Datasets:

---

clinicalnlplab

/

CochranePLS_train

like 0

Follow

Clinical NLP Lab 28

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: The five trials that met our criteria included 698 patients: data from 499 (71.5%) were available for analysis of relapse frequency at one year's, from 488 (70%) at two years' and from 415 (59.5%) at three years' follow-up. Azathioprine reduced the number of patients who had relapses during the first year of treatment (relative risk reduction [RRR] =20%; 95% CI = 5% to 33%), at two years' (RRR =23%; 95% CI = 12% to 33%) and three years' (RRR =18%; 95% CI = 7% to 27%) follow-up. These results were consistent in sensitivity analysis. There was no heterogeneity among the studies. Data from only three small trials with a total of 87 patients were available to calculate the number of patients who progressed during the first two to three years. There was a statistically significant benefit (RRR = 42%; 95% CI = 7% to 64%) of azathioprine therapy at three years' follow-up; this result was robust after sensitivity analyses and there was no heterogeneity among the trials. Gastrointestinal disturbances, bone marrow suppression and hepatic toxicity were greater in the azathioprine group rather than in the placebo group; they were anticipated, and, by monitoring and dosage adjustment, were easily managed. Withdrawals due to adverse effects were few, occurring mostly during the first year of azathioprine treatment and mainly due to gastrointestinal intolerance (5%). Data from the trials and from cohort and case controls studies available in the literature did not show an increase in risk of malignancy from azathioprine. A possible long-term risk of cancer from azathioprine may be related to a treatment duration above ten years and cumulative doses above 600 g. Azathioprine is an appropriate maintenance treatment for patients with MS who frequently relapse and require steroids. Cumulative doses of 600 g should not be exceeded in relation to a possible increased risk of malignancy. Considering the trade off between the benefits and harms, azathioprine is a fair alternative to interferon beta for treating MS. A logical next step for future trials would seem the direct comparison of azathioprine and interferon beta. In fact the direct comparison between these two widely used treatments in MS has not been made.\nOutput:\n" }, { "from": "agent", "value": "Two studies had deaths reported, comprising of four persons in the control group, and eight in the AZA group. These small numbers do not allow a statistical analysis. Conflicting conclusions on potential risk of cancer in MS patients with long-term AZA treatment have been reported in eight published papers, not considered in the present review because they came from sources other than clinical trials. The presence of patients who developed cancer ( three in the AZA and 1 the placebo group) was reported in two out of five studies considered in this review. Numerous studies of AZA treated patient populations other than MS patients are also available. The whole data, however, does not show an increase in risk of malignancy from AZA. Possible long-term risks may be related to a treatment duration above ten years and cumulative doses above 600 g." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included six studies with a total of 438 participants. Five studies were conducted in the USA, and one in Iran. All studies evaluated a long-acting version of bupropion, with the dosage ranging from 150 mg up to 450 mg daily. Study intervention length varied from six to 10 weeks. Four studies explicitly excluded participants with psychiatric comorbidity and one study included only participants with opioid dependency. Four studies were funded by industry, but the impact of this on study results is unknown. Two studies were publicly funded and in one of these studies, the lead author was a consultant for several pharmaceutical companies and also received investigator-driven funding from two companies, however none of these companies manufacture bupropion. We judged none of the studies to be free of bias because for most risk of bias domains the study reports failed to provide sufficient details. Using the GRADE approach, we rated the overall quality of evidence as low. We downgraded the quality of the evidence because of serious risk of bias and serious imprecision due to small sample sizes. We found low-quality evidence that bupropion decreased the severity of ADHD symptoms (standardised mean difference -0.50, 95% confidence interval (CI) -0.86 to -0.15, 3 studies, 129 participants), and increased the proportion of participants achieving clinical improvement (risk ratio (RR) 1.50, 95% CI 1.13 to 1.99, 4 studies, 315 participants), and reporting an improvement on the Clinical Global Impression - Improvement scale (RR 1.78, 95% CI 1.27 to 2.50, 5 studies, 337 participants). There was low-quality evidence that the proportion of participants who withdrew due to any adverse effect was similar in the bupropion and placebo groups (RR 1.20, 95% CI 0.35 to 4.10, 3 studies, 253 participants). The results were very similar when using a random-effects model and when we analysed only studies that excluded participants with a psychiatric comorbidity. The findings of this review, which compared bupropion to placebo for adult ADHD, indicate a possible benefit of bupropion. We found low-quality evidence that bupropion decreased the severity of ADHD symptoms and moderately increased the proportion of participants achieving a significant clinical improvement in ADHD symptoms. Furthermore, we found low-quality evidence that the tolerability of bupropion is similar to that of placebo. In the pharmacological treatment of adults with ADHD, extended- or sustained-release bupropion may be an alternative to stimulants. The low-quality evidence indicates uncertainty with respect to the pooled effect estimates. Further research is very likely to change these estimates. More research is needed to reach more definite conclusions as well as clarifying the optimal target population for this medicine. Treatment response remains to be reported in a DSM5-diagnosed population. There is also a lack of knowledge on long-term outcomes.\nOutput:\n" }, { "from": "agent", "value": "We included six randomised controlled trials (RCTs), that is, studies in which participants are randomly allocated to one of two or more treatment groups. Five of the studies took place in the USA, and the sixth in Iran. The studies included 438 people with ADHD. All evaluated a long-acting version of bupropion, that is to say, a version of the drug is absorbed slowly, and can therefore be taken just once a day. This simple dosage suits people with ADHD, as the illness may make it difficult for them to remember to take their medication. The duration of the studies varied between six and 10 weeks. All participants were diagnosed with ADHD, and often had other mental health problems. In one study, all participants had ADHD and were addicted to opioids (a drug that relieves pain). Four studies were funded by industry and two studies were publicly funded. In one of the publicly-funded studies, the lead author was paid by industry (although not by the manufacturers of buproprion) for research activities. Bupropion may lead to a small improvement in ADHD and it may also decrease symptoms related to ADHD. The drug does not have more adverse effects than treatment with placebo. Bupropion may be an alternative treatment for adults with ADHD who cannot or will not take stimulant drugs. The quality of the evidence in this review is low, because we found very few studies; five of the six studies were small, and all were poorly conducted. The effect of bupropion on various aspects of daily functioning was not investigated. Also, no studies assessed the long-term effects of this drug. Further studies are needed, to assess whether bupropion is effective in specific ADHD subgroups or in people who have additional disorders." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: 24 RCTs with 6915 participants fulfilled the criteria of inclusion and were included in the review. Compared to placebo, acamprosate was shown to significantly reduce the risk of any drinking RR 0.86 (95% CI 0.81 to 0.91); NNT 9.09 (95% CI 6.66 to 14.28) and to significantly increase the cumulative abstinence duration MD 10.94 (95% CI 5.08 to 16.81), while secondary outcomes (gamma-glutamyltransferase, heavy drinking) did not reach statistical significance. Diarrhea was the only side effect that was more frequently reported under acamprosate than placebo RD 0.11 (95% 0.09 to 0.13); NNTB 9.09 (95% CI 7.69 to 11.11). Effects of industry-sponsored trials RR 0.88 (95% 0.80 to 0.97) did not significantly differ from those of non-profit funded trials RR 0.88 (95% CI 0.81 to 0.96). In addition, the linear regression test did not indicate a significant risk of publication bias (p = 0.861). Acamprosate appears to be an effective and safe treatment strategy for supporting continuous abstinence after detoxification in alcohol dependent patients. Even though the sizes of treatment effects appear to be rather moderate in their magnitude, they should be valued against the background of the relapsing nature of alcoholism and the limited therapeutic options currently available for its treatment.