR 0.71, 95% CI 0.27 to 1.88, very low certainty evidence). Adverse events included diarrhea, worsening symptoms, cramping, sinusitis, and abdominal pain.\nPrevention: At 12 months, 90% (18/20) of De Simone Formulation participants had no episodes of acute pouchitis compared to 60% (12/20) of placebo participants (RR 1.50, 95% CI 1.02 to 2.21, low certainty evidence). Another study found 100% (16/16) of De Simone Formulation participants had no episodes of acute pouchitis at 12 months compared to 92% (11/12) of the no treatment control group (RR 1.10, 95% 0.89 to 1.36, very low certainty evidence). Eighty-six per cent (6/7) of Bifidobacterium longum participants had no episodes of acute pouchitis at 6 months compared to 60% (3/5) of placebo participants (RR 1.43, 95% CI 0.66 to 3.11, very low certainty evidence). Eleven per cent (1/9) of Clostridium butyricum MIYAIRI participants had no episodes of acute pouchitis at 24 months compared to 50% (4/8) of placebo participants (RR 0.22, 95% CI 0.03 to 1.60, very low certainty evidence). Forty-six per cent (43/94) of allopurinol participants had no episodes of pouchitis at 24 months compared to 43% (39/90) of placebo participants (RR 1.06, 95% CI 0.76 to 1.46; low certainty evidence). Eighty-one per cent (21/26) of tinidazole participants had no episodes of pouchitis over 12 months compared to 58% (7/12) of placebo participants (RR 1.38, 95% CI 0.83 to 2.31, very low certainty evidence).\nAuthors' conclusions\nThe effects of antibiotics, probiotics and other interventions for treating and preventing pouchitis are uncertain. Well designed, adequately powered studies are needed to determine the optimal therapy for the treatment and prevention of pouchitis.\n\nGiven the provided abstract, please respond to the following query: \"What did the researchers investigate?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "The researchers investigated whether these medications produce remission in people with active pouchitis, maintain remission in people with inactive pouchitis or prevent pouchitis in people who've had IPAA surgery. Side effects were also assessed. The medical literature was searched up to 25 July 2018." } ]

[ { "role": "user", "content": "Abstract: Background\nSeveral options exist for managing overactive bladder (OAB), including electrical stimulation (ES) with non-implanted devices, conservative treatment and drugs. Electrical stimulation with non-implanted devices aims to inhibit contractions of the detrusor muscle, potentially reducing urinary frequency and urgency.\nObjectives\nTo assess the effects of ES with non-implanted electrodes for OAB, with or without urgency urinary incontinence, compared with: placebo or any other active treatment; ES added to another intervention compared with the other intervention alone; different methods of ES compared with each other.\nSearch methods\nWe searched the Cochrane Incontinence Specialised Register, which contains trials identified from the Cochrane Central Register of Controlled Trials (CENTRAL), MEDLINE, MEDLINE In-Process, ClinicalTrials.gov, WHO ICTRP and handsearching of journals and conference proceedings (searched 10 December 2015). We searched the reference lists of relevant articles and contacted specialists in the field. We imposed no language restrictions.\nSelection criteria\nWe included randomised or quasi-randomised controlled trials of ES with non-implanted devices compared with any other treatment for OAB in adults. Eligible trials included adults with OAB with or without urgency urinary incontinence (UUI). Trials whose participants had stress urinary incontinence (SUI) were excluded.\nData collection and analysis\nTwo review authors independently screened search results, extracted data from eligible trials and assessed risk of bias, using the Cochrane 'Risk of bias' tool.\nMain results\nWe identified 63 eligible trials (4424 randomised participants). Forty-four trials did not report the primary outcomes of perception of cure or improvement in OAB. The majority of trials were deemed to be at low or unclear risk of selection and attrition bias and unclear risk of performance and detection bias. Lack of clarity with regard to risk of bias was largely due to poor reporting.\nFor perception of improvement in OAB symptoms, moderate-quality evidence indicated that ES was better than pelvic floor muscle training (PFMT) (risk ratio (RR) 1.60, 95% confidence interval (CI) 1.19 to 2.14; n = 195), drug treatment (RR 1.20, 95% 1.04 to 1.38; n = 439). and placebo or sham treatment (RR 2.26, 95% CI 1.85 to 2.77, n = 677) but it was unclear if ES was more effective than placebo/sham for urgency urinary incontinence (UUI) (RR 5.03, 95% CI 0.28 to 89.88; n = 242). Drug treatments included in the trials were oestrogen cream, oxybutynin, propantheline bromide, probanthine, solifenacin succinate, terodiline, tolterodine and trospium chloride.\nLow- or very low-quality evidence suggested no evidence of a difference in perception of improvement of UUI when ES was compared to PFMT with or without biofeedback.\nLow-quality evidence indicated that OAB symptoms were more likely to improve with ES than with no active treatment (RR 1.85, 95% CI 1.34 to 2.55; n = 121).\nLow-quality evidence suggested participants receiving ES plus PFMT, compared to those receiving PFMT only, were more than twice as likely to report improvement in UUI (RR 2.82, 95% CI 1.44 to 5.52; n = 51).\nThere was inconclusive evidence, which was either low- or very low-quality, for OAB-related quality of life when ES was compared to no active treatment, placebo/sham or biofeedback-assisted PFMT, or when ES was added to PFMT compared to PFMT-only. There was very low-quality evidence from a single trial to suggest that ES may be better than PFMT in terms of OAB-related quality of life.\nThere was a lower risk of adverse effects with ES than tolterodine (RR 0.12, 95% CI 0.05 to 0.27; n = 200) (moderate-quality evidence) and oxybutynin (RR 0.11, 95% CI 0.01 to 0.84; n = 79) (low-quality evidence).\nDue to the very low-quality evidence available, we could not be certain whether there were fewer adverse effects with ES compared to placebo/sham treatment, magnetic stimulation or solifenacin succinate. We were also very uncertain whether adding ES to PFMT or to drug therapy resulted in fewer adverse effects than PFMT or drug therapy alone Nor could we tell if there was any difference in risk of adverse effects between different types of ES.\nThere was insufficient evidence to determine if one type of ES was more effective than another or if the benefits of ES persisted after the active treatment period stopped.\nAuthors' conclusions\nElectrical stimulation shows promise in treating OAB, compared to no active treatment, placebo/sham treatment, PFMT and drug treatment. It is possible that adding ES to other treatments such as PFMT may be beneficial. However, the low quality of the evidence base overall means that we cannot have full confidence in these conclusions until adequately powered trials have been carried out, measuring subjective outcomes and adverse effects.\n\nGiven the provided abstract, please respond to the following query: \"Aim\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "We investigated whether electrical stimulation was better than no treatment at all or better than any other treatment available for OAB. We also investigated which type of electrical stimulation was better for OAB and whether or not electrical stimulation was safe." } ]

[ { "role": "user", "content": "Abstract: Background\nDementia, a global health priority, has no current cure. Around 50 million people worldwide currently live with dementia, and this number is expected to treble by 2050. Some health conditions and lifestyle behaviours can increase or decrease the risk of dementia and are known as 'predictors'. Prognostic models combine such predictors to measure the risk of future dementia. Models that can accurately predict future dementia would help clinicians select high-risk adults in middle age and implement targeted risk reduction.\nObjectives\nOur primary objective was to identify multi-domain prognostic models used in middle-aged adults (aged 45 to 65 years) for predicting dementia or cognitive impairment. Eligible multi-domain prognostic models involved two or more of the modifiable dementia predictors identified in a 2020 Lancet Commission report and a 2019 World Health Organization (WHO) report (less education, hearing loss, traumatic brain injury, hypertension, excessive alcohol intake, obesity, smoking, depression, social isolation, physical inactivity, diabetes mellitus, air pollution, poor diet, and cognitive inactivity). Our secondary objectives were to summarise the prognostic models, to appraise their predictive accuracy (discrimination and calibration) as reported in the development and validation studies, and to identify the implications of using dementia prognostic models for the management of people at a higher risk for future dementia.\nSearch methods\nWe searched MEDLINE, Embase, PsycINFO, CINAHL, and ISI Web of Science Core Collection from inception until 6 June 2022. We performed forwards and backwards citation tracking of included studies using the Web of Science platform.\nSelection criteria\nWe included development and validation studies of multi-domain prognostic models. The minimum eligible follow-up was five years. Our primary outcome was an incident clinical diagnosis of dementia based on validated diagnostic criteria, and our secondary outcome was dementia or cognitive impairment determined by any other method.\nData collection and analysis\nTwo review authors independently screened the references, extracted data using a template based on the CHecklist for critical Appraisal and data extraction for systematic Reviews of prediction Modelling Studies (CHARMS), and assessed risk of bias and applicability of included studies using the Prediction model Risk Of Bias ASsessment Tool (PROBAST). We synthesised the C-statistics of models that had been externally validated in at least three comparable studies.\nMain results\nWe identified 20 eligible studies; eight were development studies and 12 were validation studies. There were 14 unique prognostic models: seven models with validation studies and seven models with development-only studies. The models included a median of nine predictors (range 6 to 34); the median number of modifiable predictors was five (range 2 to 11). The most common modifiable predictors in externally validated models were diabetes, hypertension, smoking, physical activity, and obesity. In development-only models, the most common modifiable predictors were obesity, diabetes, hypertension, and smoking. No models included hearing loss or air pollution as predictors. Nineteen studies had a high risk of bias according to the PROBAST assessment, mainly because of inappropriate analysis methods, particularly lack of reported calibration measures. Applicability concerns were low for 12 studies, as their population, predictors, and outcomes were consistent with those of interest for this review. Applicability concerns were high for nine studies, as they lacked baseline cognitive screening or excluded an age group within the range of 45 to 65 years.\nOnly one model, Cardiovascular Risk Factors, Ageing, and Dementia (CAIDE), had been externally validated in multiple studies, allowing for meta-analysis. The CAIDE model included eight predictors (four modifiable predictors): age, education, sex, systolic blood pressure, body mass index (BMI), total cholesterol, physical activity and APOEƐ4 status. Overall, our confidence in the prediction accuracy of CAIDE was very low; our main reasons for downgrading the certainty of the evidence were high risk of bias across all the studies, high concern of applicability, non-overlapping confidence intervals (CIs), and a high degree of heterogeneity.\nThe summary C-statistic was 0.71 (95% CI 0.66 to 0.76; 3 studies; very low-certainty evidence) for the incident clinical diagnosis of dementia, and 0.67 (95% CI 0.61 to 0.73; 3 studies; very low-certainty evidence) for dementia or cognitive impairment based on cognitive scores. Meta-analysis of calibration measures was not possible, as few studies provided these data.\nAuthors' conclusions\nWe identified 14 unique multi-domain prognostic models used in middle-aged adults for predicting subsequent dementia. Diabetes, hypertension, obesity, and smoking were the most common modifiable risk factors used as predictors in the models. We performed meta-analyses of C-statistics for one model (CAIDE), but the summary values were unreliable. Owing to lack of data, we were unable to meta-analyse the calibration measures of CAIDE. This review highlights the need for further robust external validations of multi-domain prognostic models for predicting future risk of dementia in middle-aged adults.\n\nGiven the provided abstract, please respond to the following query: \"Why do we use tools that assess risk factors to predict future dementia?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "Currently, about 50 million people across the world have dementia, and without adequate preventive measures, that number is expected to triple by 2050. If we control risk factors in middle age, we may avert or delay the future development of dementia or reduce dementia severity. Preventive tools help select people who are best suited to lifestyle modification programmes aimed at regulating risk factors." } ]

[ { "role": "user", "content": "Abstract: Background\nViruses cause about 80% of all cases of acute conjunctivitis. Human adenoviruses are believed to account for 65% to 90% of cases of viral conjunctivitis, or 20% to 75% of all causes of infectious keratoconjunctivitis worldwide. Epidemic keratoconjunctivitis (EKC) is a highly contagious subset of adenoviral conjunctivitis that has been associated with large outbreaks at military installations and at medical facilities. It is accompanied by severe conjunctival inflammation, watery discharge, and light sensitivity, and can lead to chronic complications such as corneal and conjunctival scarring with discomfort and poor quality of vision. Due to a lack of consensus on the efficacy of any pharmacotherapy to alter the clinical course of EKC, no standard of care exists, therefore many clinicians offer only supportive care.\nObjectives\nTo assess the efficacy and safety of topical pharmacological therapies versus placebo, an active control, or no treatment for adults with EKC.\nSearch methods\nWe searched the Cochrane Central Register of Controlled Trials (CENTRAL, which contains the Cochrane Eyes and Vision Trials Register; 2021, Issue 4); Ovid MEDLINE; Ovid Embase; Latin American and Caribbean Health Sciences database (LILACS); ClinicalTrials.gov; and the World Health Organization (WHO) International Clinical Trials Registry Platform (ICTRP), with no restrictions on language or year of publication. The date of the last search was 27 April 2021.\nSelection criteria\nWe included randomized controlled trials in which antiseptic agents, virustatic agents, or topical immune-modulating therapy was compared with placebo, an active control, or no treatment.\nData collection and analysis\nWe used standard Cochrane methodology.\nMain results\nWe identified 10 studies conducted in Asia, Europe, the Middle East, and North Africa with a total of 892 participants who were treated for 7 days to 6 months and followed for 7 days up to 1.5 years.\nStudy characteristics and risk of bias\nIn most studies participants were predominantly men (range: 44% to 90%), with an age range from 9 to 82 years. Three studies reported information on trial registration, but we found no published study protocol. The majority of trials had small sample sizes, ranging from 18 to 90 participants enrolled per study; the only exception was a trial that enrolled 350 participants. We judged most studies to be at high or unclear risk of bias across risk of bias domains.\nFindings\nWe included 10 studies of 892 EKC participants and estimated combined intervention effects in analyses stratified by steroid-containing control treatment or artificial tears. Six trials contributed to the comparisons of topical interventions (povidone-iodine [PVP-I], trifluridine, ganciclovir, dexamethasone plus neomycin) with artificial tears (or saline). Very low certainty evidence from two trials comparing trifluridine or ganciclovir with artificial tears showed inconsistent effects on shortening the mean duration of cardinal symptoms or signs of EKC. Low certainty evidence based on two studies (409 participants) indicated that participants treated with PVP-I alone more often experienced resolution of symptoms (risk ratio (RR) 1.15, 95% confidence interval (CI) 1.07 to 1.24) and signs (RR 3.19, 95% CI 2.29 to 4.45) during the first week of treatment compared with those treated with artificial tears. Very low certainty evidence from two studies (77 participants) suggested that PVP-I or ganciclovir prevented the development of subepithelial infiltrates (SEI) when compared with artificial tears within 30 days of treatment (RR 0.24, 95% CI 0.10 to 0.56).\nFour studies compared topical interventions (tacrolimus, cyclosporin A [CsA], trifluridine, PVP-I + dexamethasone) with topical steroids, and one trial compared fluorometholone (FML) plus polyvinyl alcohol iodine (PVA-I) with FML plus levofloxacin. Evidence from one trial showed that more eyes receiving PVP-I 1.0% plus dexamethasone 0.1% had symptoms resolved by day seven compared with those receiving dexamethasone alone (RR 9.00, 95% CI 1.23 to 66.05; 52 eyes). In two trials, fewer eyes treated with PVP-I or PVA-I plus steroid developed SEI within 15 days of treatment compared with steroid alone or steroid plus levofloxacin (RR 0.08, 95% CI 0.01 to 0.55; 69 eyes). One study found that CsA was no more effective than steroid for resolving SEI within four weeks of treatment (RR 0.84, 95% CI 0.67 to 1.06; N = 88). The evidence from trials comparing topical interventions with steroids was overall of very low level certainty.\nAdverse effects\nAntiviral or antimicrobial agents plus steroid did not differ from artificial tears in terms of ocular discomfort upon instillation (RR 9.23, 95% CI 0.61 to 140.67; N = 19). CsA and tacrolimus eye drops were associated with more cases of severe ocular discomfort, and sometimes intolerance, when compared with steroids (RR 4.64, 95% CI 1.15 to 18.71; 2 studies; N = 141). Compared with steroids, tacrolimus did not increase the risk of elevated intraocular pressure (RR 0.07, 95% CI 0 to 1.13; 1 study; N = 80), while trifluridine conferred no additional risk compared to tear substitute (RR 5.50, 95% CI 0.31 to 96.49; 1 study; N = 97). Overall, bacterial superinfection was rare (one in 23 CsA users) and not associated with use of the intervention steroid (RR 3.63, 95% CI 0.15 to 84.98; N = 51). The evidence for all estimates was of low or very low certainty.\nAuthors' conclusions\nThe evidence for the seven specified outcomes was of low or very low certainty due to imprecision and high risk of bias. The evidence that antiviral agents shorten the duration of symptoms or signs when compared with artificial tears was inconclusive. Low certainty evidence suggests that PVP-I alone resolves signs and symptoms by seven days relative to artificial tears. PVP-I or PVA-I, alone or with steroid, is associated with lower risks of SEI development than artificial tears or steroid (very low certainty evidence). The currently available evidence is insufficient to determine whether any of the evaluated interventions confers an advantage over steroids or artificial tears with respect to virus eradication or its spread to initially uninvolved fellow eyes. Future updates of this review should provide evidence of high-level certainty from trials with larger sample sizes, enrollment of participants with similar durations of signs and symptoms, and validated methods to assess short- and long-term outcomes.\n\nGiven the provided abstract, please respond to the following query: \"What are the limitations of the evidence?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "Nearly all of the included studies had flawed study methods and were reported poorly. These weaknesses raised our concerns about the study findings and reduced our confidence in the overall evidence summarized in the review." } ]