\nOutput:\n" }, { "from": "agent", "value": "These conclusions are based on 24 randomised controlled trials with 6915 participants who were treated as outpatients in all but one trial that involved adolescent inpatients. The majority of participants were men, median age 42 years. Most studies were conducted in Europe; two studies were conducted in the United States and one study in each of South Korea,Australia and Brazil. The effects of acamprosate did not differ in industry-sponsored and non-profit funded trials. Three trials compared acamprosate and naltrexone and did not indicate a superiority of one or the other drug on return to any drinking, return to heavy drinking and cumulative abstinence duration." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included 12 studies (784 participants) in this review; sample sizes ranged from 10 to 187 participants (median 56.5). One study had three arms that were all relevant to this review and all the other studies had two arms. One study was a within-participant comparison. All studies were industry funded. Two studies provided unpublished data for healing. Nine of the included studies compared PMM treatments with other treatments and reported results for the primary outcomes. All treatments were dressings. All studies also gave the participants compression bandaging. Seven of these studies were in participants described as having 'non-responsive' or 'hard-to-heal' ulcers. Results, reported at short, medium and long durations and as time-to-event data, are summarised for the comparison of any dressing regimen incorporating PMM versus any other dressing regimen. The majority of the evidence was of low or very low certainty, and was mainly downgraded for risk of bias and imprecision. It is uncertain whether PMM dressing regimens heal VLUs quicker than non-PMM dressing regimens (low-certainty evidence from 1 trial with 100 participants) (HR 1.21, 95% CI 0.74 to 1.97). In the short term (four to eight weeks) it is unclear whether there is a difference between PMM dressing regimens and non-PMM dressing regimens in the probability of healing (very low-certainty evidence, 2 trials involving 207 participants). In the medium term (12 weeks), it is unclear whether PMM dressing regimens increase the probability of healing compared with non-PMM dressing regimens (low-certainty evidence from 4 trials with 192 participants) (RR 1.28, 95% CI 0.95 to 1.71). Over the longer term (6 months), it is also unclear whether there is a difference between PMM dressing regimens and non-PMM dressing regimens in the probability of healing (low certainty evidence, 1 trial, 100 participants) (RR 1.06, 95% CI 0.80 to 1.41). It is uncertain whether there is a difference in adverse events between PMM dressing regimens and non-PMM dressing regimens (low-certainty evidence from 5 trials, 363 participants) (RR 1.03, 95% CI 0.75 to 1.42). It is also unclear whether resource use is lower for PMM dressing regimens (low-certainty evidence, 1 trial involving 73 participants), or whether mean total costs in a German healthcare setting are different (low-certainty evidence, 1 trial in 187 participants). One cost-effectiveness analysis was not included because effectiveness was not based on complete healing. The evidence is generally of low certainty, particularly because of risk of bias and imprecision of effects. Within these limitations, we are unclear whether PMM dressing regimens influence venous ulcer healing relative to dressing regimens without PMM activity. It is also unclear whether there is a difference in rates of adverse events between PMM and non-PMM treatments. It is uncertain whether either resource use (products and staff time) or total costs associated with PMM dressing regimens are different from those for non-PMM dressing regimens. More research is needed to clarify the impact of PMM treatments on venous ulcer healing.\nOutput:\n" }, { "from": "agent", "value": "In September 2016 we searched for as many relevant studies as we could find that had a reliable design (randomised controlled trials) and had compared PMM treatments with other treatments for venous leg ulcers. We found 12 studies involving a total of 784 people. Ten studies gave results we could use and all treatments were dressings. All these studies gave all the participants compression therapy as well as the dressings. Most of the people in the trials had wounds that were not getting better or had been there a long time. Findings from four trials are unclear as to whether there is a benefit of PMM dressings on venous ulcer healing compared with other dressings. Five trials reported on wound side effects and their results are unclear as to whether there is a difference in rates of side effects between PMM dressings and other dressings. It is also unclear whether PMM dressings result in decreases in the amount of saline used and the time taken during dressing changes, and whether there is an effect on total costs. Overall, the certainty of the evidence was judged to be low: most studies we found were small and could have been better conducted, so it was difficult to be sure how meaningful the results were. The next step would be to do more research of better quality to see whether PMM dressings do heal venous ulcers more quickly than other dressings. This plain language summary is up to date as of September 2016." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We identified 6600 references (4647 references in our initial review) and included 10 trials (3575 participants). Follow-up ranged from 30 days to one year. Nine trials provided mortality data (3218 participants, 466 events), with a risk ratio of 1.02 (95% CI 0.87 to 1.19) (low-certainty evidence). Seven trials provided hospital readmission data (2843 participants, 1043 events) with a risk ratio of 0.95 (95% CI 0.87 to 1.04) (high-certainty evidence). Four trials provided emergency department contact data (1442 participants, 244 events) with a risk ratio of 0.73 (95% CI 0.52 to 1.03) (low-certainty evidence). The estimated reduction in emergency department contacts of 27% (with a CI ranging from 48% reduction to 3% increase in contacts) corresponds to a number needed to treat for an additional beneficial outcome of 37 for a low-risk population and 12 for a high-risk population over one year. Subgroup and sensitivity analyses did not significantly alter our results. We found no evidence that medication review reduces mortality or hospital readmissions, although we did find evidence that medication review may reduce emergency department contacts. However, because of short follow-up ranging from 30 days to one year, important treatment effects may have been overlooked. High-quality trials with long-term follow-up (i.e. at least up to a year) are needed to provide more definitive evidence for the effect of medication review on clinically important outcomes such as mortality, readmissions and emergency department contacts, and on outcomes such as adverse events. Therefore, if used in clinical practice, medication reviews should be undertaken as part of a clinical trial with long-term follow-up.\nOutput:\n" }, { "from": "agent", "value": "We included 10 randomised controlled trials with a total of 3575 participants. We found that medication review does not seem to prevent death and hospital readmissions, but that it might reduce emergency department contacts. Our confidence in results across studies ranged from low to high. We found no evidence that medication review in hospitalised patients makes a difference towards preventing mortality (low-certainty evidence) or hospital readmissions (high-certainty evidence), but we found that medication review may have a preventive effect on reducing the number of emergency department contacts (low-certainty evidence). In the included trials, participants were followed for a short time (ranging from 30 days to one year). Therefore, important long-term treatment effects may have been overlooked. We suggest that further research with long-term patient follow-up and examination of specific methods of medication review should be undertaken before this intervention is implemented in clinical practice." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: The review included 27 studies reported in 30 articles. The studies had 73,557 participants with 12 studies from the US; four from China; two from each of Australia, Canada, the Netherlands and the UK; and one from each of Israel, Greece and Brazil. Thirteen studies were RCTs, six were non-RCTs and eight were CBAs. Of the included studies, 18 provided some element of the intervention in children aged four to 11 years, 17 studies included children aged 11 to 14 years and nine studies included children aged 14 to 18 years. The overall quality of the results was poor, with the all studies assessed as being at high or unclear risks of bias across multiple domains, and varied interventions and data collection methods employed. Interventions comprised information-giving, peer education or were multi-component. Seven studies reported the primary outcome of injury occurrence and only three of these were similar enough to combine in a meta-analysis, with a pooled incidence rate ratio of 0.73 (95% confidence interval (CI) 0.49 to 1.08; 2073 children) and substantial statistical heterogeneity (I2 = 63%). However, this body of evidence was low certainty, due to concerns over this heterogeneity (inconsistency) and imprecision. This heterogeneity may be explained by the non-RCT study design of one of the studies, as a sensitivity analysis with this study removed found stronger evidence of an effect and no heterogeneity (I2 = 0%). Two studies report an improvement in safety skills in the intervention group. Likewise, the four studies measuring observed safety behaviour reported an improvement in the intervention group relative to the control. Thirteen out of 19 studies describing self-reported behaviour and safety practices showed improvements, and of the 21 studies assessing changes in safety knowledge, 19 reported an improvement in at least one question domain in the intervention compared to the control group. However, we were unable to pool data for our secondary outcomes, so our conclusions were limited, as they were drawn from highly diverse single studies and the body of evidence was low (safety skills) or very low (behaviour, safety knowledge) certainty. Only one study reported intervention costs but did not undertake a full economic evaluation (very low certainty evidence). There is insufficient evidence to determine whether school-based educational programmes can prevent unintentional injuries. More high-quality studies are needed to evaluate the impact of educational programmes on injury occurrence. There is some weak evidence that such programmes improve safety skills, behaviour/practices and knowledge, although the evidence was of low or very low quality certainty. We found insufficient economic studies to assess cost-effectiveness.\nOutput:\n" }, { "from": "agent", "value": "The evidence is current to June 2015. It includes the results from 27 studies of 73,557 children. It included boys and girls aged four to 18. The studies compared injury prevention education with either the usual curriculum or an alternative programme unrelated to injuries. The studies we included were aimed at preventing a range of injuries. We excluded programmes that focused on just one cause of injury. The review measured the effects of the educational programmes on the occurrence of injuries in children, their safety skills, behaviour and knowledge. The review also looked at whether school-based approaches are good value for money. Only a few studies reported the effect on injury occurrence in children and so these effects were inconclusive. This does not mean that school-based programmes are ineffective but rather that more evidence is needed. The review did find evidence that school-based injury prevention education programmes can improve children's safety skills, safety behaviours and safety knowledge. However, the evidence was inconsistent, with some studies showing a positive effect and others showing no effect. Only one study reported on how cost-effective school-based programmes were and so again it is difficult to draw conclusions from this evidence alone. The studies were generally of poor quality for all the measurements of effectiveness of the programmes but particularly for behaviour and knowledge. This is because information about how the study was conducted was not usually reported very clearly in the study reports or there were major flaws in the way that the studies were undertaken. More research is needed that is of higher quality." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We 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. The 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. Nerve-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.\nOutput:\n" }, { "from": "agent", "value": "We found four small studies that compared nerve-sparing radical hysterectomy versus standard radical hysterectomy. None of the included studies reported data on overall survival and rate of intermittent self-catheterisation (procedure in which patient periodically inserts a small tube (catheter) through the urethra into the bladder to empty it of urine) over one month following surgery. We could not assess the relative effect of these two operations on quality of life due to inconsistent data reported. Women undergoing nerve-sparing radical hysterectomy had better voiding (a technique of bladder training in which the woman is instructed to urinate according to pre-determined schedules) functions following surgery than those undergoing standard radical hysterectomy. We found no evidence that women undergoing nerve-sparing radical hysterectomy were more likely to have adverse consequences of surgery or relapse of their cancer. The certainty of the evidence is therefore low or very low. Nerve-sparing radical hysterectomy may reduce the chance of bladder dysfunction compared to standard radical hysterectomy. However, the certainty of this evidence is low and further studies have the potential to better inform this outcome. We are very uncertain as to whether nerve-sparing radical hysterectomy is safe in terms of cancer survival outcomes. The evidence of cancer recurrence was of very low-certainty, there were no long term data available regarding risk of death from cancer or other causes. High-quality international studies involving many women would be needed to tell us whether nerve-sparing radical hysterectomy is beneficial in terms of survival for women with early stage cervical cancer, since risk of recurrence in this group are low." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included one study that analysed 185 participants. The study compared the effects of a clinical examination every 12 months with a clinical examination every 24 months on the outcomes of caries (decayed, missing, filled surfaces (dmfs/DMFS) increment) and economic cost outcomes (total time used per person). As the study was at high risk of bias, had a small sample size and only included low-risk participants, we rated the quality of the body of evidence for these outcomes as very low. For three to five-year olds with primary teeth, the mean difference (MD) in dmfs increment was -0.90 (95% CI -1.96 to 0.16) in favour of 12-month recall. For 16 to 20-year olds with permanent teeth, the MD in DMFS increment was -0.86 (95% CI -1.75 to 0.03) also in favour of 12-month recall. There is insufficient evidence to determine whether 12 or 24-month recall with clinical examination results in better caries outcomes. For three to five-year olds with primary teeth, the MD in time used by each participant was 10 minutes (95% CI -6.7 to 26.7) in favour of 24-month recall. For 16 to 20-year olds with permanent teeth, the MD was 23.7 minutes (95% CI 4.12 to 43.28) also in favour of 24-month recall. This single study at high risk of bias represents insufficient evidence to determine whether 12 or 24-month recall with clinical examination results in better time/cost outcomes. There is a very low quality body of evidence from one RCT which is insufficient to draw any conclusions regarding the potential beneficial and harmful effects of altering the recall interval between dental check-ups. There is no evidence to support or refute the practice of encouraging patients to attend for dental check-ups at six-monthly intervals. It is important that high quality RCTs are conducted for the outcomes listed in this review in order to address the objectives of this review.