[ { "role": "user", "content": "Abstract: Background\nGingival recession is defined as the oral exposure of the root surface due to a displacement of the gingival margin apical to the cemento-enamel junction and it is regularly linked to the deterioration of dental aesthetics. Successful treatment of recession-type defects is based on the use of predictable root coverage periodontal plastic surgery (RCPPS) procedures. This review is an update of the original version that was published in 2009.\nObjectives\nTo evaluate the efficacy of different root coverage procedures in the treatment of single and multiple recession-type defects.\nSearch methods\nCochrane Oral Health's Information Specialist searched the following databases: Cochrane Oral Health's Trials Register (to 15 January 2018), the Cochrane Central Register of Controlled Trials (CENTRAL; 2017, Issue 12) in the Cochrane Library (searched 15 January 2018), MEDLINE Ovid (1946 to 15 January 2018), and Embase Ovid (1980 to 15 January 2018). The US National Institutes of Health Ongoing Trials Register (ClinicalTrials.gov) and the World Health Organization International Clinical Trials Registry Platform were searched for ongoing trials (15 January 2018). No restrictions were placed on the language or date of publication when searching the electronic databases.\nSelection criteria\nWe included randomised controlled trials (RCTs) only of at least 6 months' duration evaluating recession areas (Miller's Class I or II ≥ 3 mm) and treated by means of RCPPS procedures.\nData collection and analysis\nScreening of eligible studies, data extraction and risk of bias assessment were conducted independently and in duplicate. Authors were contacted for any missing information. We expressed results as random-effects models using mean differences (MD) for continuous outcomes and odds ratios (OR) for dichotomous outcomes with 95% confidence intervals (CI). We used GRADE methods to assess the quality of the body of evidence of our main comparisons.\nMain results\nWe included 48 RCTs in the review. Of these, we assessed one as at low risk of bias, 12 as at high risk of bias and 35 as at unclear risk of bias. The results indicated a greater reduction in gingival recession for subepithelial connective tissue grafts (SCTG) + coronally advanced flap (CAF) compared to guided tissue regeneration with resorbable membranes (GTR rm) + CAF (MD -0.37 mm; 95% CI -0.60 to -0.13, P = 0.002; 3 studies; 98 participants; low-quality evidence). There was insufficient evidence of a difference in gingival recession reduction between acellular dermal matrix grafts (ADMG) + CAF and SCTG + CAF or between enamel matrix protein (EMP) + CAF and SCTG + CAF. Regarding clinical attachment level changes, GTR rm + CAF promoted additional gains compared to SCTG + CAF (MD 0.35; 95% CI 0.06 to 0.63, P = 0.02; 3 studies; 98 participants; low-quality evidence) but there was insufficient evidence of a difference between ADMG + CAF and SCTG + CAF or between EMP + CAF and SCTG + CAF. Greater gains in the keratinized tissue were found for SCTG + CAF when compared to EMP + CAF (MD -1.06 mm; 95% CI -1.36 to -0.76, P < 0.00001; 2 studies; 62 participants; low-quality evidence), and SCTG + CAF when compared to GTR rm + CAF (MD -1.77 mm; 95% CI -2.66 to -0.89, P < 0.0001; 3 studies; 98 participants; very low-quality evidence). There was insufficient evidence of a difference in keratinized tissue gain between ADMG + CAF and SCTG + CAF. Few data exist on aesthetic condition change related to patients' opinion and patients' preference for a specific procedure.\nAuthors' conclusions\nSubepithelial connective tissue grafts, coronally advanced flap alone or associated with other biomaterial and guided tissue regeneration may be used as root coverage procedures for treating localised or multiple recession-type defects. The available evidence base indicates that in cases where both root coverage and gain in the width of keratinized tissue are expected, the use of subepithelial connective tissue grafts shows a slight improvement in outcome. There is also some weak evidence suggesting that acellular dermal matrix grafts appear as the soft tissue substitute that may provide the most similar outcomes to those achieved by subepithelial connective tissue grafts. RCTs are necessary to identify possible factors associated with the prognosis of each RCPPS procedure. The potential impact of bias on these outcomes is unclear.\n\nGiven the provided abstract, please respond to the following query: \"Background\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "Receding gums (also known as gingival recession) is the gradual loss of gum tissue, and if left untreated it can result in exposure of the tooth root, between the gum and the tooth. It can involve one tooth (single recession-type defect) or many teeth (multiple recession-type defects). It can affect the look of the teeth, and is also linked to tooth sensitivity. Exposure of the tooth root can be treated by cosmetic surgery; techniques include grafting and gum regeneration. Grafting involves taking tissue from another place in the mouth and stitching it over the area of the exposed root. With gum regeneration, biomaterials are used to regenerate gum tissue without the need for taking it from the roof of the mouth. Procedures used in gum grafting and gum regeneration include: free gingival grafts, coronally advanced flaps, acellular dermal matrix grafts, laterally positioned flaps and guided tissue regeneration. This review is an update of the original version that was published in 2009." } ]

[ { "role": "user", "content": "Abstract: Background\nUse of pressure ulcer risk assessment tools or scales is a component of the assessment process used to identify individuals at risk of developing a pressure ulcer. Use of a risk assessment tool is recommended by many international pressure ulcer prevention guidelines, however it is not known whether using a risk assessment tool makes a difference to patient outcomes. We conducted a review to provide a summary of the evidence pertaining to pressure ulcer risk assessment in clinical practice, and this is the third update of this review.\nObjectives\nTo assess whether using structured and systematic pressure ulcer risk assessment tools, in any healthcare setting, reduces the incidence of pressure ulcers.\nSearch methods\nIn February 2018 we searched the Cochrane Wounds Specialised Register; the Cochrane Central Register of Controlled Trials (CENTRAL); Ovid MEDLINE (including In-Process & Other Non-Indexed Citations); Ovid Embase; and EBSCO CINAHL Plus. We also searched clinical trials registries for ongoing and unpublished studies, and scanned reference lists of relevant included studies as well as reviews, meta-analyses and health technology reports to identify additional studies. There were no restrictions with respect to language, date of publication or study setting.\nSelection criteria\nRandomised controlled trials (RCTs) comparing the use of structured and systematic pressure ulcer risk assessment tools with no structured pressure ulcer risk assessment, or with unaided clinical judgement, or RCTs comparing the use of different structured pressure ulcer risk assessment tools.\nData collection and analysis\nTwo review authors independently performed study selection, data extraction, 'Risk of bias' assessment and GRADE assessment of the certainty of evidence.\nMain results\nWe included two studies in this review (1,487 participants). We identified no new trials for this latest update.\nBoth studies were undertaken in acute-care hospitals. In one study, patients were eligible if they had a Braden score of 18 or less. In the second study all admitted patients were eligible for inclusion, once they were expected to have a hospital stay of more than three days and they had been in hospital for no more than 24 hours before baseline assessment took place. In the first study, most of the participants were medical patients; no information on age or gender distribution was provided. In the second study, 50.3% (619) of the participants were male, with a mean age of 62.6 years (standard deviation (SD): 19.3), and 15.4% (190) were admitted to oncology wards.\nThe two included studies were three-armed studies. In the first study the three groups were: Braden risk assessment tool and training (n = 74), clinical judgement and training (n = 76) and clinical judgement alone (n = 106); follow-up was eight weeks. In the second study the three groups were: Waterlow risk assessment tool (n = 411), clinical judgement (n = 410) and Ramstadius risk assessment tool (n = 410); follow-up was four days. Both studies reported the primary outcome of pressure ulcer incidence and one study also reported the secondary outcome, severity of new pressure ulcers.\nWe are uncertain whether use of the Braden risk assessment tool and training makes any difference to pressure ulcer incidence, compared to risk assessment using clinical judgement and training (risk ratio (RR) 0.97, 95% confidence interval (CI) 0.53 to 1.77; 150 participants), or compared to risk assessment using clinical judgement alone (RR 1.43, 95% CI 0.77 to 2.68; 180 participants). We assessed the certainty of the evidence as very low (downgraded twice for study limitations and twice for imprecision).\nRisk assessment using the Waterlow tool may make little or no difference to pressure ulcer incidence, or to pressure ulcer severity, when compared to risk assessment using clinical judgement (pressure ulcers of all stages: RR 1.10, 95% CI 0.68 to 1.81; 821 participants; stage 1 pressure ulcers: RR 1.05, 95% CI 0.58 to 1.90; 821 participants; stage 2 pressure ulcers: RR 1.25, 95% CI 0.50 to 3.13; 821 participants), or risk assessment using the Ramstadius tool (pressure ulcers of all stages: RR 1.41, 95% CI 0.83 to 2.39; 821 participants; stage 1 pressure ulcers: RR 1.16, 95% CI 0.63 to 2.15; 821 participants; stage 2 pressure ulcers: RR 2.49, 95% CI 0.79 to 7.89; 821 participants). Similarily, risk assessment using the Ramstadius tool may make little or no difference to pressure ulcer incidence, or to pressure ulcer severity, when compared to risk assessment using clinical judgement (pressure ulcers of all stages: RR 0.79, 95% CI 0.46 to 1.35; 820 participants; stage 1 pressure ulcers: RR 0.90, 95% CI 0.48 to 1.68; 820 participants; stage 2 pressure ulcers: RR 0.50, 95% CI 0.15 to 1.65; 820 participants). We assessed the certainty of the evidence as low (downgraded once for study limitations and once for imprecision).\nThe studies did not report the secondary outcomes of time to ulcer development, or pressure ulcer prevalence.\nAuthors' conclusions\nWe identified two studies which evaluated the effect of risk assessment on pressure ulcer incidence. Based on evidence from one study, we are uncertain whether risk assessment using the Braden tool makes any difference to pressure ulcer incidence, compared with training and risk assessment using clinical judgement, or risk assessment using clinical judgement alone. Risk assessment using the Waterlow tool, or the Ramstadius tool may make little or no difference to pressure ulcer incidence, or severity, compared with clinical judgement. The low, or very low certainty of evidence available from the included studies is not reliable enough to suggest that the use of structured and systematic pressure ulcer risk assessment tools reduces the incidence, or severity of pressure ulcers.\n\nGiven the provided abstract, please respond to the following query: \"Key messages\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "We cannot be certain whether the use of a risk assessment tool makes any difference to the number of new pressure ulcers that develop among people who are at risk. The certainty of evidence ranged from low to very low." } ]

[ { "role": "user", "content": "Abstract: Background\nEstablishment of a secure airway is a critical part of neonatal resuscitation in the delivery room and the neonatal intensive care unit. Videolaryngoscopy has the potential to facilitate successful endotracheal intubation, and decrease adverse consequences of a delay in airway stabilization. Videolaryngoscopy may enhance visualization of the glottis and intubation success in neonates. This is an update of a review first published in 2015, and updated in 2018.\nObjectives\nTo determine the effectiveness and safety of videolaryngoscopy compared to direct laryngoscopy in decreasing the time and attempts required for endotracheal intubation and increasing the success rate on first intubation attempt in neonates (0 to 28 days of age).\nSearch methods\nIn November 2022, we updated the search for trials evaluating videolaryngoscopy for neonatal endotracheal intubation in CENTRAL, MEDLINE, Embase, CINAHL, and BIOSIS. We also searched abstracts of the Pediatric Academic Societies, clinical trials registries (www.clinicaltrials.gov; www.controlled-trials.com), and reference lists of relevant studies.\nSelection criteria\nRandomized controlled trials (RCTs), quasi-RCTs, cluster-RCTs, or cross-over trials, in neonates (0 to 28 days of age), evaluating videolaryngoscopy with any device used for endotracheal intubation compared with direct laryngoscopy.\nData collection and analysis\nThree review authors performed data collection and analysis, as recommended by Cochrane Neonatal. Two review authors independently assessed studies identified by the search strategy for inclusion.\nWe used the GRADE approach to assess the certainty of the evidence.\nMain results\nThe updated search yielded 7786 references, from which we identified five additional RCTs for inclusion, seven ongoing trials, and five studies awaiting classification. Three studies were included in the previous version of the review. For this update, we included eight studies, which provided data on 759 intubation attempts in neonates. We included neonates of either sex, who were undergoing endotracheal intubation in international hospitals. Different videolaryngoscopy devices (including C-MAC, Airtraq, and Glidescope) were used in the studies.\nFor the primary outcomes; videolaryngoscopy may not reduce the time required for successful intubation when compared with direct laryngoscopy (mean difference [MD] 0.74, 95% confidence interval [CI] -0.19 to 1.67; 5 studies; 505 intubations; low-certainty evidence). Videolaryngoscopy may result in fewer intubation attempts (MD -0.08, 95% CI -0.15 to 0.00; 6 studies; 659 intubations; low-certainty evidence). Videolaryngoscopy may increase the success of intubation at the first attempt (risk ratio [RR] 1.24, 95% CI 1.13 to 1.37; risk difference [RD] 0.14, 95% CI 0.08 to 0.20; number needed to treat for an additional beneficial outcome [NNTB] 7, 95% CI 5 to 13; 8 studies; 759 intubation attempts; low-certainty evidence).\nFor the secondary outcomes; the evidence is very uncertain about the effect of videolaryngoscopy on desaturation or bradycardia episodes, or both, during intubation (RR 0.94, 95% CI 0.38 to 2.30; 3 studies; 343 intubations; very-low certainty evidence). Videolaryngoscopy may result in little to no difference in the lowest oxygen saturations during intubation compared with direct laryngoscopy (MD -0.76, 95% CI -5.74 to 4.23; 2 studies; 359 intubations; low-certainty evidence). Videolaryngoscopy likely results in a slight reduction in the incidence of airway trauma during intubation attempts compared with direct laryngoscopy (RR 0.21, 95% CI 0.05 to 0.79; RD -0.04, 95% CI -0.07 to -0.01; NNTB 25, 95% CI 14 to 100; 5 studies; 467 intubations; moderate-certainty evidence).\nThere were no data available on other adverse effects of videolaryngoscopy. We found a high risk of bias in areas of allocation concealment and performance bias in the included studies.\nAuthors' conclusions\nVideolaryngoscopy may increase the success of intubation on the first attempt and may result in fewer intubation attempts, but may not reduce the time required for successful intubation (low-certainty evidence). Videolaryngoscopy likely results in a reduced incidence of airway-related adverse effects (moderate-certainty evidence).\nThese results suggest that videolaryngoscopy may be more effective and potentially reduce harm when compared to direct laryngoscopy for endotracheal intubation in neonates.\nWell-designed, adequately powered RCTS are necessary to confirm the efficacy and safety of videolaryngoscopy in neonatal intubation.\n\nGiven the provided abstract, please respond to the following query: \"Key Messages\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "Videolaryngoscopy may increase the success of placing a breathing tube on the first attempt, and may result in slightly fewer tries by a care provider to place the breathing tube in sick newborn babies, but it does not reduce the amount of time it takes to place the breathing tube.\nVideolaryngoscopy likely results in slightly less injury to the newborn baby's airway while the breathing tube is being placed.\nWe need better studies to understand the role of videolaryngoscopy in different practice areas and with different care providers doing the placement." } ]

[ { "role": "user", "content": "Abstract: Background\nInfectious mononucleosis, also known as glandular fever or the kissing disease, is a benign lymphoproliferative disorder. It is a viral infection caused by the Epstein-Barr virus (EBV), a ubiquitous herpes virus that is found in all human societies and cultures. Epidemiological studies show that over 95% of adults worldwide have been infected with EBV. Most cases of symptomatic infectious mononucleosis occur between the ages of 15 and 24 years. It is transmitted through close contact with an EBV shedder, contact with infected saliva or, less commonly, through sexual contact, blood transfusions or by sharing utensils; however, transmission actually occurs less than 10% of the time. Precautions are not needed to prevent transmission because of the high percentage of seropositivity for EBV. Infectious mononucleosis is self-limiting and typically lasts for two to three weeks. Nevertheless, symptoms can last for weeks and occasionally months.\nSymptoms include fever, lymphadenopathy, pharyngitis, hepatosplenomegaly and fatigue. Symptom relief and rest are commonly recommended treatments. Steroids have been used for their anti-inflammatory effects, but there are no universal criteria for their use.\nObjectives\nThe objectives of the review were to determine the efficacy and safety of steroid therapy versus placebo, usual care or different drug therapies for symptom control in infectious mononucleosis.\nSearch methods\nFor this 2015 update we searched the Cochrane Central Register of Controlled Trials (CENTRAL 2015, Issue 7), which includes the Cochrane Acute Respiratory Infections Group's Specialised Register; MEDLINE (January 1966 to August 2015) and EMBASE (January 1974 to August 2015). We also searched trials registries, however we did not identify any new relevant completed or ongoing trials for inclusion. We combined the MEDLINE search with the Cochrane search strategy for identifying randomised controlled trials (RCTs). We adapted the search terms when searching EMBASE.\nSelection criteria\nRCTs comparing the effectiveness of steroids with placebo, usual care, or other interventions for symptom control for people with documented infectious mononucleosis.\nData collection and analysis\nWe used the standard methodological procedures expected by Cochrane.\nMain results\nFor this 2015 update, we did not identify any new RCTs for inclusion. The previous version of the review included seven trials with a total of 362 participants. Four trials compared the effectiveness of a steroid to placebo for short-term symptom control in glandular fever, one to aspirin, and two trials explored the effects of steroids in conjunction with an antiviral. Heterogeneity between trials prevented a combined analysis.\nTrials under-reported methodological design features. Three trials did not adequately describe sequence generation for randomisation. Four trials provided adequate details of allocation concealment. All trials were double-blind but four were not specific as to who was blinded. Loss to follow-up was under-reported in four trials, making it difficult to exclude attrition bias. The risk of selective reporting in the included trials was unclear.\nAcross the trials, no benefit was found in 8/10 assessments of health improvement. Two trials found benefit of steroid therapy over placebo in reducing sore throat at 12 hours (eight-day course odds ratio (OR) 21.00, 95% confidence interval (CI) 1.94 to 227.20; one-dose OR 4.20, 95% CI 1.08 to 16.32), but the benefit was not maintained.\nIn combination with an antiviral drug, participants in the steroid group had less pharyngeal discomfort between days two to four (OR 0.31, 95% CI 0.09 to 1.08) compared to placebo. Across the trials the effects on other common symptoms were less clear. Two trials set out to measure safety; they documented no major adverse effects. In two other trials adverse events were reported, including respiratory distress and acute onset of diabetes. However, the association of the events with the steroid is not definite.\nAuthors' conclusions\nThere is insufficient evidence to the efficacy of steroids for symptom control in infectious mononucleosis. There is a lack of research on the side effects and long-term complications.\n\nGiven the provided abstract, please respond to the following query: \"Background\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "Glandular fever is caused by a virus. It spreads in saliva through kissing, coughing and sneezing. Symptoms vary in terms of how severe they are and for how long they persist. While young adults commonly suffer from severe symptoms, some people may have mild symptoms or none. Common symptoms include fever, sore throat, swollen lymph nodes and feeling tired.These symptoms usually last for two to three weeks, but can last for months. Symptom relief and rest are common treatments. Doctors commonly use prednisone, a steroid, to reduce the symptoms of sore throat or enlarged tonsils. However, there is no agreement on its use due to the possibility of little benefit and the chance of side effects." } ]

[ { "role": "user", "content": "Abstract: Background\nSpecific diagnostic tests to detect severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and resulting COVID-19 disease are not always available and take time to obtain results. Routine laboratory markers such as white blood cell count, measures of anticoagulation, C-reactive protein (CRP) and procalcitonin, are used to assess the clinical status of a patient. These laboratory tests may be useful for the triage of people with potential COVID-19 to prioritize them for different levels of treatment, especially in situations where time and resources are limited.\nObjectives\nTo assess the diagnostic accuracy of routine laboratory testing as a triage test to determine if a person has COVID-19.\nSearch methods\nOn 4 May 2020 we undertook electronic searches in the Cochrane COVID-19 Study Register and the COVID-19 Living Evidence Database from the University of Bern, which is updated daily with published articles from PubMed and Embase and with preprints from medRxiv and bioRxiv. In addition, we checked repositories of COVID-19 publications. We did not apply any language restrictions.\nSelection criteria\nWe included both case-control designs and consecutive series of patients that assessed the diagnostic accuracy of routine laboratory testing as a triage test to determine if a person has COVID-19. The reference standard could be reverse transcriptase polymerase chain reaction (RT-PCR) alone; RT-PCR plus clinical expertise or and imaging; repeated RT-PCR several days apart or from different samples; WHO and other case definitions; and any other reference standard used by the study authors.\nData collection and analysis\nTwo review authors independently extracted data from each included study. They also assessed the methodological quality of the studies, using QUADAS-2. We used the 'NLMIXED' procedure in SAS 9.4 for the hierarchical summary receiver operating characteristic (HSROC) meta-analyses of tests for which we included four or more studies. To facilitate interpretation of results, for each meta-analysis we estimated summary sensitivity at the points on the SROC curve that corresponded to the median and interquartile range boundaries of specificities in the included studies.\nMain results\nWe included 21 studies in this review, including 14,126 COVID-19 patients and 56,585 non-COVID-19 patients in total. Studies evaluated a total of 67 different laboratory tests. Although we were interested in the diagnotic accuracy of routine tests for COVID-19, the included studies used detection of SARS-CoV-2 infection through RT-PCR as reference standard. There was considerable heterogeneity between tests, threshold values and the settings in which they were applied. For some tests a positive result was defined as a decrease compared to normal vaues, for other tests a positive result was defined as an increase, and for some tests both increase and decrease may have indicated test positivity. None of the studies had either low risk of bias on all domains or low concerns for applicability for all domains. Only three of the tests evaluated had a summary sensitivity and specificity over 50%. These were: increase in interleukin-6, increase in C-reactive protein and lymphocyte count decrease.\nBlood count\nEleven studies evaluated a decrease in white blood cell count, with a median specificity of 93% and a summary sensitivity of 25% (95% CI 8.0% to 27%; very low-certainty evidence). The 15 studies that evaluated an increase in white blood cell count had a lower median specificity and a lower corresponding sensitivity. Four studies evaluated a decrease in neutrophil count. Their median specificity was 93%, corresponding to a summary sensitivity of 10% (95% CI 1.0% to 56%; low-certainty evidence). The 11 studies that evaluated an increase in neutrophil count had a lower median specificity and a lower corresponding sensitivity. The summary sensitivity of an increase in neutrophil percentage (4 studies) was 59% (95% CI 1.0% to 100%) at median specificity (38%; very low-certainty evidence). The summary sensitivity of an increase in monocyte count (4 studies) was 13% (95% CI 6.0% to 26%) at median specificity (73%; very low-certainty evidence). The summary sensitivity of a decrease in lymphocyte count (13 studies) was 64% (95% CI 28% to 89%) at median specificity (53%; low-certainty evidence). Four studies that evaluated a decrease in lymphocyte percentage showed a lower median specificity and lower corresponding sensitivity. The summary sensitivity of a decrease in platelets (4 studies) was 19% (95% CI 10% to 32%) at median specificity (88%; low-certainty evidence).\nLiver function tests\nThe summary sensitivity of an increase in alanine aminotransferase (9 studies) was 12% (95% CI 3% to 34%) at median specificity (92%; low-certainty evidence). The summary sensitivity of an increase in aspartate aminotransferase (7 studies) was 29% (95% CI 17% to 45%) at median specificity (81%) (low-certainty evidence). The summary sensitivity of a decrease in albumin (4 studies) was 21% (95% CI 3% to 67%) at median specificity (66%; low-certainty evidence). The summary sensitivity of an increase in total bilirubin (4 studies) was 12% (95% CI 3.0% to 34%) at median specificity (92%; very low-certainty evidence).\nMarkers of inflammation\nThe summary sensitivity of an increase in CRP (14 studies) was 66% (95% CI 55% to 75%) at median specificity (44%; very low-certainty evidence). The summary sensitivity of an increase in procalcitonin (6 studies) was 3% (95% CI 1% to 19%) at median specificity (86%; very low-certainty evidence). The summary sensitivity of an increase in IL-6 (four studies) was 73% (95% CI 36% to 93%) at median specificity (58%) (very low-certainty evidence).\nOther biomarkers\nThe summary sensitivity of an increase in creatine kinase (5 studies) was 11% (95% CI 6% to 19%) at median specificity (94%) (low-certainty evidence). The summary sensitivity of an increase in serum creatinine (four studies) was 7% (95% CI 1% to 37%) at median specificity (91%; low-certainty evidence). The summary sensitivity of an increase in lactate dehydrogenase (4 studies) was 25% (95% CI 15% to 38%) at median specificity (72%; very low-certainty evidence).\nAuthors' conclusions\nAlthough these tests give an indication about the general health status of patients and some tests may be specific indicators for inflammatory processes, none of the tests we investigated are useful for accurately ruling in or ruling out COVID-19 on their own. Studies were done in specific hospitalized populations, and future studies should consider non-hospital settings to evaluate how these tests would perform in people with milder symptoms.\n\nGiven the provided abstract, please respond to the following query: \"What did we do?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "We searched for studies that assessed the accuracy of routine laboratory tests to diagnose COVID-19 compared with RT-PCR or other tests. Studies could be of any design and be set anywhere in the world. Studies could include participants of any age or sex, with suspected COVID-19, or use samples from people known to have – or not to have - COVID-19." } ]

[ { "role": "user", "content": "Abstract: Background\nLow back pain is costly and disabling. Prognostic factor evidence can help healthcare providers and patients understand likely prognosis, inform the development of prediction models to identify subgroups, and may inform new treatment strategies. Recent studies have suggested that people who have poor expectations for recovery experience more back pain disability, but study results have differed.\nObjectives\nTo synthesise evidence on the association between recovery expectations and disability outcomes in adults with low back pain, and explore sources of heterogeneity.\nSearch methods\nThe search strategy included broad and focused electronic searches of MEDLINE, Embase, CINAHL, and PsycINFO to 12 March 2019, reference list searches of relevant reviews and included studies, and citation searches of relevant expectation measurement tools.\nSelection criteria\nWe included low back pain prognosis studies from any setting assessing general, self-efficacy, and treatment expectations (measured dichotomously and continuously on a 0 - 10 scale), and their association with work participation, clinically important recovery, functional limitations, or pain intensity outcomes at short (3 months), medium (6 months), long (12 months), and very long (> 16 months) follow-up.\nData collection and analysis\nWe extracted study characteristics and all reported estimates of unadjusted and adjusted associations between expectations and related outcomes. Two review authors independently assessed risks of bias using the Quality in Prognosis Studies (QUIPS) tool. We conducted narrative syntheses and meta-analyses when appropriate unadjusted or adjusted estimates were available. Two review authors independently graded and reported the overall quality of evidence.\nMain results\nWe screened 4635 unique citations to include 60 studies (30,530 participants). Thirty-five studies were conducted in Europe, 21 in North America, and four in Australia. Study populations were mostly chronic (37%), from healthcare (62%) or occupational settings (26%). General expectation was the most common type of recovery expectation measured (70%); 16 studies measured more than one type of expectation.\nUsable data for syntheses were available for 52 studies (87% of studies; 28,885 participants). We found moderate-quality evidence that positive recovery expectations are strongly associated with better work participation (narrative synthesis: 21 studies; meta-analysis: 12 studies, 4777 participants: odds ratio (OR) 2.43, 95% confidence interval (CI) 1.64 to 3.62), and low-quality evidence for clinically important recovery outcomes (narrative synthesis: 12 studies; meta-analysis: 5 studies, 1820 participants: OR 1.89, 95% CI 1.49 to 2.41), both at follow-up times closest to 12 months, using adjusted data. The association of recovery expectations with other outcomes of interest, including functional limitations (narrative synthesis: 10 studies; meta-analysis: 3 studies, 1435 participants: OR 1.40, 95% CI 0.85 to 2.31) and pain intensity (narrative synthesis: 9 studies; meta-analysis: 3 studies, 1555 participants: OR 1.15, 95% CI 1.08 to 1.23) outcomes at follow-up times closest to 12 months using adjusted data, is less certain, achieving very low- and low-quality evidence, respectively. No studies reported statistically significant or clinically important negative associations between recovery expectations and any low back pain outcome.\nAuthors' conclusions\nWe found that individual recovery expectations are probably strongly associated with future work participation (moderate-quality evidence) and may be associated with clinically important recovery outcomes (low-quality evidence). The association of recovery expectations with other outcomes of interest is less certain. Our findings suggest that recovery expectations should be considered in future studies, to improve prognosis and management of low back pain.\n\nGiven the provided abstract, please respond to the following query: \"How up-to-date is this review?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "The review authors searched for studies that had been published up to 12 March 2019." } ]

[ { "role": "user", "content": "Abstract: Background\nIt is well known that physical exercise can trigger asthma symptoms and can induce bronchial obstruction in people without clinical asthma. International guidelines on asthma management recommend the use of beta2-agonists at any stage of the disease. At present, however, no consensus has been reached about the efficacy and safety of beta2-agonists in the pretreatment of exercise-induced asthma and exercise-induced bronchoconstriction. For the purpose of the present review, both of these conditions are referred to by the acronymous EIA, independently from the presence of an underlying chronic clinical disease.\nObjectives\nTo assess the effects of inhaled short- and long-acting beta2-agonists, compared with placebo, in the pretreatment of children and adults with exercise-induced asthma (or exercise-induced bronchoconstriction).\nSearch methods\nTrials were identified by electronic searching of the Cochrane Airways Group Specialised Register of Trials and by handsearching of respiratory journals and meetings. Searches are current as of August 2013.\nSelection criteria\nWe included randomised, double-blind, placebo-controlled trials of any study design, published in full text, that assessed the effects of inhaled beta2-agonists on EIA in adults and children. We excluded studies that did not clearly state diagnostic criteria for EIA.\nData collection and analysis\nWe used standard methodological procedures as expected by The Cochrane Collaboration.\nMain results\nWe included 53 trials consisting of 1139 participants. Forty-eight studies used a cross-over design, and five were performed in accordance with a parallel-group design. Forty-five studies addressed the effect of a single beta2-agonist administration, and eight focused on long-term treatment. We addressed these two different intervention regimens as different comparisons.\nAmong primary outcomes for short-term administration, data on maximum fall in forced expiratory volume in 1 second (FEV1) showed a significant protective effect for both short-acting beta-agonists (SABA) and long-acting beta-agonists (LABA) compared with placebo, with a mean difference of -17.67% (95% confidence interval (CI) -19.51% to -15.84%, P = 0.00001, 799 participants from 72 studies). The subgroup analysis of studies performed in adults compared with those performed in children showed high heterogeneity confined to children, despite the comparable mean bronchoprotective effect.\nSecondary outcomes on other pulmonary function parameters confirmed a more positive and protective effect of beta2-agonists on EIA compared with placebo. Occurrence of side effects was not significantly different between beta2-agonists and placebo.\nOverall evaluation of the included long-term studies suggests a beta2-agonist bronchoprotective effect for the first dose of treatment. However, long-term use of both SABA and LABA induced the onset of tolerance and decreased the duration of drug effect, even after a short treatment period.\nAuthors' conclusions\nEvidence of low to moderate quality shows that beta2-agonists, both SABA and LABA, when administered in a single dose, are effective and safe in preventing EIA.\nLong-term regular administration of inhaled beta2-agonists induces tolerance and lacks sufficient safety data. This finding appears to be of particular clinical relevance in view of the potential for prolonged regular use of beta2-agonists as monotherapy in the pretreatment of EIA, despite the warnings of drug agencies (FDA, EMA) regarding LABA.\n\nGiven the provided abstract, please respond to the following query: \"Results\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "Studies in which people received a single administration of a beta-agonist showed that FEV1 (a measure of lung function) fell significantly less for people taking SABA or LABA compared with placebo (mean difference (MD) -17.67%; 95% confidence interval (CI) -19.51% to -15.84%). Other lung function measures confirmed that beta2-agonists were more beneficial compared with placebo. No significant difference in the number of side effects was noted in people taking SABA or LABA compared with people taking placebo. However, it is unlikely that people would be prescribed an inhaler for a single treatment, so we must consider longer-term studies to get a true measure of the side effects that inhalers can cause.\nWe found that included longer-term studies showed that beta2-agonists were helpful in terms of lung function for the first dose of treatment. However, studies that provided longer-term treatment with SABA or LABA showed that over time, people built up a tolerance to the effects of treatments, and the beneficial effects lasted for shorter periods of time." } ]

[ { "role": "user", "content": "Abstract: Background\nThe benefits and risks of antibiotics for acute bronchitis remain unclear despite it being one of the most common illnesses seen in primary care.\nObjectives\nTo assess the effects of antibiotics in improving outcomes and to assess adverse effects of antibiotic therapy for people with a clinical diagnosis of acute bronchitis.\nSearch methods\nWe searched CENTRAL 2016, Issue 11 (accessed 13 January 2017), MEDLINE (1966 to January week 1, 2017), Embase (1974 to 13 January 2017), and LILACS (1982 to 13 January 2017). We searched the World Health Organization International Clinical Trials Registry Platform (WHO ICTRP) and ClinicalTrials.gov on 5 April 2017.\nSelection criteria\nRandomised controlled trials comparing any antibiotic therapy with placebo or no treatment in acute bronchitis or acute productive cough, in people without underlying pulmonary disease.\nData collection and analysis\nAt least two review authors extracted data and assessed trial quality.\nMain results\nWe did not identify any new trials for inclusion in this 2017 update. We included 17 trials with 5099 participants in the primary analysis. The quality of trials was generally good. At follow-up there was no difference in participants described as being clinically improved between the antibiotic and placebo groups (11 studies with 3841 participants, risk ratio (RR) 1.07, 95% confidence interval (CI) 0.99 to 1.15). Participants given antibiotics were less likely to have a cough (4 studies with 275 participants, RR 0.64, 95% CI 0.49 to 0.85; number needed to treat for an additional beneficial outcome (NNTB) 6) and a night cough (4 studies with 538 participants, RR 0.67, 95% CI 0.54 to 0.83; NNTB 7). Participants given antibiotics had a shorter mean cough duration (7 studies with 2776 participants, mean difference (MD) -0.46 days, 95% CI -0.87 to -0.04). The differences in presence of a productive cough at follow-up and MD of productive cough did not reach statistical significance.\nAntibiotic-treated participants were more likely to be improved according to clinician's global assessment (6 studies with 891 participants, RR 0.61, 95% CI 0.48 to 0.79; NNTB 11) and were less likely to have an abnormal lung exam (5 studies with 613 participants, RR 0.54, 95% CI 0.41 to 0.70; NNTB 6). Antibiotic-treated participants also had a reduction in days feeling ill (5 studies with 809 participants, MD -0.64 days, 95% CI -1.16 to -0.13) and days with impaired activity (6 studies with 767 participants, MD -0.49 days, 95% CI -0.94 to -0.04). The differences in proportions with activity limitations at follow-up did not reach statistical significance. There was a significant trend towards an increase in adverse effects in the antibiotic group (12 studies with 3496 participants, RR 1.20, 95% CI 1.05 to 1.36; NNT for an additional harmful outcome 24).\nAuthors' conclusions\nThere is limited evidence of clinical benefit to support the use of antibiotics in acute bronchitis. Antibiotics may have a modest beneficial effect in some patients such as frail, elderly people with multimorbidity who may not have been included in trials to date. However, the magnitude of this benefit needs to be considered in the broader context of potential side effects, medicalisation for a self limiting condition, increased resistance to respiratory pathogens, and cost of antibiotic treatment.\n\nGiven the provided abstract, please respond to the following query: \"Key results\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "Our evidence is current to 13 January, 2017.\nWe found limited evidence of clinical benefit to support the use of antibiotics for acute bronchitis. Some people treated with antibiotics recovered a bit more quickly with reduced cough-related outcomes. However, this difference may not be of practical importance as it amounted to a difference of half a day over an 8- to 10-day period. There was a small but significant increase in adverse side effects in people treated with antibiotics. The most commonly reported side effects included nausea, vomiting, diarrhoea, headache, and rash.\nThis review suggests that there is limited benefit to the patient in using antibiotics for acute bronchitis in otherwise healthy individuals. More research is needed on the effects of using antibiotics for acute bronchitis in frail, elderly people with multiple chronic conditions who may not have been included in the existing trials. Antibiotic use needs to be considered in the context of the potential side effects, medicalisation for a self limiting condition, cost of antibiotic treatment, and in particular associated population-level harms due to increasing antibiotic resistance." } ]