\nOutput:\n" }, { "from": "agent", "value": "The Cochrane Oral Health Group carried out this review of existing studies, which includes evidence current up to 27 September 2013. This review includes one published study in which a total of 185 children and young adults were randomly chosen to have a clinical examination every 12 months or every 24 months. The study measured what effects the two different check-up times had on tooth decay and total time used per person (which could then be used to measure costs to the healthcare system). The limited results did not enable a conclusion to be made about whether or not extending the time to the next dental check-up can reduce tooth decay or costs. The evidence presented is of very low quality due to there only being one study and issues with the way it was conducted." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: This update included three new studies, providing a 26% increase in participants in comparisons between diclofenac and placebo. We included 18 studies involving 3714 participants, 1902 treated with diclofenac and 1007 with placebo. This update has also changed the focus of the review, examining the effects of formulation in more detail than previously. This is a result of increased understanding of the importance of speed of onset in determining analgesic efficacy in acute pain. The largest body of information, for diclofenac potassium 50 mg, in seven studies, produced an NNT for at least 50% of maximum pain relief compared with placebo of 2.1 (95% confidence interval (CI) 1.9 to 2.5) (high quality evidence). There was a graded improvement in efficacy as doses rose from 25 mg to 100 mg, both for participants achieving at least 50% maximum pain relief, and for remedication within 6 to 8 hours. Fast-acting formulations (dispersible products, solutions, and softgel formulations) had a similar efficacy for a 50 mg dose, with an NNT of 2.4 (2.0 to 3.0). Diclofenac sodium in a small number of studies produced a lesser effect, with an NNT of 6.6 (4.1 to 17) for the 50 mg dose. Adverse event rates were low in these single dose studies, with no difference between diclofenac and placebo (moderate quality evidence). Diclofenac potassium provides good pain relief at 25 mg, 50 mg, and 100 mg doses. Diclofenac sodium has limited efficacy and should probably not be used in acute pain.\nOutput:\n" }, { "from": "agent", "value": "This is an update of a review published in 2009. New searches in March 2015 identified three new studies, making 18 studies with 3714 participants altogether, 1902 of whom were treated with diclofenac and 1007 with placebo. Diclofenac potassium is a rapidly absorbed formulation, and the 50 mg dose provided the largest amount on information. With this dose of this formulation, more than 6 in 10 (64%) participants had effective pain relief, compared with fewer than 2 in 10 (17%) with placebo (high quality evidence). Adverse events occurred at similar rates with diclofenac and placebo in these single dose studies (moderate quality evidence). There were few serious adverse events or withdrawals due to adverse events. Diclofenac potassium represents a useful option in controlling acute pain." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Seven studies mostly with small sample sizes, comparing 4 different interventions (prostaglandins alone, mifepristone alone, and mifepristone/misoprostol and methotrexate/misoprostol versus vacuum aspiration) were included. Results are sometimes based on one trial only. Prostaglandins vs vacuum aspiration: the rate of abortions not completed with the intended method was statistically significant higher in the prostaglandin group (2.7, 95% CI 1.1 to 6.8) compared to surgery. There are no data on the most commonly medical (mifepristone/misoprostol) and surgical abortion available to be included in the review. Duration of bleeding was longer in the medical abortion groups compared to vacuum aspiration. There was only one major complication (uterine perforation) in one trial in the surgical group. There was no difference between the groups for ongoing pregnancies at the time of follow-up or pelvic infections. No data on acceptability, side effects or women's satisfaction with the procedure were availbale for inclusion in the review. The results are derived from relatively small trials. Prostaglandins used alone seems to be less effective and more painful compared to surgical first-trimester abortion. However, there is inadequate evidence to comment on the acceptability and side effects of medical compared to surgical first-trimester abortions. There is a need for trials to address the efficacy of currently used methods and women's preferences more reliably.\nOutput:\n" }, { "from": "agent", "value": "The review of trials found that medical methods for abortion in early pregnancy can be safe and effective, with the most evidence of effectiveness for a combination of mifepristone and misoprostol (a prostaglandin). Almost all of the trials were done in well-resourced hospitals where women returned for check-up." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included 6 studies (2 full reports, 2 abstracts, 1 brief communication, and 1 letter), with a total of 544 participants. Risk of bias was unclear in several studies because of insufficient reporting. Five studies compared FAE with placebo, and one study compared FAE with methotrexate. All studies reported data at 12 to 16 weeks, and we identified no longer-term studies. When FAE were compared with placebo, we could not perform meta-analysis for the primary outcome of PASI score because the three studies that assessed this outcome reported the data differently, although all studies reported a significant reduction in PASI scores with FAE. Only 1 small study designed for psoriatic arthritis reported on the other primary outcome of participants discontinuing treatment due to adverse effects (2 of 13 participants on FAE compared with none of the 14 participants on placebo; risk ratio (RR) 5.36, 95% confidence interval (CI) 0.28 to 102.1; 27 participants; very low-quality evidence). However, these findings are uncertain due to indirectness and a very wide confidence interval. Two studies, containing 247 participants and both only reported as abstracts, allowed meta-analysis for PASI 50, which showed superiority of FAE over placebo (RR 4.55, 95% CI 2.80 to 7.40; low-quality evidence), with a combined PASI 50 of 64% in those given FAE compared with a PASI 50 of 14% for those on placebo, representing a number needed to treat to benefit of 2. The same studies reported more participants achieving PASI 75 with FAE, but we did not pool the data because of significant heterogeneity; none of the studies measured PASI 90. One study reported significant improvement in participants' quality of life (QoL) with FAE, measured with Skindex-29. However, we could not compute the mean difference because of insufficient reporting in the abstract. More participants experienced adverse effects, mainly gastrointestinal disturbance and flushing, on FAE (RR 4.72, 95% CI 2.45 to 9.08; 1 study, 99 participants; moderate-quality evidence), affecting 76% of participants given FAE and 16% of the placebo group (representing a number needed to treat to harm of 2). The other studies reported similar findings or did not report adverse effects fully. One study of 54 participants compared methotrexate (MTX) with FAE. PASI score at follow-up showed superiority of MTX (mean Difference (MD) 3.80, 95% CI 0.68 to 6.92; 51 participants; very low-quality evidence), but the difference was not significant after adjustment for baseline disease severity. The difference between groups for the proportion of participants who discontinued treatment due to adverse effects was uncertain because of imprecision (RR 0.19, 95% CI 0.02 to 1.53; 1 study, 51 participants; very low-quality evidence). Overall, the number of participants experiencing common nuisance adverse effects was not significantly different between the 2 groups, with 89% of the FAE group affected compared with 100% of the MTX group (RR 0.89, 95% CI 0.77 to 1.03; 54 participants; very low-quality evidence). Flushing was more frequent in those on FAE, with 13 out of 27 participants affected compared with 2 out of 27 given MTX. There was no significant difference in the number of participants who attained PASI 50, 75, and 90 in the 2 groups (very low-quality evidence) whereas this study did not measure the effect of treatments on QoL. The included studies reported no serious adverse effects of FAE and were too small and of limited duration to provide evidence about rare or delayed effects. Evidence suggests that FAE are superior to placebo and possibly similar in efficacy to MTX for psoriasis; however, the evidence provided in this review was limited, and it must be noted that four out of six included studies were abstracts or brief reports, restricting study reporting. FAE are associated with nuisance adverse effects, including flushing and gastrointestinal disturbance, but short-term studies reported no serious adverse effects.