[ { "role": "user", "content": "Abstract: Background\nChorioamnionitis is a leading cause of perinatal morbidity and mortality. Amnioinfusion aims at reducing the adverse effects of chorioamnionitis by dilution of the infective organisms or by an anti-microbial effect of the fluid infused.\nObjectives\nThe objective of this review was to determine the effect of amnioinfusion on clinical and sub-clinical chorioamnionitis, fetal well-being, fetal heart rate characteristics and perinatal and maternal morbidity and mortality.\nSearch methods\nWe searched the Cochrane Pregnancy and Childbirth Group's Trials Register (6 July 2016), PubMed, ClinicalTrials.gov, the WHO International Clinical Trials Registry Platform (ICTRP) (6 July 2016) and reference lists of retrieved studies.\nSelection criteria\nRandomised clinical trials (RCTs) of amnioinfusion (treatment group) versus no amnioinfusion in women with chorioamnionitis.\nWe would have also considered trials comparing amnioinfusion with sham amnioinfusion; different types or volumes of amnioinfusion fluid but none were identified.\nCluster-RCTs and quasi-RCTs were eligible for inclusion but none were identified. We identified one study published in abstract form but it did not contain any numerical data and has therefore been excluded. Studies using a cross-over design are not an appropriate study design and thus were not eligible for inclusion in this review.\nData collection and analysis\nTwo review authors independently assessed potential studies for inclusion and assessed trial quality. Both review authors independently extracted data and data were checked for accuracy.\nMain results\nWe included one small trial (with data from 34 participants) comparing transcervical amnioinfusion with no amnioinfusion. The trial was considered to be at a high risk of bias overall, due to small numbers, inconsistency in the reporting and lack of information on blinding. Meta-analysis was not possible. Transcervical amnioinfusion was with room temperature saline at 10 mL per minute for 60 minutes, then 3 mL per minute until delivery versus no amnioinfusion. All women received intrauterine pressure catheter, acetaminophen and antibiotics (ampicillin or, if receiving Group B beta streptococcal prophylaxis, penicillin and gentamycin). We did not identify any trials that used transabdominal amnioinfusion.\nCompared to no amnioinfusion, transcervical amnioinfusion had no clear effect on the incidence of postpartum endometritis (risk ratio (RR) 1.50, 95% confidence interval (CI) 0.29 to 7.87; absolute risk 176/1000 (95% CI 34 to 96) versus 118/1000;low-quality evidence). Nor was there a clear effect in the incidence of neonatal infection (RR 3.00, 95% CI 0.13 to 68.84; absolute risk 0/1000 (95% CI 0 to 0) versus 0/1000; low-quality evidence). The outcome of perinatal death or severe morbidity (such as neonatal encephalopathy, intraventricular haemorrhage, admission to intensive/high care) was not reported in the included trial.\nIn terms of this review's secondary outcomes, the rate of caesarean section was the same in both groups (RR 1.00, 95% CI 0.35 to 2.83; absolute risk 294/1000 (95% CI 103 to 832) versus 294/1000; low-quality evidence). There was no clear difference in the duration of maternal antibiotic treatment between the amnioinfusion and no amnioinfusion control group (mean difference (MD) 16 hours, 95% CI -1.75 to 33.75); nor in the duration of hospitalisation (MD 3.00 hours, 95% CI -15.49 to 21.49). The study did not report any information about how many babies had a low Apgar score at five minutes after birth.\nWomen in the amnioinfusion group had a lower temperature at delivery compared to women in the control group (MD -0.38°C, 95% CI -0.74 to -0.02) but this outcome was not pre-specified in the protocol for this review.\nThe majority of this review's secondary outcomes were not reported in the included study.\nAuthors' conclusions\nThere is insufficient evidence to fully evaluate the effectiveness of using transcervical amnioinfusion for chorioamnionitis and to assess the safety of this intervention or women’s satisfaction. We did not identify any trials that used transabdominal amnioinfusion. The evidence in this review can neither support nor refute the use of transcervical amnioinfusion outside of clinical trials. We included one small study that reported on a limited number of outcomes of interest in this review. The numbers included in this review are too small for meaningful assessment of substantive outcomes, where reported. For those outcomes we assessed using GRADE (postpartum endometritis, neonatal infection, and caesarean section), we downgraded the quality of the evidence to low - with downgrading decisions based on small numbers and a lack of information on blinding. The included study did not report on this review's other primary outcome (perinatal death or severe morbidity).\nThe reduction in pyrexia, though not a pre-specified outcome of this review, may be of relevance in terms of benefits to the fetus of reduced exposure to heat. We postulate that the temperature reduction found may be a direct cooling effect of amnioinfusion with room temperature fluid, rather than reduction of infection. Larger trials are needed to confirm and extend the findings of the trial reviewed here. These should be randomised controlled trials; participants, women with chorioamnionitis; interventions, amnioinfusion; comparisons, no amnioinfusion; outcomes, maternal and perinatal outcomes including neurodevelopmental measures.\nFurther research is justified to determine possible benefits or risks of amnioinfusion for chorioamnionitis, and to investigate possible benefits of reducing temperature in fetuses considered at risk of neurological damage. Research should include randomised trials to examine transcervical or transabdominal amnioinfusion compared with no infusion for chorioamnionitis and examine outcomes listed in the methods of this review.\n\nGiven the provided abstract, please respond to the following query: \"Why is this important?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "Chorioamnionitis may lead to serious complications such as infection of the baby or of the mother. Any effective additional method of treatment would be useful." } ]

[ { "role": "user", "content": "Abstract: Background\nCarpal tunnel syndrome is a common problem and surgical decompression of the carpal tunnel is the most effective treatment. After surgical decompression, the palmar skin may be closed using either absorbable or non-absorbable sutures. To date, there is conflicting evidence regarding the ideal suture material and this formed the rationale for our review.\nObjectives\nTo assess the effects of absorbable versus non-absorbable sutures for skin closure after elective carpal tunnel decompression surgery in adults on postoperative pain, hand function, scar satisfaction, wound inflammation and adverse events.\nSearch methods\nWe searched the following databases on 30 October 2017: the Cochrane Neuromuscular Specialised Register, CENTRAL, MEDLINE, and Embase. We searched two clinical trials registries on 30 October 2017.\nSelection criteria\nWe considered all randomised or quasi-randomised controlled trials comparing absorbable and non-absorbable sutures for skin closure after any form of carpal tunnel decompression surgery in adults.\nData collection and analysis\nThe unit of analysis was the hand rather than the patient. We performed meta-analysis of direct comparisons to generate standardised mean differences (SMDs) with 95% confidence intervals (CIs) in pain scores and risk ratios (RRs) with 95% CIs for dichotomous outcomes, such as wound inflammation. The primary outcome was postoperative pain. Secondary outcomes included hand function, scar satisfaction, scar inflammation and adverse events (complications). We assessed the quality of evidence for key outcomes using GRADE.\nMain results\nWe included five randomised trials (255 participants). The trials were all European (UK, Republic of Ireland, Denmark and the Netherlands). Where quoted, the mean age of participants was between 48 and 53 years. The trials measured outcomes between one and 12 weeks postoperatively.\nMeta-analysis of postoperative pain scores for absorbable versus non-absorbable sutures at 10 days following open carpal tunnel decompression (OCTD) produced a SMD of 0.03 (95% CI -0.43 to 0.48; 3 studies, number of participants (N) = 137; I2 = 43%); the SMD suggests little or no difference, but with a high degree of uncertainty because of very low-quality evidence. At 10 days following endoscopic carpal tunnel decompression (ECTD), the SMD for postoperative pain with use of absorbable versus non-absorbable sutures was -0.81 (95% CI -1.36 to -0.25; 1 study; N = 54); although the SMD is consistent with a large effect, the very low-quality evidence means the results are very uncertain. Only the OCTD studies provided pain data at 6 weeks, when the SMD was 0.06 (95% CI -0.72 to 0.84; 4 studies; N = 175; I2 = 84%), which indicates little or no evidence of difference, but with a high degree of uncertainty (very low-quality evidence). The RR for wound inflammation using absorbable versus non-absorbable sutures after OCTD was 2.28 (95% CI 0.24 to 21.91; N = 95; I2 = 90%) and after ECTD 0.93 (95% CI 0.06 to 14.09; 1 study, N = 54). Any difference in effect on wound inflammation is uncertain because the quality of evidence is very low. One study reported postoperative hand function but found no evidence of a difference between suture types at two weeks (mean difference (MD) -0.10, 95% CI -0.53 to 0.33, N = 36), with similar findings at six and 12 weeks. Only the ECTD trial reported scar satisfaction, with 25 out of 28 people reporting a 'nice' result in the absorbable-suture group, versus 18 out of 26 in the group who received non-absorbable sutures (RR 1.29, 95% CI 0.97 to 1.72, N = 54). These findings are also very uncertain as we judged the quality of the evidence to be very low. All studies were at high risk of bias for most domains. No trials reported adverse events.\nAuthors' conclusions\nIt is uncertain whether absorbable sutures confer better, worse or equivalent outcomes compared to non-absorbable sutures following carpal tunnel decompression, because the quality of evidence is very low. Use of absorbable suture eliminates the need for suture removal, which could confer considerable savings to patients and healthcare providers alike. We need rigorously-performed, non-inferiority randomised trials with economic analyses to inform choice of suture.\n\nGiven the provided abstract, please respond to the following query: \"What is the aim of this review?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "The aim of this Cochrane review was to compare absorbable and non-absorbable material for stitching the wound after carpal tunnel surgery. We collected and analysed information on this question and found five relevant studies." } ]

[ { "role": "user", "content": "Abstract: Background\nCognitive stimulation (CS) is an intervention for people with dementia offering a range of enjoyable activities providing general stimulation for thinking, concentration and memory, usually in a social setting, such as a small group. CS is distinguished from other approaches such as cognitive training and cognitive rehabilitation by its broad focus and social elements, aiming to improve domains such as quality of life (QoL) and mood as well as cognitive function.\nRecommended in various guidelines and widely implemented internationally, questions remain regarding different modes of delivery and the clinical significance of any benefits. A systematic review of CS is important to clarify its effectiveness and place practice recommendations on a sound evidence base. This review was last updated in 2012.\nObjectives\nTo evaluate the evidence for the effectiveness of CS for people with dementia, including any negative effects, on cognition and other relevant outcomes, accounting where possible for differences in its implementation.\nSearch methods\nWe identified trials from a search of the Cochrane Dementia and Cognitive Improvement Group Specialized Register, last searched on 3 March 2022. We used the search terms: cognitive stimulation, reality orientation, memory therapy, memory groups, memory support, memory stimulation, global stimulation, cognitive psychostimulation. We performed supplementary searches in a number of major healthcare databases and trial registers to ensure the search was up-to-date and comprehensive.\nSelection criteria\nWe included all randomised controlled trials (RCTs) of CS for dementia published in peer review journals in the English language incorporating a measure of cognitive change.\nData collection and analysis\nWe used standard methodological procedures expected by Cochrane. As CS is a psychosocial intervention, we did not expect those receiving or delivering CS to be blinded to the nature of the intervention. Where necessary, we contacted study authors requesting data not provided in the papers. Where appropriate, we undertook subgroup analysis by modality (individual versus group), number of sessions and frequency, setting (community versus care home), type of control condition and dementia severity. We used GRADE methods to assess the overall quality of evidence for each outcome.\nMain results\nWe included 37 RCTs (with 2766 participants), 26 published since the previous update. Most evaluated CS groups; eight examined individual CS. Participants' median age was 79.7 years. Sixteen studies included participants resident in care homes or hospitals. Study quality showed indications of improvement since the previous review, with few areas of high risk of bias. Assessors were clearly blinded to treatment allocation in most studies (81%) and most studies (81%) reported use of a treatment manual by those delivering the intervention. However, in a substantial number of studies (59%), we could not find details on all aspects of the randomisation procedures, leading us to rate the risk of selection bias as unclear.\nWe entered data in the meta-analyses from 36 studies (2704 participants; CS: 1432, controls: 1272). The primary analysis was on changes evident immediately following the treatment period (median length 10 weeks; range 4 to 52 weeks). Only eight studies provided data allowing evaluation of whether effects were subsequently maintained (four at 6- to 12-week follow-up; four at 8- to 12-month follow-up). No negative effects were reported. Overall, we found moderate-quality evidence for a small benefit in cognition associated with CS (standardised mean difference (SMD) 0.40, 95% CI 0.25 to 0.55). In the 25 studies, with 1893 participants, reporting the widely used MMSE (Mini-Mental State Examination) test for cognitive function in dementia, there was moderate-quality evidence of a clinically important difference of 1.99 points between CS and controls (95% CI: 1.24, 2.74).\nIn secondary analyses, with smaller total sample sizes, again examining the difference between CS and controls on changes immediately following the intervention period, we found moderate-quality evidence of a slight improvement in self-reported QoL (18 studies, 1584 participants; SMD: 0.25 [95% CI: 0.07, 0.42]) as well as in QoL ratings made by proxies (staff or caregivers). We found high-quality evidence for clinically relevant improvements in staff/interviewer ratings of communication and social interaction (5 studies, 702 participants; SMD: 0.53 [95% CI: 0.36, 0.70]) and for slight benefits in instrumental Activities of Daily Living, self-reported depressed mood, staff/interviewer-rated anxiety and general behaviour rating scales. We found moderate-quality evidence for slight improvements in behaviour that challenges and in basic Activities of Daily Living and low-quality evidence for a slight improvement in staff/interviewer-rated depressed mood. A few studies reported a range of outcomes for family caregivers. We found moderate-quality evidence that overall CS made little or no difference to caregivers' mood or anxiety.\nWe found a high level of inconsistency between studies in relation to both cognitive outcomes and QoL. In exploratory subgroup analyses, we did not identify an effect of modality (group versus individual) or, for group studies, of setting (community versus care home), total number of group sessions or type of control condition (treatment-as-usual versus active controls). However, we did find improvements in cognition were larger where group sessions were more frequent (twice weekly or more versus once weekly) and where average severity of dementia among participants at the start of the intervention was 'mild' rather than 'moderate'. Imbalance in numbers of studies and participants between subgroups and residual inconsistency requires these exploratory findings to be interpreted cautiously.\nAuthors' conclusions\nIn this updated review, now with a much more extensive evidence base, we have again identified small, short-term cognitive benefits for people with mild to moderate dementia participating in CS programmes. From a smaller number of studies, we have also found clinically relevant improvements in communication and social interaction and slight benefits in a range of outcomes including QoL, mood and behaviour that challenges. There are relatively few studies of individual CS, and further research is needed to delineate the effectiveness of different delivery methods (including digital and remote, individual and group) and of multi-component programmes. We have identified that the frequency of group sessions and level of dementia severity may influence the outcomes of CS, and these aspects should be studied further. There remains an evidence gap in relation to the potential benefits of longer-term CS programmes and their clinical significance.\n\nGiven the provided abstract, please respond to the following query: \"What did we want to find out?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "We wanted to find out if CS was better for people living with dementia than usual care or unstructured social activities to improve:\n- cognitive abilities (including memory, thinking and language skills)\n- well-being and mood\n- day-to-day abilities\n- distress and upset for the person with dementia and/or carers\nWe also wanted to find out if family carers experienced any changes associated with the person with dementia receiving CS or if there were any unwanted effects." } ]

[ { "role": "user", "content": "Abstract: Background\nPeritonsillar abscess is a common infection presenting as a collection of pus in the peritonsillar area. The condition is characterised by a severe sore throat, difficulty in swallowing and pain on swallowing, fever and malaise, and trismus. Needle aspiration and incision and drainage are the two main treatment modalities currently used in the treatment of this condition. The effectiveness of one versus the other has not been clearly demonstrated and remains an area of debate.\nObjectives\nTo assess the effectiveness and risks of needle aspiration versus incision and drainage for the treatment of peritonsillar abscess in older children (eight years of age or older), adolescents and adults.\nSearch methods\nThe Cochrane ENT Information Specialist searched the ENT Trials Register; Central Register of Controlled Trials (CENTRAL 2016, Issue 7); Ovid MEDLINE; Ovid Embase; CINAHL; Web of Science; ClinicalTrials.gov; ICTRP and additional sources for published and unpublished trials. The date of the search was 25 August 2016.\nSelection criteria\nRandomised controlled trials comparing needle aspiration with incision and drainage.\nData collection and analysis\nWe used the standard methodological procedures expected by Cochrane. Our primary outcomes were recurrence rate (proportion of patients needing repeat intervention) and adverse effects associated with the intervention. Secondary outcomes were time to resumption of normal diet, complications of the disease process and symptom scores. We used GRADE to assess the quality of evidence for each outcome; this is indicated in italics.\nMain results\nWe included 11 studies (674 participants). The risk of bias was high or unclear in all of the included studies. All studies compared needle aspiration to incision and drainage.\nAll but one of the 11 studies reported on the primary outcome of recurrence. When we pooled data from the 10 studies the recurrence rate was higher in the needle aspiration group compared with incision and drainage: risk ratio (RR) 3.74 (95% confidence interval (CI) 1.63 to 8.59; 612 participants). We detected moderate heterogeneity in this analysis (I2 = 48%). In interpreting the pooled result it is important to note that the evidence for this outcome was of very low quality.\nNone of the other outcomes (adverse effects of the intervention, time to resumption of normal diet, complications of the disease process and symptom scores) were consistently measured across all studies.\nOnly three studies reported on adverse effects/events associated with the intervention and only one such event in a single patient was reported (post-procedure bleeding following incision and drainage: 1/28, 3.6%) (very low-quality evidence).\nTime to resumption of normal diet was compared in two studies; neither found an obvious difference between needle aspiration and incision and drainage (very low-quality evidence).\nOnly three studies stated that they would report complications of the disease process. In these three studies, the only complication reported was admission to hospital for dehydration in two patients who underwent incision and drainage (2/13, 6.7%).\nSymptom scores were measured in four studies; three evaluated pain using different scales and one other symptoms. The data could not be pooled in a meta-analysis. Two studies evaluating procedural pain reported this to be lower in the needle aspiration groups. One study found comparable rates of pain resolution at five days post-intervention between groups. The quality of the evidence for symptom scores was very low.\nAuthors' conclusions\nAlthough a number of studies have sought to evaluate whether or not needle aspiration or incision and drainage is more effective in patients with peritonsillar abscess, there is no high-quality evidence to allow a firm conclusion to be drawn and the answer remains uncertain. Very low-quality evidence suggests that incision and drainage may be associated with a lower chance of recurrence than needle aspiration. There is some very low-quality evidence to suggest that needle aspiration is less painful.\n\nGiven the provided abstract, please respond to the following query: \"Review question\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "This review compared the effectiveness of the two main treatment options for peritonsillar abscess: needle aspiration and incision and drainage." } ]

[ { "role": "user", "content": "Abstract: Background\nHealthcare workers can suffer from work-related stress as a result of an imbalance of demands, skills and social support at work. This may lead to stress, burnout and psychosomatic problems, and deterioration of service provision. This is an update of a Cochrane Review that was last updated in 2015, which has been split into this review and a review on organisational-level interventions.\nObjectives\nTo evaluate the effectiveness of stress-reduction interventions targeting individual healthcare workers compared to no intervention, wait list, placebo, no stress-reduction intervention or another type of stress-reduction intervention in reducing stress symptoms.\nSearch methods\nWe used the previous version of the review as one source of studies (search date: November 2013). We searched the Cochrane Central Register of Controlled Trials (CENTRAL), MEDLINE, Embase, PsycINFO, CINAHL, Web of Science and a trials register from 2013 up to February 2022.\nSelection criteria\nWe included randomised controlled trials (RCT) evaluating the effectiveness of stress interventions directed at healthcare workers. We included only interventions targeted at individual healthcare workers aimed at reducing stress symptoms.\nData collection and analysis\nReview authors independently selected trials for inclusion, assessed risk of bias and extracted data. We used standard methodological procedures expected by Cochrane. We categorised interventions into ones that:\n1. focus one’s attention on the (modification of the) experience of stress (thoughts, feelings, behaviour);\n2. focus one’s attention away from the experience of stress by various means of psychological disengagement (e.g. relaxing, exercise);\n3. alter work-related risk factors on an individual level; and ones that\n4. combine two or more of the above.\nThe crucial outcome measure was stress symptoms measured with various self-reported questionnaires such as the Maslach Burnout Inventory (MBI), measured at short term (up to and including three months after the intervention ended), medium term (> 3 to 12 months after the intervention ended), and long term follow-up (> 12 months after the intervention ended).\nMain results\nThis is the second update of the original Cochrane Review published in 2006, Issue 4. This review update includes 89 new studies, bringing the total number of studies in the current review to 117 with a total of 11,119 participants randomised.\nThe number of participants per study arm was ≥ 50 in 32 studies. The most important risk of bias was the lack of blinding of participants.\nFocus on the experience of stress versus no intervention/wait list/placebo/no stress-reduction intervention\nFifty-two studies studied an intervention in which one's focus is on the experience of stress. Overall, such interventions may result in a reduction in stress symptoms in the short term (standardised mean difference (SMD) -0.37, 95% confidence interval (CI) -0.52 to -0.23; 41 RCTs; 3645 participants; low-certainty evidence) and medium term (SMD -0.43, 95% CI -0.71 to -0.14; 19 RCTs; 1851 participants; low-certainty evidence). The SMD of the short-term result translates back to 4.6 points fewer on the MBI-emotional exhaustion scale (MBI-EE, a scale from 0 to 54). The evidence is very uncertain (one RCT; 68 participants, very low-certainty evidence) about the long-term effect on stress symptoms of focusing one's attention on the experience of stress.\nFocus away from the experience of stress versus no intervention/wait list/placebo/no stress-reduction intervention\nForty-two studies studied an intervention in which one's focus is away from the experience of stress. Overall, such interventions may result in a reduction in stress symptoms in the short term (SMD -0.55, 95 CI -0.70 to -0.40; 35 RCTs; 2366 participants; low-certainty evidence) and medium term (SMD -0.41 95% CI -0.79 to -0.03; 6 RCTs; 427 participants; low-certainty evidence). The SMD on the short term translates back to 6.8 fewer points on the MBI-EE. No studies reported the long-term effect.\nFocus on work-related, individual-level factors versus no intervention/no stress-reduction intervention\nSeven studies studied an intervention in which the focus is on altering work-related factors. The evidence is very uncertain about the short-term effects (no pooled effect estimate; three RCTs; 87 participants; very low-certainty evidence) and medium-term effects and long-term effects (no pooled effect estimate; two RCTs; 152 participants, and one RCT; 161 participants, very low-certainty evidence) of this type of stress management intervention.\nA combination of individual-level interventions versus no intervention/wait list/no stress-reduction intervention\nSeventeen studies studied a combination of interventions. In the short-term, this type of intervention may result in a reduction in stress symptoms (SMD -0.67 95%, CI -0.95 to -0.39; 15 RCTs; 1003 participants; low-certainty evidence). The SMD translates back to 8.2 fewer points on the MBI-EE. On the medium term, a combination of individual-level interventions may result in a reduction in stress symptoms, but the evidence does not exclude no effect (SMD -0.48, 95% CI -0.95 to 0.00; 6 RCTs; 574 participants; low-certainty evidence). The evidence is very uncertain about the long term effects of a combination of interventions on stress symptoms (one RCT, 88 participants; very low-certainty evidence).\nFocus on stress versus other intervention type\nThree studies compared focusing on stress versus focusing away from stress and one study a combination of interventions versus focusing on stress. The evidence is very uncertain about which type of intervention is better or if their effect is similar.\nAuthors' conclusions\nOur review shows that there may be an effect on stress reduction in healthcare workers from individual-level stress interventions, whether they focus one's attention on or away from the experience of stress. This effect may last up to a year after the end of the intervention. A combination of interventions may be beneficial as well, at least in the short term. Long-term effects of individual-level stress management interventions remain unknown. The same applies for interventions on (individual-level) work-related risk factors.\nThe bias assessment of the studies in this review showed the need for methodologically better-designed and executed studies, as nearly all studies suffered from poor reporting of the randomisation procedures, lack of blinding of participants and lack of trial registration. Better-designed trials with larger sample sizes are required to increase the certainty of the evidence. Last, there is a need for more studies on interventions which focus on work-related risk factors.\n\nGiven the provided abstract, please respond to the following query: \"What did we do\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "We searched for studies that looked at stress management interventions in healthcare workers and reported on stress symptoms. The healthcare workforce comprises a wide variety of professions and occupations who provide some type of healthcare service, including direct care practitioners and allied professionals.\nWe compared and summarised the results of the studies and rated our confidence in the evidence, based on factors such as study methods and study size." } ]

[ { "role": "user", "content": "Abstract: Background\nThis is the third updated version of a Cochrane review first published in Issue 4, 2003 of The Cochrane Library and first updated in 2007. Morphine has been used for many years to relieve pain. Oral morphine in either immediate release or modified release form remains the analgesic of choice for moderate or severe cancer pain.\nObjectives\nTo determine the efficacy of oral morphine in relieving cancer pain, and to assess the incidence and severity of adverse events.\nSearch methods\nWe searched the following databases: Cochrane Central Register of Controlled Trials (CENTRAL 2015, Issue 9); MEDLINE (1966 to October 2015); and EMBASE (1974 to October 2015). We also searched ClinicalTrials.gov (1 October 2015).\nSelection criteria\nPublished randomised controlled trials (RCTs) using placebo or active comparators reporting on the analgesic effect of oral morphine in adults and children with cancer pain. We excluded trials with fewer than 10 participants.\nData collection and analysis\nOne review author extracted data, which were checked by another review author. There were insufficient comparable data for meta-analysis to be undertaken or to produce numbers needed to treat (NNTs) for the analgesic effect. We extracted any available data on the number or proportion of participants with 'no worse than mild pain' or treatment success (very satisfied, or very good or excellent on patient global impression scales).\nMain results\nWe identified seven new studies in this update. We excluded six, and one study is ongoing so also not included in this update. This review contains a total of 62 included studies, with 4241 participants. Thirty-six studies used a cross-over design ranging from one to 15 days, with the greatest number (11) for seven days for each arm of the trial. Overall we judged the included studies to be at high risk of bias because the methods of randomisation and allocation concealment were poorly reported. The primary outcomes for this review were participant-reported pain and pain relief.\nFifteen studies compared oral morphine modified release (Mm/r) preparations with morphine immediate release (MIR). Fourteen studies compared Mm/r in different strengths; six of these included 24-hour modified release products. Fifteen studies compared Mm/r with other opioids. Six studies compared MIR with other opioids. Two studies compared oral Mm/r with rectal Mm/r. Three studies compared MIR with MIR by a different route of administration. Two studies compared Mm/r with Mm/r at different times and two compared MIR with MIR given at a different time. One study was found comparing each of the following: Mm/r tablet with Mm/r suspension; Mm/r with non-opioids; MIR with non-opioids; and oral morphine with epidural morphine.\nIn the previous update, a standard of 'no worse than mild pain' was set, equivalent to a score of 30/100 mm or less on a visual analogue pain intensity scale (VAS), or the equivalent in other pain scales. Eighteen studies achieved this level of pain relief on average, and no study reported that good levels of pain relief were not attained. Where results were reported for individual participants in 17 studies, 'no worse than mild pain' was achieved by 96% of participants (362/377), and an outcome equivalent to treatment success in 63% (400/638).\nMorphine is an effective analgesic for cancer pain. Pain relief did not differ between Mm/r and MIR. Modified release versions of morphine were effective for 12- or 24-hour dosing depending on the formulation. Daily doses in studies ranged from 25 mg to 2000 mg with an average of between 100 mg and 250 mg. Dose titration was undertaken with both instant release and modified release products. A small number of participants did not achieve adequate analgesia with morphine. Adverse events were common, predictable, and approximately 6% of participants discontinued treatment with morphine because of intolerable adverse events.\nThe quality of the evidence is generally poor. Studies are old, often small, and were largely carried out for registration purposes and therefore were only designed to show equivalence between different formulations.\nAuthors' conclusions\nThe conclusions have not changed for this update. The effectiveness of oral morphine has stood the test of time, but the randomised trial literature for morphine is small given the importance of this medicine. Most trials recruited fewer than 100 participants and did not provide appropriate data for meta-analysis. Only a few reported how many people had good pain relief, but where it was reported, over 90% had no worse than mild pain within a reasonably short time period. The review demonstrates the wide dose range of morphine used in studies, and that a small percentage of participants are unable to tolerate oral morphine. The review also shows the wide range of study designs, and inconsistency in cross-over designs. Trial design was frequently based on titration of morphine or comparator to achieve adequate analgesia, then crossing participants over in cross-over design studies. It was not clear if these trials were sufficiently powered to detect any clinical differences between formulations or comparator drugs. New studies added to the review for the previous update reinforced the view that it is possible to use modified release morphine to titrate to analgesic effect. There is qualitative evidence that oral morphine has much the same efficacy as other available opioids.\n\nGiven the provided abstract, please respond to the following query: \"Background\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "Morphine taken by mouth produced good pain relief for most people with moderate or severe cancer pain.\nOne person in two or three who gets cancer will suffer from pain that becomes moderate or severe in intensity. The pain tends to get worse as the cancer progresses. Morphine taken by mouth has been used since the 1950s for controlling cancer pain. In 1986 the World Health Organization recommended taking an oral solution of morphine every four hours. Morphine is now available in a number of different formats that release the morphine over various periods of time. Morphine immediate release is rapidly absorbed, and would usually be taken every four hours. Modified release tablets are available that release morphine more slowly, so that they can be taken only twice a day or even only once a day." } ]

[ { "role": "user", "content": "Abstract: Background\nPhosphate binders are used to reduce positive phosphate balance and to lower serum phosphate levels for people with chronic kidney disease (CKD) with the aim to prevent progression of chronic kidney disease-mineral and bone disorder (CKD-MBD). This is an update of a review first published in 2011.\nObjectives\nThe aim of this review was to assess the benefits and harms of phosphate binders for people with CKD with particular reference to relevant biochemical end-points, musculoskeletal and cardiovascular morbidity, hospitalisation, and death.\nSearch methods\nWe searched the Cochrane Kidney and Transplant Register of Studies up to 12 July 2018 through contact with the Information Specialist using search terms relevant to this review. Studies in the Register are identified through searches of CENTRAL, MEDLINE, and EMBASE, conference proceedings, the International Clinical Trials Register (ICTRP) Search Portal and ClinicalTrials.gov.\nSelection criteria\nWe included randomised controlled trials (RCTs) or quasi-RCTs of adults with CKD of any GFR category comparing a phosphate binder to another phosphate binder, placebo or usual care to lower serum phosphate. Outcomes included all-cause and cardiovascular death, myocardial infarction, stroke, adverse events, vascular calcification and bone fracture, and surrogates for such outcomes including serum phosphate, parathyroid hormone (PTH), and FGF23.\nData collection and analysis\nTwo authors independently selected studies for inclusion and extracted study data. We applied the Cochrane 'Risk of Bias' tool and used the GRADE process to assess evidence certainty. We estimated treatment effects using random-effects meta-analysis. Results were expressed as risk ratios (RR) for dichotomous outcomes together with 95% confidence intervals (CI) or mean differences (MD) or standardised MD (SMD) for continuous outcomes.\nMain results\nWe included 104 studies involving 13,744 adults. Sixty-nine new studies were added to this 2018 update.\nMost placebo or usual care controlled studies were among participants with CKD G2 to G5 not requiring dialysis (15/25 studies involving 1467 participants) while most head to head studies involved participants with CKD G5D treated with dialysis (74/81 studies involving 10,364 participants). Overall, seven studies compared sevelamer with placebo or usual care (667 participants), seven compared lanthanum to placebo or usual care (515 participants), three compared iron to placebo or usual care (422 participants), and four compared calcium to placebo or usual care (278 participants). Thirty studies compared sevelamer to calcium (5424 participants), and fourteen studies compared lanthanum to calcium (1690 participants). No study compared iron-based binders to calcium. The remaining studies evaluated comparisons between sevelamer (hydrochloride or carbonate), sevelamer plus calcium, lanthanum, iron (ferric citrate, sucroferric oxyhydroxide, stabilised polynuclear iron(III)-oxyhydroxide), calcium (acetate, ketoglutarate, carbonate), bixalomer, colestilan, magnesium (carbonate), magnesium plus calcium, aluminium hydroxide, sucralfate, the inhibitor of phosphate absorption nicotinamide, placebo, or usual care without binder. In 82 studies, treatment was evaluated among adults with CKD G5D treated with haemodialysis or peritoneal dialysis, while in 22 studies, treatment was evaluated among participants with CKD G2 to G5. The duration of study follow-up ranged from 8 weeks to 36 months (median 3.7 months). The sample size ranged from 8 to 2103 participants (median 69). The mean age ranged between 42.6 and 68.9 years.\nRandom sequence generation and allocation concealment were low risk in 25 and 15 studies, respectively. Twenty-seven studies reported low risk methods for blinding of participants, investigators, and outcome assessors. Thirty-one studies were at low risk of attrition bias and 69 studies were at low risk of selective reporting bias.\nIn CKD G2 to G5, compared with placebo or usual care, sevelamer, lanthanum, iron and calcium-based phosphate binders had uncertain or inestimable effects on death (all causes), cardiovascular death, myocardial infarction, stroke, fracture, or coronary artery calcification. Sevelamer may lead to constipation (RR 6.92, CI 2.24 to 21.4; low certainty) and lanthanum (RR 2.98, CI 1.21 to 7.30, moderate certainty) and iron-based binders (RR 2.66, CI 1.15 to 6.12, moderate certainty) probably increased constipation compared with placebo or usual care. Lanthanum may result in vomiting (RR 3.72, CI 1.36 to 10.18, low certainty). Iron-based binders probably result in diarrhoea (RR 2.81, CI 1.18 to 6.68, high certainty), while the risks of other adverse events for all binders were uncertain.\nIn CKD G5D sevelamer may lead to lower death (all causes) (RR 0.53, CI 0.30 to 0.91, low certainty) and induce less hypercalcaemia (RR 0.30, CI 0.20 to 0.43, low certainty) when compared with calcium-based binders, and has uncertain or inestimable effects on cardiovascular death, myocardial infarction, stroke, fracture, or coronary artery calcification. The finding of lower death with sevelamer compared with calcium was present when the analysis was restricted to studies at low risk of bias (RR 0.50, CI 0.32 to 0.77). In absolute terms, sevelamer may lower risk of death (all causes) from 210 per 1000 to 105 per 1000 over a follow-up of up to 36 months, compared to calcium-based binders. Compared with calcium-based binders, lanthanum had uncertain effects with respect to all-cause or cardiovascular death, myocardial infarction, stroke, fracture, or coronary artery calcification and probably had reduced risks of treatment-related hypercalcaemia (RR 0.16, CI 0.06 to 0.43, low certainty). There were no head-to-head studies of iron-based binders compared with calcium. The paucity of placebo-controlled studies in CKD G5D has led to uncertainty about the effects of phosphate binders on patient-important outcomes compared with placebo.\nIt is uncertain whether the effects of binders on clinically-relevant outcomes were different for patients who were and were not treated with dialysis in subgroup analyses.\nAuthors' conclusions\nIn studies of adults with CKD G5D treated with dialysis, sevelamer may lower death (all causes) compared to calcium-based binders and incur less treatment-related hypercalcaemia, while we found no clinically important benefits of any phosphate binder on cardiovascular death, myocardial infarction, stroke, fracture or coronary artery calcification. The effects of binders on patient-important outcomes compared to placebo are uncertain. In patients with CKD G2 to G5, the effects of sevelamer, lanthanum, and iron-based phosphate binders on cardiovascular, vascular calcification, and bone outcomes compared to placebo or usual care, are also uncertain and they may incur constipation, while iron-based binders may lead to diarrhoea.\n\nGiven the provided abstract, please respond to the following query: \"Conclusions\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "Overall, we are not very sure whether specific phosphate binders are beneficial to patients with CKD. There is a possibility that sevelamer may prevent death compared to calcium-based binders, but we don't know whether this may be caused by an increased risk of calcium-based binders, a lower risk with sevelamer treatment, or the possibility that both may be true. Patients need to know that it is not certain whether phosphate binders help to prevent complications of kidney disease, but sevelamer may be preferred to calcium binders.\nWe did not find differences in the effects of treatment for patients on dialysis and those not on dialysis, although most studies evaluating treatment with calcium-based binders were among dialysis patients and those comparing binders with placebo were among people not treated with dialysis." } ]