\nOutput:\n" }, { "from": "agent", "value": "Our review included six randomised control trials (RCTs) that involved 544 participants. Five RCTs compared FAE with placebo, and one compared FAE with methotrexate. The outcomes we were interested in measuring were the Psoriasis Area and Severity Index (PASI), which is a psoriasis severity score, and the proportion of participants who discontinued treatment because of adverse (side) effects that are common but sufficiently serious that the drug had to be stopped, such as severe diarrhoea, infections, or cutaneous malignancy. It was difficult to pool and compare results because outcome measures differed between the studies. Three studies reported significant benefit with FAE when compared with placebo after 12 to 16 weeks of treatment, but we could not combine these results in a statistical analysis to show the overall difference. The included studies did not fully examine the chance of discontinuing FAE treatment because of adverse effects, which is uncertain. One study showed that individuals on FAE are nearly five times more likely to develop nuisance adverse effects; the most common were diarrhoea and abdominal cramps, flushing, reversible protein loss in the urine, and raised levels of eosinophil blood cells. Two RCTs were similar enough to allow the combination of their results and found that FAE were better than placebo when measured by the proportion of individuals who experienced at least a 50% improvement in their psoriasis severity score. One study reported improvement of individuals' quality of life with FAE in comparison with placebo, but the significance of this difference could not be calculated. The benefit of FAE was similar to methotrexate after 12 weeks when changes in disease severity from the start to the end of the trial were compared. The number of individuals experiencing nuisance adverse effects with these two treatments was not significantly different. The included studies, which were too small and of limited duration to provide evidence about rare or delayed effects, reported no serious adverse effects of FAE. The risk of study bias, which means any factors that may systematically deviate away from the true findings, was unclear in most studies. This may be because most of the studies were conducted decades ago or were incompletely reported. Several analyses comparing FAE with placebo and methotrexate were limited because the studies were small or did not provide enough information to establish how these treatments compare with each other. Therefore, the overall quality of the evidence was low when comparing FAE with placebo and very low when comparing FAE with methotrexate. Future RCTs should use standard psoriasis outcome measures, including a validated quality of life scale, to enable the comparison and combination of results. They should be longer in duration or have longer follow-up phases to provide evidence about any delayed adverse effects." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Nine randomized placebo-controlled trials involving 499 individuals with HIV infection and AIDS met the inclusion criteria. Methodological quality of trials was assessed as adequate in five full publications and unclear in other trials. Eight different herbal medicines were tested. A compound of Chinese herbs (IGM-1) showed significantly better effect than placebo in improvement of health-related quality of life in 30 symptomatic HIV-infected patients (WMD 0.66, 95% CI 0.05 to 1.27). IGM-1 appeared not to affect overall health perception, symptom severity, CD4 count, anxiety or depression (Burack 1996a). An herbal formulation of 35 Chinese herbs did not affect CD4 cell counts, viral load, AIDS events, symptoms, psychosocial measure, or quality of life (Weber 1999). There was no statistical difference between SPV30 and placebo in new AIDS-defining events, CD4 cell counts, or viral load (Durant 1998) although an earlier pilot trial showed positive effect of SPV30 on CD4 cell count (Durant 1997). Combined treatment of Chinese herbal compound SH and antiretroviral agents showed increased antiviral benefit compared with antiretrovirals alone (Sangkitporn 2004). SP-303 appeared to reduce stool weight (p = 0.008) and abnormal stool frequency (p = 0.04) in 51 patients with AIDS and diarrhoea (Holodniy 1999). Qiankunning appeared not to affect HIV-1 RNA levels (Shi 2003), Curcumin ineffective in reducing viral load or improving CD4 cell counts (Hellinger 1996), and Capsaicin ineffective in relieving pain associated with HIV-related peripheral neuropathy (Paice 2000). The occurrence of adverse effects was higher in the 35 Chinese herbs preparation (19/24) than in placebo (11/29) (79% versus 38%, p = 0.003) (Weber 1999). Qiankunning was associated with stomach discomfort and diarrhoea (Shi 2003). There is insufficient evidence to support the use of herbal medicines in HIV-infected individuals and AIDS patients. Potential beneficial effects need to be confirmed in large, rigorous trials.\nOutput:\n" }, { "from": "agent", "value": "Although many trials of these therapies exist, very few meet the scientific standards necessary to support the claims of beneficial effects in the therapies studied. This review identified nine randomized clinical trials, which tested eight different herbal medicines, compared with placebo, in HIV-infected individuals or AIDS patients with diarrhoea. The results showed that a preparation called SPV30 may be helpful in delaying the progression of HIV disease in HIV-infected people who do not have any symptoms of this infection. A Chinese herbal medicine, IGM-1, seems to improve the quality of life in HIV-infected people who do have symptoms. Another herbal compound ,SH, showed an increase of antiviral benefit when combined with antiretroviral agents. A South American herb preparation, SP-303, may reduce the frequency of abnormal stools in AIDS patients with diarrhoea. Other herbs tested were no better than placebo; however, the beneficial effects need to be considered with caution because the number of patients in these trials was small and the size of the effects quite moderate. In one trial the use of medicinal herbs was related to adverse effects such as gastrointestinal discomfort. Conclusion: No compelling evidence exists to support the use of the herbal medicines identified in this review for treatment of HIV infection and AIDS. To ensure that evidence is reliable, there need to be larger and more rigorously-designed trials." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Six studies were eligible for inclusion (517 patients). Five studies compared type I IFNs to placebo injections (485 patients) and a single study compared IFNs to prednisolone enemas in patients with left-sided colitis (32 patients). The active comparator study was rated as high risk of bias due to an open-label design. Three studies were rated as unclear risk of bias for random sequence generation and allocation concealment. Two studies described as double blind were rated as unclear risk of bias for blinding. There was no significant benefit of type I IFNs over placebo for inducing clinical remission or improvement in patients with active ulcerative colitis. Thirty-six per cent (87/242) of patients in the type I IFNs group achieved clinical remission by 8 to 12 weeks compared to 30% (36/120) of placebo patients (RR 1.16, 95% CI 0.84 to 1.58; 4 studies, 362 patients). A GRADE analysis indicated that the overall quality of the evidence supporting the outcome clinical remission was moderate due to sparse data (123 events). Fifty-six per cent (149/264) of patients in the type I IFNs group improved clinically by 8 to 12 weeks compared to 48% (77/161) of placebo patients (RR 1.16, 95% CI 0.96 to 1.40; 4 studies, 425 patients). A GRADE analysis indicated that the overall quality of the evidence supporting the outcome clinical improvement was moderate due to sparse data (226 events). Patients who received type I IFNs were significantly more likely to withdraw from the studies due to adverse events than those who received placebo. Seven per cent (18/42) of type I IFNs patients withdrew due to adverse events compared to 2% (3/152) of placebo patients (RR 3.16, 95% CI 1.06 to 9.40). A GRADE analysis indicated that the overall quality of the evidence supporting the outcome withdrawal due to adverse events was low due to very sparse data (21 events). The study comparing type I IFNs to prednisolone enemas found no difference between the treatment groups in quality of life or disease activity scores. Common adverse events included headaches, arthralgias, myalgias, fatigue, back pain, nausea, application site reactions, rigors, and fevers. There were no statistically significant differences in the other secondary outcomes. Moderate quality evidence suggests that type I IFNs are not effective for the induction of remission in UC. In addition, there are concerns regarding the tolerability of this class of treatment.