[ { "role": "user", "content": "Abstract: Background\nGenital Chlamydia trachomatis (C.trachomatis) infection may lead to pregnancy complications such as miscarriage, preterm labour, low birthweight, preterm rupture of membranes, increased perinatal mortality, postpartum endometritis, chlamydial conjunctivitis and C.trachomatis pneumonia.This review supersedes a previous review on this topic.\nObjectives\nTo establish the most efficacious and best-tolerated therapy for treatment of genital chlamydial infection in preventing maternal infection and adverse neonatal outcomes.\nSearch methods\nWe searched the Cochrane Pregnancy and Childbirth Group’s Trials Register, ClinicalTrials.gov, the WHO International Clinical Trials Registry Platform (ICTRP) (26 June 2017) and reference lists of retrieved studies.\nSelection criteria\nRandomised controlled trials (RCTs) as well as studies published in abstract form assessing interventions for treating genital C.trachomatis infection in pregnancy. Cluster-RCTs were also eligible for inclusion but none were identified. Quasi-randomised trials and trials using cross-over design are not eligible for inclusion in this review.\nData collection and analysis\nTwo review authors independently assessed studies for inclusion, assessed trial quality and extracted the data using the agreed form. Data were checked for accuracy. Evidence was assessed using the GRADE approach.\nMain results\nWe included 15 trials (involving 1754 women) although our meta-analyses were based on fewer numbers of studies/women. All of the included studies were undertaken in North America from 1982 to 2001. Two studies were low risk of bias in all domains, all other studies had varying risk of bias. Four other studies were excluded and one study is ongoing.\nEight comparisons were included in this review; three compared antibiotic (erythromycin, clindamycin, amoxicillin) versus placebo; five compared an antibiotic versus another antibiotic (erythromycin, clindamycin, amoxicillin, azithromycin). No study reported different antibiotic regimens.\nMicrobiological cure (primary outcome)\nAntibiotics versus placebo: Erythromycin (average risk ratio (RR) 2.64, 95% confidence interval (CI) 1.60 to 4.38; two trials, 495 women; I2 = 68%; moderate-certainty evidence), and clindamycin (RR 4.08, 95% CI 2.35 to 7.08; one trial, 85 women;low-certainty evidence) were associated with improved microbiological cure compared to a placebo control. In one very small trial comparing amoxicillin and placebo, the results were unclear, but the evidence was graded very low (RR 2.00, 95% CI 0.59 to 6.79; 15 women).\nOne antibiotic versus another antibiotic: Amoxicillin made little or no difference in microbiological cure in comparison to erythromycin (RR 0.97, 95% CI 0.93 to 1.01; four trials, 466 women; high-certainty evidence), probably no difference compared to clindamycin (RR 0.96, 95% CI 0.89 to 1.04; one trial, 101 women; moderate-quality evidence), and evidence is very low certainty when compared to azithromycin so the effect is not certain (RR 0.89, 95% CI 0.71 to 1.12; two trials, 144 women; very low-certainty evidence). Azithromycin versus erythromycin (average RR 1.11, 95% CI 1.00 to 1.23; six trials, 374 women; I2 = 53%; moderate-certainty evidence) probably have similar efficacy though results appear to favour azithromycin. Clindamycin versus erythromycin (RR 1.06, 95% CI 0.97 to 1.15; two trials, 173 women; low-certainty evidence) may have similar numbers of women with a microbiological cure between groups.\nEvidence was downgraded for design limitations, inconsistency, and imprecision in effect estimates.\nSide effects of the treatment (maternal) (secondary outcome)\nAntibiotics versus placebo: side effects including nausea, vomiting, and abdominal pain, were reported in two studies (495 women) but there was no clear evidence whether erythromycin was associated with more side effects than placebo and a high level of heterogeneity (I2 = 78%) was observed (average RR 2.93, 95% CI 0.36 to 23.76). There was no clear difference in the number of women experiencing side effects when clindamycin was compared to placebo in one small study (5/41 versus 1/44) (RR 6.35, 95% CI 0.38 to 107.45, 62 women). The side effects reported were mostly gastrointestinal and also included resolving skin rashes.\nOne antibiotic versus another antibiotic: There was no clear difference in incidence of side effects (including nausea, vomiting, diarrhoea and abdominal pain) when amoxicillin was compared to azithromycin based on data from one small study (36 women) (RR 0.56, 95% CI 0.24 to 1.31).\nHowever, amoxicillin was associated with fewer side effects compared to erythromycin with data from four trials (513 women) (RR 0.31, 95% CI 0.21 to 0.46; I2 = 27%). Side effects included nausea, vomiting, diarrhoea, abdominal cramping, rash, and allergic reaction.\nBoth azithromycin (RR 0.24, 95% CI 0.17 to 0.34; six trials, 374 women) and clindamycin (RR 0.44, 95% CI 0.22 to 0.87; two trials, 183 women) were associated with a lower incidence of side effects compared to erythromycin. These side effects included nausea, vomiting, diarrhoea and abdominal cramping.\nOne small study (101 women) reported there was no clear difference in the number of women with side effects when amoxicillin was compared with clindamycin (RR 0.57, 95% CI 0.14 to 2.26; 107 women). The side effects reported included rash and gastrointestinal complaints.\nOther secondary outcomes\nSingle trials reported data on repeated infections, preterm birth, preterm rupture of membranes, perinatal mortality and low birthweight and found no clear differences between treatments.\nMany of this review's secondary outcomes were not reported in the included studies.\nAuthors' conclusions\nTreatment with antibacterial agents achieves microbiological cure from C.trachomatis infection during pregnancy. There was no apparent difference between assessed agents (amoxicillin, erythromycin, clindamycin, azithromycin) in terms of efficacy (microbiological cure and repeat infection) and pregnancy complications (preterm birth, preterm rupture of membranes, low birthweight). Azithromycin and clindamycin appear to result in fewer side effects than erythromycin.\nAll of the studies in this review were conducted in North America, which may limit the generalisability of the results. In addition, study populations may differ in low-resource settings and these results are therefore only applicable to well-resourced settings. Furthermore, the trials in this review mainly took place in the nineties and early 2000's and antibiotic resistance may have changed since then.\nFurther well-designed studies, with appropriate sample sizes and set in a variety of settings, are required to further evaluate interventions for treating C.trachomatis infection in pregnancy and determine which agents achieve the best microbiological cure with the least side effects. Such studies could report on the outcomes listed in this review.\n\nGiven the provided abstract, please respond to the following query: \"What does this mean?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "Treatment of chlamydia infection with antibiotics appears to be effective during pregnancy. There is no clear difference between amoxicillin, erythromycin, clindamycin, azithromycin in curing the infection or preterm birth, preterm rupture of membranes, and low birthweight. Azithromycin and clindamycin appear to result in fewer side effects than erythromycin.\nThe included studies were all carried out in North America. Chlamydia testing remains a problem in low-resource settings because of its costs. We conclude that well-designed studies of appropriate sample size, in different settings, are needed to further assess the effects of treatment of chlamydia infection in pregnancy. Resistance to the tested antibiotics could have changed since the studies included in this review were conducted. In particular, future research could report on the outcomes of focus in this review and target those antibiotics, such as amoxicillin and clindamycin, which may be effective in curing chlamydia with the least side effects." } ]

[ { "role": "user", "content": "Abstract: Background\nFollowing surgery, incisions are usually closed by fixing the edges together with sutures (stitches), staples, adhesives (glue) or clips. This process helps the cut edges heal together and is called 'healing by primary intention'. However, a minority of surgical wounds are not closed in this way. Where the risk of infection is high or there has been significant loss of tissue, wounds may be left open to heal by the growth of new tissue rather than by primary closure; this is known as 'healing by secondary intention'. There is a risk of infection in open wounds, which may impact on wound healing, and antiseptic or antibiotic treatments may be used with the aim of preventing or treating such infections. This review is one of a suite of Cochrane reviews investigating the evidence on antiseptics and antibiotics in different types of wounds. It aims to present current evidence related to the use of antiseptics and antibiotics for surgical wounds healing by secondary intention (SWHSI).\nObjectives\nTo assess the effects of systemic and topical antibiotics, and topical antiseptics for the treatment of surgical wounds healing by secondary intention.\nSearch methods\nIn November 2015 we searched: The Cochrane Wounds Specialised Register; The Cochrane Central Register of Controlled Trials (CENTRAL) (The Cochrane Library); Ovid MEDLINE; Ovid MEDLINE (In-Process & Other Non-Indexed Citations); Ovid EMBASE and EBSCO CINAHL. We also searched three clinical trials registries and the references of included studies and relevant systematic reviews. There were no restrictions with respect to language, date of publication or study setting.\nSelection criteria\nRandomised controlled trials which enrolled adults with a surgical wound healing by secondary intention and assessed treatment with an antiseptic or antibiotic treatment. Studies enrolling people with skin graft donor sites were not included, neither were studies of wounds with a non-surgical origin which had subsequently undergone sharp or surgical debridement or other surgical treatments or wounds within the oral or aural cavities.\nData collection and analysis\nTwo review authors independently performed study selection, risk of bias assessment and data extraction.\nMain results\nEleven studies with a total of 886 participants were included in the review. These evaluated a range of comparisons in a range of surgical wounds healing by secondary intention. In general studies were small and some did not present data or analyses that could be easily interpreted or related to clinical outcomes. These factors reduced the quality of the evidence.\nTwo comparisons compared different iodine preparations with no antiseptic treatment and found no clear evidence of effects for these treatments. The outcome data available were limited and what evidence there was low quality.\nOne study compared a zinc oxide mesh dressing with a plain mesh dressing. There was no clear evidence of a difference in time to wound healing between groups. There was some evidence of a difference in measures used to assess wound infection (wound with foul smell and number of participants prescribed antibiotics) which favoured the zinc oxide group. This was low quality evidence.\nOne study reported that sucralfate cream increased the likelihood of healing open wounds following haemorrhoidectomy compared to a petrolatum cream (RR: 1.50, 95% CI 1.13 to 1.99) over a three week period. This evidence was graded as being of moderate quality. The study also reported lower wound pain scores in the sucralfate group.\nThere was a reduction in time to healing of open wounds following haemorrhoidectomy when treated with Triclosan post-operatively compared with a standard sodium hypochlorite solution (mean difference -1.70 days, 95% CI -3.41 to 0.01). This was classed as low quality evidence.\nThere was moderate quality evidence that more open wounds resulting from excision of pyomyositis abscesses healed when treated with a honey-soaked gauze compared with a EUSOL-soaked gauze over three weeks' follow-up (RR: 1.58, 95% CI 1.03 to 2.42). There was also some evidence of a reduction in the mean length of hospital stay in the honey group. Evidence was taken from one small study that only had 43 participants.\nThere was moderate quality evidence that more Dermacym®-treated post-operative foot wounds in people with diabetes healed compared to those treated with iodine (RR 0.61, 95% CI 0.40 to 0.93). Again estimates came from one small study with 40 participants.\nAuthors' conclusions\nThere is no robust evidence on the relative effectiveness of any antiseptic/antibiotic/anti-bacterial preparation evaluated to date for use on SWHSI. Where some evidence for possible treatment effects was reported, it stemmed from single studies with small participant numbers and was classed as moderate or low quality evidence. This means it is likely or very likely that further research will have an important impact on our confidence in the estimate of effect, and may change this estimate.\n\nGiven the provided abstract, please respond to the following query: \"What are surgical wounds healing by secondary intention?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "These are surgical wounds which are left open to heal through the growth of new tissue, rather than being closed in the usual way with stitches or other methods which bring the wound edges together. This is usually done when there is a high risk of infection or a large amount of tissue has been lost from the wound. Wounds which are often treated in this way include chronic wounds in the cleft between the buttocks (pilonidal sinuses) and some types of abscesses." } ]

[ { "role": "user", "content": "Abstract: Background\nTrachoma remains a major cause of avoidable blindness among underprivileged populations in many developing countries. It is estimated that about 146 million people have active trachoma and nearly six million people are blind due to complications associated with repeat infections.\nObjectives\nThe objective of this review was to assess the effects of face washing promotion for the prevention of active trachoma in endemic communities.\nSearch methods\nWe searched CENTRAL (which contains the Cochrane Eyes and Vision Group Trials Register) (2015, Issue 1), Ovid MEDLINE, Ovid MEDLINE In-Process and Other Non-Indexed Citations, Ovid MEDLINE Daily, Ovid OLDMEDLINE (January 1946 to January 2015), EMBASE (January 1980 to January 2015), PubMed (January 1948 to January 2015), Latin American and Caribbean Health Sciences Literature Database (LILACS) (January 1982 to January 2015), the metaRegister of Controlled Trials (mRCT) (www.controlled-trials.com) (accessed 10 January 2014), ClinicalTrials.gov (www.clinicaltrials.gov) and the World Health Organization (WHO) International Clinical Trials Registry Platform (ICTRP) (www.who.int/ictrp/search/en). We did not use any date or language restrictions in the electronic searches for trials. We last searched the electronic databases on 26 January 2015.\nTo identify further relevant trials we checked the reference lists of the included trials. Also, we used the Science Citation Index to search for references to publications that cited the trials included in the review. We contacted investigators and experts in the field to identify additional trials.\nSelection criteria\nWe included randomized controlled trials (RCTs) or quasi-RCTs that compared face washing with no treatment or face washing combined with antibiotics against antibiotics alone. Trial participants were residents of endemic trachoma communities.\nData collection and analysis\nTwo review authors independently extracted data and assessed trial quality. We contacted trial authors for additional information when needed. Two trials met our inclusion criteria; but we did not conduct meta-analysis due to methodological heterogeneity.\nMain results\nWe included two cluster-RCTs, which provided data from 2447 participants. Both trials were conducted in areas endemic to trachoma: Northern Australia and Tanzania. The follow-up period was three months in one trial and 12 months in the other; both trials had about 90% participant follow-up at final visit. Overall the quality of the evidence is uncertain due to the trials not reporting many design methods and the differences in outcomes reported between trials.\nFace washing combined with topical tetracycline was compared with topical tetracycline alone in three pairs of villages in one trial. The trial found that face washing combined with topical tetracycline reduced 'severe' active trachoma compared with topical tetracycline alone at 12 months (adjusted odds ratio (OR) 0.62, 95% confidence interval (CI) 0.40 to 0.97); however, the trial did not find any important difference between the intervention and control villages in reducing other types of active trachoma (adjusted OR 0.81, 95% CI 0.42 to 1.59). Intervention villages had a higher prevalence of clean faces than the control villages among children with severe trachoma (adjusted OR 0.35, 95% CI 0.21 to 0.59) and any trachoma (adjusted OR 0.58, 95% CI 0.47 to 0.72) at 12 months follow-up. The second trial compared eye washing to no treatment or to topical tetracycline alone or to a combination of eye washing and tetracycline drops in children with follicular trachoma. At three months, the trial found no evidence of benefit of eye washing alone or in combination with tetracycline eye drops in reducing follicular trachoma amongst children with follicular trachoma (risk ratio (RR) 1.03, 95% CI 0.96 to 1.11; one trial, 1143 participants).\nAuthors' conclusions\nThere is evidence from one trial that face washing combined with topical tetracycline may be effective in reducing severe active trachoma and in increasing the prevalence of clean faces at one year follow-up. Current evidence is inconclusive as to the effectiveness of face washing alone or in combination with topical tetracycline in reducing active or severe trachoma.\n\nGiven the provided abstract, please respond to the following query: \"Study characteristics\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "We included two randomized controlled trials with a total of 2560 participants set in Australia and Tanzania. One trial compared a combined strategy of face washing plus tetracycline (an antibiotic) ointment with tetracycline ointment alone for up to one year. The second trial compared four intervention groups for three months in children who already had follicular trachoma: a combined strategy of face washing plus tetracycline eye drops, face washing alone, tetracycline eye drops alone, and no treatment. The evidence is current to January 2015." } ]

[ { "role": "user", "content": "Abstract: Background\nEach year, more than four million abdominal surgeries are performed in the US and over 250,000 in England. Acute respiratory failure, a common complication that can affect 30% to 50% of people after upper abdominal surgery, can lead to significant morbidity and mortality. Noninvasive ventilation has been associated with lower rates of tracheal intubation in adults with acute respiratory failure, thus reducing the incidence of complications and mortality. This review compared the effectiveness and safety of noninvasive positive pressure ventilation (NPPV) versus standard oxygen therapy in the treatment of acute respiratory failure after upper abdominal surgery.\nObjectives\nTo assess the effectiveness and safety of noninvasive positive pressure ventilation (NPPV), that is, continuous positive airway pressure (CPAP) or bilevel NPPV, in reducing mortality and the rate of tracheal intubation in adults with acute respiratory failure after upper abdominal surgery, compared to standard therapy (oxygen therapy), and to assess changes in arterial blood gas levels, hospital and intensive care unit (ICU) length of stay, gastric insufflation, and anastomotic leakage.\nSearch methods\nThe date of the last search was 12 May 2015. We searched the following databases: the Cochrane Handbook for Systematic Reviews of Interventions (CENTRAL) (2015, Issue 5), MEDLINE (Ovid SP, 1966 to May 2015), EMBASE (Ovid SP, 1974 to May 2015); the physiotherapy evidence database (PEDro) (1999 to May 2015); the Cumulative Index to Nursing and Allied Health Literature (CINAHL, EBSCOhost, 1982 to May 2015), and LILACS (BIREME, 1986 to May 2015). We reviewed reference lists of included studies and contacted experts. We also searched grey literature sources. We checked databases of ongoing trials such as www.controlled-trials.com/ and www.trialscentral.org/. We did not apply language restrictions.\nSelection criteria\nWe selected randomized or quasi-randomized controlled trials involving adults with acute respiratory failure after upper abdominal surgery who were treated with CPAP or bilevel NPPV with, or without, drug therapy as standard medical care, compared to adults treated with oxygen therapy with, or without, standard medical care.\nData collection and analysis\nTwo authors independently selected and abstracted data from eligible studies using a standardized form. We evaluated study quality by assessing allocation concealment; random sequence generation; incomplete outcome data; blinding of participants, personnel, and outcome assessors; selective reporting; and adherence to the intention-to-treat (ITT) principle.\nMain results\nWe included two trials involving 269 participants. The participants were mostly men (67%); the mean age was 65 years. The trials were conducted in China and Italy (one was a multicentre trial). Both trials included adults with acute respiratory failure after upper abdominal surgery. We judged both trials at high risk of bias. Compared to oxygen therapy, CPAP or bilevel NPPV may reduce the rate of tracheal intubation (risk ratio (RR) 0.25; 95% confidence interval (CI) 0.08 to 0.83; low quality evidence) with a number needed to treat for an additional beneficial outcome of 11. There was very low quality evidence that the intervention may also reduce ICU length of stay (mean difference (MD) -1.84 days; 95% CI -3.53 to -0.15). We found no differences for mortality (low quality evidence) and hospital length of stay. There was insufficient evidence to be certain that CPAP or NPPV had an effect on anastomotic leakage, pneumonia-related complications, and sepsis or infections. Findings from one trial of 60 participants suggested that bilevel NPPV, compared to oxygen therapy, may improve blood gas levels and blood pH one hour after the intervention (partial pressure of arterial oxygen (PaO2): MD 22.5 mm Hg; 95% CI 17.19 to 27.81; pH: MD 0.06; 95% CI 0.01 to 0.11; partial pressure of arterial carbon dioxide (PCO2) levels (MD -9.8 mm Hg; 95% CI -14.07 to -5.53). The trials included in this systematic review did not present data on the following outcomes that we intended to assess: gastric insufflation, fistulae, pneumothorax, bleeding, skin breakdown, eye irritation, sinus congestion, oronasal drying, and patient-ventilator asynchrony.\nAuthors' conclusions\nThe findings of this review indicate that CPAP or bilevel NPPV is an effective and safe intervention for the treatment of adults with acute respiratory failure after upper abdominal surgery. However, based on the Grading of Recommendations Assessment, Development and Evaluation (GRADE) methodology, the quality of the evidence was low or very low. More good quality studies are needed to confirm these findings.\n\nGiven the provided abstract, please respond to the following query: \"Key results\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "This review examined mortality, rate of tracheal intubation, length of stay in the ICU, length of hospital stay, complications after NPPV, and changes in the levels of gases within the blood (arterial blood gases).\nCompared with oxygen therapy, NPPV decreased the rate of tracheal intubation. Out of every 1000 adults who developed acute respiratory failure after upper abdominal surgery, 181 adults treated with oxygen therapy would need to be intubated compared with 54 adults treated with NPPV.\nWhen compared to oxygen therapy, NPPV tended to reduce mortality. However, since the number of participants included in the two trials was small, more studies are needed.\nThe use of NPPV also reduced the length of stay in the ICU by almost two days when compared to oxygen therapy. However, the mean length of stay in the hospital was similar in the two groups.\nWhen compared to oxygen therapy, NPPV improved blood gas levels one hour after the intervention.\nThere was insufficient evidence to be certain that CPAP or NPPV had an effect on anastomotic (e.g. where two pieces of intestine are joined together) leakage, pneumonia related complications and sepsis (blood poisoning) or infections. However, adults treated with NPPV had lower rates these complications than adults treated with oxygen." } ]

[ { "role": "user", "content": "Abstract: Background\nRecurrent endobronchial infection in cystic fibrosis requires treatment with intravenous antibiotics for several weeks usually in hospital, affecting health costs and quality of life for patients and their families. This is an update of a previously published review.\nObjectives\nTo determine whether home intravenous antibiotic therapy in cystic fibrosis is as effective as inpatient intravenous antibiotic therapy and if it is preferred by individuals or families or both.\nSearch methods\nWe searched the Cochrane Cystic Fibrosis and Genetic Disorders Group Trials Register comprising references identified from comprehensive electronic database searches and handsearches of relevant journals and abstract books of conference proceedings.\nMost recent search of the Group's Trials Register: 23 November 2015.\nSelection criteria\nRandomized and quasi-randomized controlled studies of intravenous antibiotic treatment for adults and children with cystic fibrosis at home compared to in hospital.\nData collection and analysis\nThe authors independently selected studies for inclusion in the review, assessed methodological quality of each study and extracted data using a standardised form.\nMain results\nEighteen studies were identified by the searches. Only one study could be included which reported results from 17 participants aged 10 to 41 years with an infective exacerbation of Pseudomonas aeruginosa. All their 31 admissions (18 hospital and 13 at home after two to four days of hospital treatment) were analysed as independent events. Outcomes were measured at 0, 10 and 21 days after initiation of treatment. Home participants underwent fewer investigations than hospital participants (P < 0.002) and general activity was higher in the home group. No significant differences were found for clinical outcomes, adverse events, complications or change of intravenous lines,or time to next admission. Home participants received less low-dose home maintenance antibiotic.\nQuality of life measures showed no significant differences for dyspnoea and emotional state, but fatigue and mastery were worse for home participants, possibly due to a higher general activity and need of support. Personal, family, sleeping and eating disruptions were less important for home than hospital admissions.\nHome therapy was cheaper for families and the hospital. Indirect costs were not determined.\nAuthors' conclusions\nCurrent evidence is restricted to a single randomized clinical trial. It suggests that, in the short term, home therapy does not harm individuals, entails fewer investigations, reduces social disruptions and can be cost-effective. There were both advantages and disadvantages in terms of quality of life. The decision to attempt home treatment should be based on the individual situation and appropriate local resources. More research is urgently required.\n\nGiven the provided abstract, please respond to the following query: \"Search date\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "The evidence is current to: 23 November 2015." } ]

[ { "role": "user", "content": "Abstract: Background\nInfantile nystagmus syndrome (INS) is a type of eye movement disorder that can negatively impact vision. Currently, INS cannot be cured, but its effects can potentially be treated pharmacologically, optically, or surgically. This review focuses on the surgical interventions for INS.\nDespite the range of surgical interventions available, and currently applied in practice for the management of INS, there is no clear consensus, and no accepted clinical guidelines regarding the relative efficacy and safety of the various treatment options. A better understanding of these surgical options, along with their associated side effects, will assist clinicians in evidence-based decision-making in relation to the management of INS.\nObjectives\nTo assess the efficacy and safety of surgical interventions for INS.\nSearch methods\nWe searched CENTRAL, MEDLINE Ovid, Embase Ovid, ISRCTN registry, ClinicalTrials.gov, and the World Health Organization (WHO) International Clinical Trials Registry Platform (ICTRP) to 3 July 2020, with no language restrictions.\nSelection criteria\nWe included randomised controlled trials (RCTs) studying the efficacy and safety of surgical options for treating INS.\nData collection and analysis\nOur prespecified outcome measures were the change from baseline in: binocular best-corrected distance visual acuity; head posture; amplitude, frequency, intensity, and foveation period durations of the nystagmus waveform; visual recognition times; quality of life and self-reported outcome measures; incidence of adverse effects with a probable causal link to treatment; and permanent adverse effects after surgery.\nTwo review authors independently screened titles and abstracts and full-text articles, extracted data from eligible RCTs, and judged the risk of bias using the Cochrane tool. We reached consensus on any disagreements by discussion. We summarised the overall certainty of the evidence using the GRADE approach.\nMain results\nWe only identified one eligible RCT (N = 10 participants), undertaken in India. This trial randomised participants to receive either a large retro-equatorial recession of the horizontal rectus muscle of 9 mm on the medial rectus and 12 mm on the lateral rectus, or a simple tenotomy and resuturing of the four horizontal rectus muscles. We did not identify any RCTs comparing a surgical intervention for INS relative to no treatment.\nIn the single eligible RCT, both eyes of each participant received the same intervention. The participants’ age and gender were not reported, nor was information on whether participants were idiopathic or had sensory disorders. The study only included participants with null in primary position and did not explicitly exclude those with congenital periodic alternating nystagmus. The study did not report funding source(s) or author declaration of interests. The evaluation period was six months.\nWe judged this study at low risk for sequence generation and other sources of bias, but at high risk of bias for performance and detection bias. The risk of bias was unclear for selection bias, attrition bias, and reporting bias.\nThere is very uncertain evidence about the effect of the interventions on visual acuity and change in amplitude, frequency, and intensity of the nystagmus waveform. We were unable to calculate relative effects due to lack of data. None of the participants in either intervention group reported adverse effects at six-month follow-up (very low-certainty evidence). There was no quantitative data reported for quality of life, although the study reported an improvement in quality of life after surgery in both intervention groups (very low-certainty evidence).\nChange in head posture, foveation period durations of the nystagmus waveform, visual recognition times, and permanent adverse effects after surgery were not reported in the included study.\nWe judged the certainty of the evidence, for both the primary and secondary efficacy outcomes, to be very low. Due to a lack of comprehensive reporting of adverse events, there was also very low-certainty of the safety profile of the evaluated surgical interventions in this population. As such, we are very uncertain about the relative efficacy and safety of these interventions for the surgical management of INS.\nAuthors' conclusions\nThis systematic review identified minimal high-quality evidence relating to the efficacy and safety of surgical interventions for INS. The limited availability of evidence must be considered by clinicians when treating INS, particularly given these procedures are irreversible and often performed on children. More high-quality RCTs are needed to better understand the efficacy and safety profile of surgical interventions for INS. This will assist clinicians, people with INS, and their parents or caregivers to make evidence-based treatment decisions.\n\nGiven the provided abstract, please respond to the following query: \"Why is this question important?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "Infantile nystagmus syndrome (INS) is an eye disorder that causes involuntary movement of the eyes from side to side, up and down, or in circles. INS typically develops shortly after birth, and persists throughout life. It is often associated with visual problems, such as:- long-sightedness (when people can see distant objects clearly, but near objects appear blurred);- or short-sightedness (when people can see near objects clearly, but distant objects appear blurred).\nThere is currently no cure for INS. However, it is possible to reduce eye movement and improve people’s vision. One of the main options is eye surgery, which involves operating on the muscles that control eye movement. Several different surgical procedures can be used: some procedures involve detaching and reattaching the eye muscles, whereas others require complete removal of these muscles.\nIt is unclear whether some surgical procedures for INS have more benefits or risks than others. To find out which surgical procedures work best, we reviewed the evidence from research studies. We were particularly interested in whether different surgical procedures could improve vision and quality of life in people with INS. We also wanted to know about any adverse (unwanted) effects." } ]

[ { "role": "user", "content": "Abstract: Background\nPostnatal depression is a common disorder that can have adverse short- and long-term effects on maternal morbidity, the new infant and the family as a whole. Treatment is often largely by social support and psychological interventions. It is not known whether antidepressants are an effective and safe choice for treatment of this disorder. This review was undertaken to evaluate the effectiveness of different antidepressants and to compare their effectiveness with other forms of treatment, placebo or treatment as usual. It is an update of a review first published in 2001.\nObjectives\nTo assess the effectiveness of antidepressant drugs in comparison with any other treatment (psychological, psychosocial or pharmacological), placebo or treatment as usual for postnatal depression.\nSearch methods\nWe searched the Cochrane Depression, Anxiety and Neurosis Group's Specialized Register (CCDANCTR) to 11 July 2014. This register contains reports of relevant randomised controlled trials (RCTs) from the following bibliographic databases: The Cochrane Library (all years), MEDLINE (1950 to date), EMBASE, (1974 to date) and PsycINFO (1967 to date). We also searched international trial registries and contacted pharmaceutical companies and experts in the field.\nSelection criteria\nWe included RCTs of women with depression with onset up to six months postpartum that compared antidepressant treatment (alone or in combination with another treatment) with any other treatment, placebo or treatment as usual.\nData collection and analysis\nTwo review authors independently extracted data from the trial reports. We requested missing information from investigators wherever possible. We sought data to allow an intention-to-treat analysis. Random effects meta-analyses were conducted to pool data where sufficient comparable studies were identified.\nMain results\nWe included six trials with 596 participants in this review. All studies had a randomised controlled parallel group design, with two conducted in the UK, three in the US and one in Israel. Meta-analyses were performed to pool data on response and remission from studies comparing antidepressants with placebo. No meta-analyses could be conducted for other comparisons due to the small number of trials identified.\nFour studies compared selective serotonin reuptake inhibitors (SSRIs) with placebo (two using sertraline, one using paroxetine and one using fluoxetine; 233 participants in total). In two of these studies both the experimental and placebo groups also received psychological therapy. Pooled risk ratios based on data from three of these studies (146 participants) showed that women randomised to SSRIs had higher rates of response and remission than those randomised to placebo (response: RR 1.43, 95% CI 1.01 to 2.03; remission: RR 1.79, 95% CI 1.08 to 2.98); the fourth study did not report data on response or remission.\nOne study (254 participants) compared antidepressant treatment with treatment as usual (for the first four weeks) followed by listening visits. The study found significantly higher rates of improvement in the antidepressant group than treatment-as-usual group after the first four weeks, but no difference between antidepressants and listening visits at the later follow-up. In addition, one study comparing sertraline with nortriptyline (a tricyclic antidepressant) found no difference in effectiveness (109 participants).\nSide effects were experienced by a substantial proportion of women, but there was no evidence of a meaningful difference in the number of adverse effects between treatment arms in any study. There were very limited data on adverse effects experienced by breastfed infants, with no long-term follow-up. All but one of the studies were assessed as being at high or uncertain risk of attrition bias and selective outcome reporting. In particular, one of the placebo-controlled studies had over 50% drop-out.\nAuthors' conclusions\nThe evidence base for this review was very limited, with a small number of studies and little information on a number of important outcomes, particularly regarding potential effects on the child. Risk of bias, for example from high attrition rates, as well as low representativeness of participants (e.g. exclusion of women with severe or chronic depression in several trials) also limit the conclusions that can be drawn.\nPooled estimates for response and remission found that SSRIs were significantly more effective than placebo for women with postnatal depression. However the quality of evidence contributing to this comparison was assessed as very low owing to the small sample size for this comparison (146 participants from three studies), the risk of bias in included studes and the inclusion of one study where all participants in both study arms additionally received psychological therapy. There was insufficient evidence to conclude whether, and for whom, antidepressant or psychological/psychosocial treatments are more effective, or whether some antidepressants are more effective or better tolerated than others. There is also inadequate evidence on whether the benefits of antidepressants persist beyond eight weeks or whether they have short- or long-term adverse effects on breastfeeding infants.\nProfessionals treating women with severe depression in the postnatal period will need to draw on other evidence, including trials among general adult populations and observational studies of antidepressant safety when breastfeeding (although the potential for confounding in non-randomised studies must be considered). More RCTs are needed with larger sample sizes and longer follow-up, including assessment of the impact on the child and safety of breastfeeding. Further larger-scale trials comparing antidepressants with alternative treatment modalities are also required.\n\nGiven the provided abstract, please respond to the following query: \"What questions does this review aim to answer?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "This review is an update of a previous Cochrane review from 2001, which found insufficient evidence to make conclusions about antidepressant treatment in postnatal depression. Therefore, this update aims to answer the following question:\nWhat are the effects of antidepressants in comparison with other any other treatment, placebo or treatment as usual for postnatal depression?" } ]