\nOutput:\n" }, { "from": "agent", "value": "The researchers identified six studies that included a total of 517 participants. Five studies (total 485 participants) compared type I IFNs to placebo (fake medicine) injections. One small (32 participants) low quality study compared types I IFNs to prednisolone (a steroid drug) enemas. This study did not measure remission and found no difference between the treatment groups in quality of life or disease activity scores. There was no difference between type I interferons and placebo treatment groups for the number of people who achieved remission or improvement of their symptoms. These results suggest that type I IFNs do not produce remission from ulcerative colitis. Common side effects included headaches, arthralgias (joint pain), myalgias (muscle pain), fatigue, back pain, nausea, injection site reactions, rigors (cold and shivering), and fevers. At present, the results from medical trials do not support the use of type I IFNs for the production of remission in active ulcerative colitis." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Primary outcome measure: one cross-over trial including 18 participants showed after four weeks, 2 (95% confidence interval (CI) 0.9 to 3.1) points more improvement on an 11-point disability scale with plasma exchange (10 exchanges over four weeks) than with sham exchange. Rapid deterioration after plasma exchange occurred in eight of 12 who had improved. Secondary outcome measures: when we combined the results of this cross-over trial and a trial with 29 participants treated in a parallel-group design, there were 31 points (95% CI 18 to 45) more improvement on an impairment scale (maximum score 280) after plasma exchange (six exchanges over three weeks) than after sham exchange. There were significant improvements in both trials in an electrophysiological measure, the proximally evoked compound muscle action potential, after three or four weeks. Non-randomised evidence indicates that plasma exchange induces adverse events in 3% to 17% of procedures. These events are sometimes serious. Both trials had a low risk of bias. A trial that showed no significant difference in the benefit between plasma exchange and intravenous immunoglobulin is included in the Cochrane review of intravenous immunoglobulin for this condition. Moderate- to high-quality evidence from two small trials shows that plasma exchange provides significant short-term improvement in disability, clinical impairment, and motor nerve conduction velocity in CIDP but rapid deterioration may occur afterwards. Adverse events related to difficulty with venous access, use of citrate, and haemodynamic changes are not uncommon. We need more research to identify agents that will prolong the beneficial action of plasma exchange.\nOutput:\n" }, { "from": "agent", "value": "We found two randomised controlled trials. Both studies compared plasma exchange with sham exchange (in which blood was removed and returned but not exchanged). One trial aimed to compare four weeks' plasma exchange with sham exchange. The 18 participants received both treatments, being randomised to either treatment in the first period of the trial, crossing over to the other treatment for the second period. The other trial compared three-weeks' plasma exchange in 15 participants with sham exchange in 14 participants. We considered both trials at low risk of bias, which means largely free of flaws that could have influenced the results. A charitable grant supported the cross-over trial. The other did not report any support. The cross-over trial showed on average two points more improvement on an 11-point disability scale with plasma exchange than sham exchange. This was unlikely to have occurred by chance. The parallel-group trial did not report this outcome. When we combined the results of both trials, plasma exchange produced significantly more improvement in severity of disease signs measured by neurologists than sham exchange. The results reported were short term. In practice, people with CIDP receive repeated courses or combinations of plasma exchange with additional agents. Another Cochrane review includes a trial showing similar improvement after plasma exchange to that after intravenous infusion of immunoglobulin (the antibody portion of blood). According to non-randomised evidence, plasma exchange causes adverse events in 3% to 17% of procedures. These are sometimes serious. Because of the small size of the only trial reporting changes in disability, the quality of the evidence that plasma exchange reduces disability is moderate. The quality of the evidence that plasma exchange improves the signs of disease measured by a neurologist is high. The evidence is up to date to 30 June 2015." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included three RCTs (n=277) with 24-28 weeks follow-up. Three combinations of minerals were investigated: potassium-magnesium, calcium-magnesium, and calcium-potassium. One trial investigated combinations of calcium-magnesium and of calcium-potassium, and for each found a statistically non-significant increase in both SBP and DBP. All three trials investigated the potassium-magnesium combination. None of the trials provided mortality or morbidity data. The potassium-magnesium combination compared to control resulted in statistically non-significant reductions in both SBP (mean difference = -4.6 mmHg, 95% CI: -9.9 to 0.7) and DBP (mean difference = -3.8 mmHg, 95% CI: -9.5 to 1.8), although the results were heterogeneous (I2=68% and 85% for SBP and DBP respectively). A sensitivity analysis using alternative reported values which accounted for missing data had very little effect on DBP but resulted in a larger, statistically significant reduction in SBP (mean difference = -5.8 mmHg, 95% CI: -10.5 to -1.0). The quality of the trials was not well reported. We found no robust evidence that supplements of any combination of potassium, magnesium or calcium reduce mortality, morbidity or BP in adults. More trials are needed to investigate whether the combination of potassium & magnesium is effective.\nOutput:\n" }, { "from": "agent", "value": "This review found no robust evidence to suggest that combinations of potassium, calcium or magnesium can reduce high blood pressure (BP) in adults. Only three trials assessing a total of 277 participants were found. The only combination assessed by all three trials was potassium and magnesium, demonstrating a statistically non-significant reduction in BP among people receiving this combination. One trial assessed both calcium & magnesium and calcium & potassium and found that neither combination had very much effect on BP. None of the trials were of high quality, so their results may not be reliable. Very few mild adverse effects were reported. These were of short duration and participants did not have to stop taking their treatment." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: The original version of this Cochrane review included five RCTs involving 1277 women. In this 2015 update, no new studies met the inclusion criteria but we included an additional paper with mature data (10-year follow-up) relating to a previously included study (ICON1). We included four studies in the meta-analyses and considered them to be at a low risk of bias. Most study participants (> 95%) had stage I ovarian cancer. Meta-analysis of five-year data from three studies indicated that women who received adjuvant platinum-based chemotherapy had better overall survival (OS) than those who did not (Hazard ratio (HR) 0.71, 95% confidence interval (CI) 0.53 to 0.93; 1008 women; 3 studies; I² statistic = 0%; high quality evidence). Likewise, meta-analysis of five-year data from four studies indicated that women who received adjuvant chemotherapy had better progression-free survival (PFS) than those who did not (HR 0.67, 95% CI 0.53 to 0.84; 1170 women, 4 studies; I² statistic = 0%; high quality evidence). These findings were robust over time, with 10-year HR estimates of 0.72 (95% CI 0.57 to 0.92; 925 women, 2 studies) and 0.67 (95% CI 0.53 to 0.83; 925 women, 2 studies) for OS and PFS, respectively (high quality evidence). The risk of death at 10 years follow-up favoured the adjuvant chemotherapy arm (0.76, 95% CI 0.62 to 0.94; 923 women, 2 studies; I² statistic = 0%), as did the findings for risk of progression at 10 years (RR 0.72, 95% CI 0.60 to 0.87; 925 women, 2 studies; I² statistic = 0%). Low quality evidence suggested that women with high-risk disease may have the most to gain from adjuvant chemotherapy. However, subgroup analyses could neither confirm nor exclude survival benefits in lower risk disease or in optimally staged disease. We found insufficient data to compare adverse events and long term risks between chemotherapy and observation groups. High-quality evidence indicates that adjuvant platinum-based chemotherapy is effective in prolonging survival in women with early stage (FIGO stage I/IIa) epithelial ovarian cancer. It remains uncertain whether women with low- and intermediate-risk early stage disease will benefit as much from adjuvant chemotherapy as women with high-risk disease. Decisions to use adjuvant chemotherapy (AC) in these women should be mindful of this uncertainty, and the uncertainty regarding adverse events. Treatment of women with lower risk disease should be individualised to take into account individual factors.