[ { "role": "user", "content": "Abstract: Background\nAsthma is a respiratory (airway) condition that affects an estimated 300 million people worldwide and is associated with significant morbidity and mortality. Omalizumab is a monoclonal antibody that binds and inhibits free serum immunoglobulin E (IgE). It is called an 'anti-IgE' drug. IgE is an immune mediator involved in clinical manifestations of asthma. A recent update of National Institute for Health and Care Excellence (NICE) guidance in 2013 recommends omalizumab for use as add-on therapy in adults and children over six years of age with inadequately controlled severe persistent allergic IgE-mediated asthma who require continuous or frequent treatment with oral corticosteroids.\nObjectives\nTo assess the effects of omalizumab versus placebo or conventional therapy for asthma in adults and children.\nSearch methods\nWe searched the Cochrane Airways Group Specialised Register of trials for potentially relevant studies. The most recent search was performed in June 2013. We also checked the reference lists of included trials and searched online trial registries and drug company websites.\nSelection criteria\nRandomised controlled trials examining anti-IgE administered in any manner for any duration. Trials with co-interventions were included, as long as they were the same in each arm.\nData collection and analysis\nTwo review authors independently assessed study quality and extracted and entered data. Three modes of administration were identified from the published literature: inhaled, intravenous and subcutaneous injection. The main focus of the updated review is subcutaneous administration, as this route is currently used in clinical practice. Subgroup analysis was performed by asthma severity. Data were extracted from published and unpublished sources.\nMain results\nIn all, 25 trials were included in the review, including 11 new studies since the last update, for a total of 19 that considered the efficacy of subcutaneous anti-IgE treatment as an adjunct to treatment with corticosteroids.\nFor participants with moderate or severe asthma who were receiving background inhaled corticosteroid steroid (ICS) therapy, a significant advantage favoured subcutaneous omalizumab with regard to experiencing an asthma exacerbation (odds ratio (OR) 0.55, 95% confidence interval (CI) 0.42 to 0.60; ten studies, 3261 participants). This represents an absolute reduction from 26% for participants suffering an exacerbation on placebo to 16% on omalizumab, over 16 to 60 weeks. A significant benefit was noted for subcutaneous omalizumab versus placebo with regard to reducing hospitalisations (OR 0.16, 95% CI 0.06 to 0.42; four studies, 1824 participants), representing an absolute reduction in risk from 3% with placebo to 0.5% with omalizumab over 28 to 60 weeks. No separate data on hospitalisations were available for the severe asthma subgroup, and all of these data were reported for participants with the diagnosis of moderate to severe asthma. Participants treated with subcutaneous omalizumab were also significantly more likely to be able to withdraw their ICS completely than those treated with placebo (OR 2.50, 95% CI 2.00 to 3.13), and a small but statistically significant reduction in daily inhaled steroid dose was reported for omalizumab-treated participants compared with those given placebo (weighted mean difference (WMD) -118 mcg beclomethasone dipropionate (BDP) equivalent per day, 95% CI -154 to -84). However, no significant difference between omalizumab and placebo treatment groups was seen in the number of participants who were able to withdraw from oral corticosteroid (OCS) therapy (OR 1.18, 95% CI 0.53 to 2.63).\nParticipants treated with subcutaneous omalizumab as an adjunct to treatment with corticosteroids required a small but significant reduction in rescue beta2-agonist medication compared with placebo (mean difference (MD) -0.39 puffs per day, 95% CI -0.55 to -0.24; nine studies, 3524 participants). This benefit was observed in both the moderate to severe (MD -0.58, 95% CI -0.84 to -0.31) and severe (MD -0.30, 95% CI -0.49 to -0.10) asthma subgroups on a background therapy of inhaled corticosteroids; however, no significant difference between subcutaneous omalizumab and placebo was noted for this outcome in participants with severe asthma who were receiving a background therapy of inhaled plus oral corticosteroids. Significantly fewer serious adverse events were reported in participants assigned to subcutaneous omalizumab than in those receiving placebo (OR 0.72, 95% CI 0.57 to 0.91; 15 studies, 5713 participants), but more injection site reactions were observed (from 5.6% with placebo to 9.1% with omalizumab).\nTo reflect current clinical practice, discussion of the results is limited to subcutaneous use, and trials involving intravenous and inhaled routes have been archived.\nAuthors' conclusions\nOmalizumab was effective in reducing asthma exacerbations and hospitalisations as an adjunctive therapy to inhaled steroids and during steroid tapering phases of clinical trials. Omalizumab was significantly more effective than placebo in increasing the numbers of participants who were able to reduce or withdraw their inhaled steroids. Omalizumab was generally well tolerated, although more injection site reactions were seen with omalizumab. Further assessment in paediatric populations is necessary, as is direct double-dummy comparison with ICS. Although subgroup analyses suggest that participants receiving prednisolone had better asthma control when they received omalizumab, it remains to be tested prospectively whether the addition of omalizumab has a prednisolone-sparing effect. It is also not clear whether there is a threshold level of baseline serum IgE for optimum efficacy of omalizumab. Given the high cost of the drug, identification of biomarkers predictive of response is of major importance for future research.\n\nGiven the provided abstract, please respond to the following query: \"Quality of the evidence\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "The evidence presented in this review is generally of moderate quality. Most of the studies did not clearly explain how investigators decided which people would receive omalizumab and which would receive placebo, and this decision is an important part of well-conducted studies." } ]

[ { "role": "user", "content": "Abstract: Background\nDespite the availability of several evidence-based therapies and non-pharmacological strategies to improve control of symptoms and prevent exacerbations of asthma, patients with asthma continue to be at risk for mortality and morbidity.\nPrevious trials have demonstrated the potentially beneficial effects of the long-acting muscarinic antagonist (LAMA) tiotropium on lung function in patients with asthma; however, a definitive conclusion on the benefit of LAMA in asthma is lacking, as is information on where in the current step-wise management strategy they would be most beneficial.\nObjectives\nTo assess the efficacy and safety of a LAMA added to any dose of an inhaled corticosteroid (ICS) compared with the same dose of ICS alone for adults whose asthma is not well controlled.\nSearch methods\nWe searched the Cochrane Airways Group Specialised Register (CAGR) from inception to April 2015, and we imposed no restriction on language of publication. We also searched clinicaltrials.gov, the World Health Organization (WHO) trials portal and drug company registries to identify unpublished studies.\nSelection criteria\nWe searched for parallel and cross-over randomised controlled trials in which adults whose asthma was not well controlled by ICS alone were randomly assigned to receive LAMA add-on or placebo (both combined with ICS) for at least 12 weeks.\nData collection and analysis\nTwo review authors independently screened the searches and extracted data from study reports. We used Covidence for duplicate screening, extraction of study characteristics and numerical data and risk of bias ratings. Pre-specified primary outcomes included exacerbations requiring oral corticosteroids, quality of life and all-cause serious adverse events.\nMain results\nWe identified five studies that met the inclusion criteria. All studies applied a double-blind, double-dummy design, and the population of all studies totalled 2563 adult participants. Study duration ranged from 12 weeks to 52 weeks, and risk of bias across domains in all studies was low. Trials included more women than men (33% to 47% male), and mean age of participants ranged from 41 to 48 years. Participants generally had a long history of asthma, and mean baseline predicted forced expiratory volume in one second (FEV1) was between 72% and 75% in three studies reporting pre-bronchodilator values.\nThe rate of exacerbations requiring oral corticosteroids (OCS) was lower in patients prescribed an LAMA add-on than in those receiving the same dose of ICS alone (odds ratio (OR) 0.65, 95% confidence interval (CI) 0.46 to 0.93; 2277 participants; four studies; I2 = 0%; high-quality evidence), meaning that 27 fewer people per 1000 would have an exacerbation over 21 weeks requiring OCS with LAMA compared with ICS alone (95% CI 42 fewer to 6 fewer).\nAll-cause serious adverse events (SAEs) and exacerbations requiring hospital admission were rare and the effects too imprecise to permit firm conclusions, but effects suggested that LAMA add-on may be associated with fewer of both compared with ICS alone (SAEs: OR 0.60, 95% CI 0.23 to 1.57; 2532 participants; four studies; low-quality evidence; exacerbations requiring hospital admission: OR 0.42, 95% CI 0.12 to 1.47; 2562 participants; five studies; moderate-quality evidence). Additional therapy with a LAMA showed no clear benefit in terms of quality of life compared with ICS given alone; high-quality evidence showed only a small mean improvement in quality of life as measured on the Asthma Quality of Life Questionnaire (AQLQ), which was not statistically significant. The same was true for asthma control as measured on the Asthma Control Questionnaire (ACQ), which was based on moderate-quality evidence. LAMA combined with ICS showed consistent benefit in a range of lung function measures compared with the same dose of ICS alone, and LAMA was not associated with significantly higher rates of adverse events than were reported with placebo.\nAuthors' conclusions\nFor adults taking ICS for asthma without a long-acting beta₂-agonist (LABA), LAMA given as add-on treatment reduces the likelihood of exacerbations requiring treatment with OCS and improves lung function. The benefits of LAMA combined with ICS for hospital admissions, all-cause serious adverse events, quality of life and asthma control remain unknown.\nResults of this review, along with findings of related reviews conducted to assess the use of LAMA in other clinical scenarios involving asthma, can help to define the role of LAMA in the management of asthma. Trials of longer duration (up to 52 weeks) would provide a better opportunity to observe rare events such as serious adverse events and exacerbations requiring hospital admission.\n\nGiven the provided abstract, please respond to the following query: \"Main point\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "People with poorly controlled asthma are less likely to have an asthma attack needing treatment with oral steroids if they take a LAMA on top of their inhaled steroid. LAMA also improve lung function compared with inhaled steroids alone, but their benefit is uncertain for hospital admissions, serious adverse events, quality of life and asthma control." } ]

[ { "role": "user", "content": "Abstract: Background\nThis an update of the review first published in 2009.\nMajor abdominal and pelvic surgery carries a high risk of venous thromboembolism (VTE). The efficacy of thromboprophylaxis with low molecular weight heparin (LMWH) administered during the in-hospital period is well-documented, but the optimal duration of prophylaxis after surgery remains controversial. Some studies suggest that patients undergoing major abdominopelvic surgery benefit from prolongation of the prophylaxis up to 28 days after surgery.\nObjectives\nTo evaluate the efficacy and safety of prolonged thromboprophylaxis with LMWH for at least 14 days after abdominal or pelvic surgery compared with thromboprophylaxis administered during the in-hospital period only in preventing late onset VTE.\nSearch methods\nWe performed electronic searches on 28 October 2017 in the Cochrane Central Register of Controlled Trials, MEDLINE, Embase, LILACS and registered trials (Clinicaltrials.gov October 28, 2017 and World Health Organization International Clinical Trials Registry Platform (ICTRP) 28 October 2017). Abstract books from major congresses addressing thromboembolism were handsearched from 1976 to 28 October 2017, as were reference lists from relevant studies.\nSelection criteria\nWe assessed randomized controlled clinical trials (RCTs) comparing prolonged thromboprophylaxis (≥ fourteen days) with any LMWH agent to thromboprophylaxis during the admission period only followed by placebo or no thromoprophylaxis after discharge. The population consisted of persons undergoing abdominal or pelvic surgery for both benign and malignant pathology. The outcome measures included VTE (deep venous thrombosis (DVT) or pulmonary embolism (PE)) as assessed by objective means (venography, ultrasonography, pulmonary ventilation/perfusion scintigraphy, spiral computed tomography (CT) scan or autopsy). We excluded studies exclusively reporting on clinical diagnosis of VTE without objective confirmation.\nData collection and analysis\nReview authors identified studies and extracted data. Outcomes were VTE (DVT or PE) assessed by objective means. Safety outcomes were defined as bleeding complications and mortality within three months after surgery. Sensitivity analyses were also performed with unpublished studies excluded, and with study participants limited to those undergoing solely open and not laparoscopic surgery. We used a fixed-effect model for analysis.\nMain results\nWe identified seven RCTs (1728 participants) evaluating prolonged thromboprophylaxis with LMWH compared with in-hospital thromoprophylaxis followed by placebo or no thromboprophylaxis after discharge. The searches resulted in 1632 studies, of which we excluded 1528. One hundred and four abstracts, eligible for inclusion, were assessed of which seven studies met the inclusion criteria.\nFor the primary outcome, the incidence of overall VTE after major abdominal or pelvic surgery was 13.2% in the control group compared to 5.3% in the patients receiving out-of-hospital LMWH (Mantel Haentzel (M-H) odds ratio (OR) 0.38, 95% confidence interval (CI) 0.26 to 0.54; I2 = 28%; moderate-quality evidence).\nFor the secondary outcome of all DVT, seven studies, n = 1728, showed prolonged thromboprophylaxis with LMWH to be associated with a statistically significant reduction in the incidence of all DVT (M-H OR 0.39, 95% CI 0.27 to 0.55; I2 = 28%; moderate-quality evidence).\nWe found a similar reduction when analysis was limited to incidence in proximal DVT (M-H OR 0.22, 95% CI 0.10 to 0.47; I2 = 0%; moderate-quality evidence).\nThe incidence of symptomatic VTE was also reduced from 1.0% in the control group to 0.1% in patients receiving prolonged thromboprophylaxis, which approached significance (M-H OR 0.30, 95% CI 0.08 to 1.11; I2 = 0%; moderate-quality evidence).\nNo difference in the incidence of bleeding between the control and LMWH group was found, 2.8% and 3.4%, respectively (M-H OR 1.10, 95% CI 0.67 to 1.81; I2 = 0%; moderate-quality evidence).\nNo difference in mortality between the control and LMWH group was found, 3.8% and 3.9%, respectively (M-H OR 1.15, 95% CI 0.72 to 1.84; moderate-quality evidence).\nEstimates of heterogeneity ranged between 0% and 28% depending on the analysis, suggesting low or unimportant heterogeneity.\nAuthors' conclusions\nProlonged thromboprophylaxis with LMWH significantly reduces the risk of VTE compared to thromboprophylaxis during hospital admittance only, without increasing bleeding complications or mortality after major abdominal or pelvic surgery. This finding also holds true for DVT alone, and for both proximal and symptomatic DVT. The quality of the evidence is moderate and provides moderate support for routine use of prolonged thromboprophylaxis. Given the low heterogeneity between studies and the consistent and moderate evidence of a decrease in risk for VTE, our findings suggest that additional studies may help refine the degree of risk reduction but would be unlikely to significantly influence these findings. This updated review provides additional evidence and supports the previous results reported in the 2009 review.\n\nGiven the provided abstract, please respond to the following query: \"Review question\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "For persons having surgery on the abdomen and pelvis, does continuing blood thinner injections after discharge from a hospital stay decrease the likelihood of developing a blood clot in the lower limbs or lungs when compared to usual treatment in the hospital?" } ]

[ { "role": "user", "content": "Abstract: Background\nDiabetic retinopathy is one of the major causes of blindness and the number of cases has risen in recent years. Herbal medicine has been used to treat diabetes and its complications including diabetic retinopathy for thousands of years around the world. However, common practice is not always evidence-based. Evidence is needed to help people with diabetic retinopathy or doctors to make judicious judgements about using herbal medicine as treatment.\nObjectives\nTo evaluate the effectiveness and harm of single herbal medicine for diabetic retinopathy.\nSearch methods\nWe searched CENTRAL, which contains the Cochrane Eyes and Vision Trials Register, MEDLINE, Embase, OpenGrey, the ISRCTN registry, ClinicalTrials.gov and the ICTRP. The date of the search was 12 June 2018. We also searched the following Chinese databases in June 2013: Chinese BioMedical Literature Database (CBM), Traditional Chinese Medical Literature Analysis and Retrieval System (TCMLARS), Wanfang China Dissertation Database (CDDB), Wanfang China Conference Paper Database (CCPD) and the Index to Chinese Periodical Literature.\nSelection criteria\nWe included randomised controlled trials (RCTs) and quasi-RCTs that investigated the effects of any single herb (or extracts from a single herb) as a treatment for people with diabetic retinopathy. We considered the following comparators: placebo, no treatment, non-herbal (conventional) medicine or surgical treatment.\nData collection and analysis\nTwo review authors independently extracted data and assessed the risk of bias in the studies. Our prespecified outcomes were: progression of diabetic retinopathy, visual acuity, microaneurysms and haemorrhages in the retina, blood glycated haemoglobin A1c (HbA1c) (%) and adverse effects. We performed meta-analyses using risk ratios (RR) for dichotomous outcomes and mean differences (MD) for continuous outcomes, with 95% confidence intervals (CI). We assessed the certainty of the evidence using GRADE.\nMain results\nWe included 10 studies involving 754 participants, of which nine were conducted in China and one in Poland. In all studies, participants in both groups received conventional treatment for diabetic retinopathy which included maintaining blood glucose and lipids using medicines and keeping a stable diabetic diet. In three studies, the comparator group also received an additional potentially active comparator in the form of a vasoprotective drug. The single herbs or extracts included Ruscus extract tablet, Sanqi Tongshu capsule, tetramethylpyrazine injection, Xueshuantong injection, Puerarin injection and Xuesaitong injection. The Sanqi Tongshu capsule, Xueshuantong injection and Xuesaitong injection were all made from the extract of Radix Notoginseng (San qi) and the main ingredient was sanchinoside. The risk of bias was high in all included studies mainly due to lack of masking (blinding). None of the studies reported the primary outcome of this review, progression of retinopathy.\nCombined analysis of herbal interventions suggested that people who took these herbs in combination with conventional treatment may have been more likely to gain 2 or more lines of visual acuity compared to people who did not take these herbs when compared to conventional intervention alone at the end of treatment (RR 1.26, 95% CI 1.08 to 1.48; 5 trials, 541 participants; low-certainty evidence). Subgroup analyses based on the different single herbs found no evidence for different effects of different herbs, but the power of this analysis was low. One study reported Sanqi Tongshu capsule might be associated with a greater reduction in microaneurysms and haemorrhages in the retina (very low-certainty evidence). The pooled analysis of two studies on tetramethylpyrazine or Xueshuantong injection showed such herbs may have had little effect on lowering HbA1c (MD 0.00, 95% CI -0.58 to 0.58; 215 participants; low-certainty evidence).\nThere was very low-certainty evidence on adverse events. Two studies reported minor adverse events such as uncomfortable stomach, urticaria, dizziness and headache. There was no report of observation on adverse events in the other studies.\nAuthors' conclusions\nNo conclusions could be drawn about the effect of any single herb or herbal extract on diabetic retinopathy from the current available evidence. It was difficult to exclude the placebo effect as a possible explanation for observed differences due to the lack of placebo control in the included studies. Further adequately designed trials are needed to establish the evidence.\n\nGiven the provided abstract, please respond to the following query: \"What was the aim of this review?\". Use language that can be easily comprehended by individuals without domain knowledge:\n" }, { "role": "assistant", "content": "The aim of this Cochrane Review was to find out if herbal medicine is useful for people with diabetic retinopathy when compared with placebo, no treatment, non-herbal (conventional) medicine or surgical treatment. Cochrane researchers collected and analysed all relevant studies to answer this question and found 10 studies." } ]