\nOutput:\n" }, { "from": "agent", "value": "We searched the literature up to 24th March 2015 and included five trials involving 1277 women with early-stage OC in the review, and four good quality trials contributed data. Most women (more than 95%) had stage I OC. For this update, we identified one additional publication of 10-year follow-up results from a trial already included in the review, but found no new trials. We found high quality evidence that women diagnosed with early-stage OC who received AC after surgery to remove and stage the disease had a lower risk of dying within 10 years than women who did not receive AC (observation group), and a lower risk of the cancer returning in the 10 years after treatment (see Cates plot, Figures 4 to 7). Low quality evidence suggested that women with higher risk disease may have more to gain from AC, but we could not exclude a survival benefit for other early stage disease. Chemotherapy can have side effects but we found insufficient data to compare adverse events and long term risks between chemotherapy and observation groups. In early stage ovarian cancer, AC improves survival and reduces the risk of ovarian cancer recurring compared with no AC. Therefore AC in early stage disease should be considered in all women. However, it remains uncertain whether women with lower risk early stage disease will benefit much from AC and decisions to use AC should be mindful of this uncertainty, and the uncertainty regarding adverse events." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Fourteen clinical trials, involving 721 participants, met the criteria for inclusion in the review. Thirteen studies compared a pharmaceutical treatment with placebo (or a low dose of the intervention), in heterogenous groups of degenerative cerebellar ataxias. Three compounds were studied in two trials each: a levorotatory form of 5-hydroxytryptophan (L-5HT), idebenone and thyrotropin-releasing hormone tartrate (TRH-T); each of the other compounds (riluzole, varenicline, buspirone, betamethasone, coenzyme Q10 with vitamin E, α-tocopheryl quinone and erythropoietin) were studied in one trial. The 14th trial, involving a mixed group of participants with spinocerebellar ataxia, compared the effectiveness of nonspecific physiotherapy and occupational therapy within an inpatient hospital setting to no treatment. No studies utilised traditional speech therapies. We defined the primary outcome measure in this review as the percentage change (improvement) in overall speech production immediately following completion of the intervention or later, measured by any validated speech assessment tool. None of the trials included speech as a primary outcome or examined speech using any validated speech assessment tool. Eleven studies reported speech outcomes derived from a subscale embedded within disease rating scales. The remaining three studies used alternative assessments to measure speech, including mean time to produce a standard sentence, a subjective rating of speech on a 14-point analogue scale, patient-reported assessment of the impact of dysarthria on activities of daily living and acoustic measures of syllable length. One study measured speech both subjectively as part of a disease rating scale and with further measures of speech timing. Three studies utilised the Short Form-36 Health Survey (SF-36) and one used the Child Health Questionnaire as measures of general quality of life. A further study utilised the Functional Independence Measure to assess functional health. Five studies reported statistically significant improvement on an overall disease rating scale in which a speech subscale was included. Only three of those studies provided specific data on speech performance; all were comparisons with placebo. Improvements in overall disease severity were observed with α-tocopheryl quinone; however, no significant changes were found on the speech subscale in a group of individuals with Friedreich ataxia. A statistically significant improvement in speech according to a speech disorders subscale was observed with betamethasone. Riluzole was found to have a statistically significant effect on speech in a group of participants with mixed hereditary, sporadic and unknown origin ataxias. No significant differences were observed between treatment and placebo in any other pharmaceutical study. A statistically significant improvement in functional independence occurred at the end of the treatment period in the rehabilitation study compared to the delayed treatment group but these effects were not present 12 to 24 weeks after treatment. Of the four studies that assessed quality of life, none found a significant effect. A variety of minor adverse events were reported for the 13 pharmaceutical therapies, including gastrointestinal side effects and nausea. Serious adverse effects were reported in two participants in one of the L-5HT trials (participants discontinued due to gastrointestinal effects), and in four participants (three taking idebenone, one taking placebo) in the idebenone studies. Serious adverse events with idebenone were gastrointestinal side effects and, in people with a previous history of these events, chest pain and idiopathic thrombocytopenic purpura. The rehabilitation study did not report any adverse events. We considered six studies to be at high risk of bias in some respect. We suspected inadequate blinding of participants or assessors in four studies and poor randomisation in a further two studies. There was a high risk of reporting bias in two studies and attrition bias in four studies. Only one study had a low risk of bias across all criteria. Taken together with other limitations of the studies relating to the validity of the measurement scales used, we downgraded the quality of the evidence for many of the outcomes to low or very low. There is insufficient and low or very low quality evidence from either RCTs or observational studies to determine the effectiveness of any treatment for speech disorder in any of the hereditary ataxia syndromes.\nOutput:\n" }, { "from": "agent", "value": "We searched widely for clinical trials and found 14 trials of treatments for speech problems in hereditary ataxias. The trials involved 721 participants. The duration of treatment was between two weeks and two years. Thirteen trials compared a medicine to a placebo and the 14th compared a mixed physiotherapy and occupational therapy treatment to no treatment. Ten different medicines were tested: L-hydroxytryptophan (L-5HT) (two studies), thyrotropin-releasing hormone (TRH) (two studies), varenicline, riluzole, idebenone (two studies), betamethasone, coenzyme Q10 with vitamin E, buspirone, ɑ-tocopheryl quinone and erythropoietin. We did not find any studies of traditional speech therapies. There were three ongoing trials. When planning the review, we decided to use the percentage change in speech production after treatment as our primary measure of whether treatments were effective. None of the studies measured speech in a way that allowed us to report this. Five studies reported improvement in overall disease severity but only two studies, of riluzole in various ataxias and betamethasone in ataxia telangiectasia, demonstrated improvement of speech production. It is difficult to say whether these improvements in speech might make a meaningful difference to patients. A variety of minor adverse events occurred with the medicines, including effects on the stomach and intestines, such as feeling sick. This kind of effect caused two people taking L-5HT to stop treatment. Another person experienced this effect while taking idebenone. Two more people taking idebenone experienced heart or autoimmune problems; however, they each had experienced those problems earlier in their life. None of the other studies found differences in speech performance on active treatment. All trials had some problems in conduct or design that could potentially affect the findings. Most of the included studies were small and looked at a mixed group of people with different forms of ataxia. The current evidence base is of low or very low quality and does not allow us to decide whether treatments for speech problems in the hereditary ataxia syndromes are effective. The evidence is up to date to October 2013." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We identified 60 studies, enrolling 3802 recipients. Twenty-nine studies (2262 participants) compared calcium channel blockers (CCB) to placebo/no treatment, 10 studies (445 participants) compared angiotensin converting enzyme inhibitors (ACEi) to placebo/no treatment and seven studies (405 participants) compared CCB to ACEi. CCB compared to placebo/no treatment (plus additional agents in either arm as required) reduced graft loss (RR 0.75, 95% CI 0.57 to 0.99) and improved glomerular filtration rate (GFR), (MD, 4.45 mL/min, 95% CI 2.22 to 6.68). Data on ACEi versus placebo/no treatment were inconclusive for GFR (MD -8.07 mL/min, 95% CI -18.57 to 2.43), and variable for graft loss, precluding meta-analysis. In direct comparison with CCB, ACEi decreased GFR (MD -11.48 mL/min, 95% CI -5.75 to -7.21), proteinuria (MD -0.28 g/24 h, 95% CI -0.47 to -0.10), haemoglobin (MD -12.96 g/L, 95% CI -5.72 to -10.21) and increased hyperkalaemia (RR 3.74, 95% CI 1.89 to 7.43). Graft loss data were inconclusive (RR 7.37, 95% CI 0.39 to 140.35). Other drug comparisons were compared in small numbers of participants and studies. These data suggest that CCB may be preferred as first line agents for hypertensive kidney transplant recipients. ACEi have some detrimental effects in kidney transplant recipients. More high quality studies reporting patient centred outcomes are required.\nOutput:\n" }, { "from": "agent", "value": "We found that calcium channel blockers (CCB) reduced the risk of graft loss by about 25% in randomised studies, compared to placebo or no treatment. CCB also improved the function of grafts, as measured by glomerular filtration rate (GFR) with GFR 4.5 mL/min higher on average in patients receiving CCB compared to placebo. There were fewer studies comparing angiotensin converting enzyme inhibitors (ACEi) to placebo and their results were inconclusive. In studies that compared ACEi to CCB, ACEi worsened GFR by about 11.5 mL/min on average. ACEi also lowered haemoglobin and increased the risk of elevated blood potassium compared to CCB. There were not enough studies of other classes of drugs to draw conclusions about their relative effects. On current evidence CCB might therefore be the best agents for kidney transplant patients." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included three small trials (total 397 women) of average quality in the review. Magnesium sulphate was associated with fewer maternal deaths (risk ratio (RR) 0.14, 95% confidence interval (CI) 0.03 to 0.59; 3 trials, 397 women) and was better at preventing further seizures (RR 0.06, 95% CI 0.03 to 0.12; 3 trials, 397 women) than lytic cocktail. Magnesium sulphate was also associated with less respiratory depression (RR 0.12, 95% CI 0.02 to 0.91; 2 trials, 198 women), less coma (RR 0.04, 95% CI 0.00 to 0.74; 1 trial, 108 women), and less pneumonia (RR 0.20, 95% CI 0.06 to 0.67; 2 trials, 307 women). There was no clear difference in the RR for any death of the baby (RR 0.35, 95% CI 0.05 to 2.38, random effects; 2 trials, 177 babies). Magnesium sulphate, rather than lytic cocktail, for women with eclampsia reduces the RR of maternal death, of further seizures and of serious maternal morbidity (respiratory depression, coma, pneumonia). Magnesium sulphate is the anticonvulsant of choice for women with eclampsia; the use of lytic cocktail should be abandoned.\nOutput:\n" }, { "from": "agent", "value": "Pre-eclampsia, also known as toxaemia, is a condition which leads to high blood pressure and protein in the urine. Eclampsia is when a pregnant woman with pre-eclampsia has one or more seizures (fits). Eclampsia is a serious threat to the life of both mother and baby. We identified three randomised trials, involving 397 women with eclampsia who were randomly assigned to treatment with magnesium sulphate or a lytic mixture of chlorpromazine, promethazine and pethidine that lowers blood pressure and is a sedative. Both drugs could be given either by intravenous or intramuscular injection. Although the trials were small and of average quality, the review found that magnesium sulphate was better than lytic cocktail at preventing maternal deaths, further seizures, and breathing problems and coma for the mother. Magnesium sulphate is also relatively cheap and easy to use. The adverse effects of magnesium sulphate come largely from its smooth muscle relaxant activity; respiratory depression is dose dependent and, with monitoring of the woman's clinical condition, uncommon." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: One hundred and twenty one trials with 6700 participants were included. In most trials, PRT was performed two to three times per week and at a high intensity. PRT resulted in a small but significant improvement in physical ability (33 trials, 2172 participants; SMD 0.14, 95% CI 0.05 to 0.22). Functional limitation measures also showed improvements: e.g. there was a modest improvement in gait speed (24 trials, 1179 participants, MD 0.08 m/s, 95% CI 0.04 to 0.12); and a moderate to large effect for getting out of a chair (11 trials, 384 participants, SMD -0.94, 95% CI -1.49 to -0.38). PRT had a large positive effect on muscle strength (73 trials, 3059 participants, SMD 0.84, 95% CI 0.67 to 1.00). Participants with osteoarthritis reported a reduction in pain following PRT(6 trials, 503 participants, SMD -0.30, 95% CI -0.48 to -0.13). There was no evidence from 10 other trials (587 participants) that PRT had an effect on bodily pain. Adverse events were poorly recorded but adverse events related to musculoskeletal complaints, such as joint pain and muscle soreness, were reported in many of the studies that prospectively defined and monitored these events. Serious adverse events were rare, and no serious events were reported to be directly related to the exercise programme. This review provides evidence that PRT is an effective intervention for improving physical functioning in older people, including improving strength and the performance of some simple and complex activities. However, some caution is needed with transferring these exercises for use with clinical populations because adverse events are not adequately reported.\nOutput:\n" }, { "from": "agent", "value": "Evidence from 121 randomised controlled trials (6,700 participants) shows that older people who exercise their muscles against a force or resistance become stronger. They also improve their performance of simple activities such as walking, climbing steps, or standing up from a chair more quickly. The improvement in activities such as getting out of a chair or stair climbing is generally greater than walking speed. Moreover, these strength training exercises also improved older people's physical abilities, including more complex daily activities such as bathing or preparing a meal. PRT also reduced pain in people with osteoarthritis. There was insufficient evidence to comment on the risks of PRT or long term effects." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We identified 37 randomised controlled trials involving 11,948 participants. These trials compared lidocaine versus placebo or no intervention, disopyramide, mexiletine, tocainide, propafenone, amiodarone, dimethylammonium chloride, aprindine and pirmenol. Overall, trials were underpowered and had high risk of bias. Ninety-seven per cent of trials (36/37) were conducted without an a priori sample size estimation. Ten trials were sponsored by the pharmaceutical industry. Trials were conducted in 17 countries, and intravenous intervention was the most frequent route of administration. In trials involving participants with proven or non-proven acute myocardial infarction, lidocaine versus placebo or no intervention showed no significant differences regarding all-cause mortality (213/5879 (3.62%) vs 199/5848 (3.40%); RR 1.02, 95% CI 0.82 to 1.27; participants = 11727; studies = 18; I2 = 15%); low-quality evidence), cardiac mortality (69/4184 (1.65%) vs 62/4093 (1.51%); RR 1.03, 95% CI 0.70 to 1.50; participants = 8277; studies = 12; I2 = 12%; low-quality evidence) and prophylaxis of ventricular fibrillation (76/5128 (1.48%) vs 103/4987 (2.01%); RR 0.78, 95% CI 0.55 to 1.12; participants = 10115; studies = 16; I2 = 18%; low-quality evidence). In terms of sinus bradycardia, lidocaine effect is imprecise compared with effects of placebo or no intervention (55/1346 (4.08%) vs 49/1203 (4.07%); RR 1.09, 95% CI 0.66 to 1.80; participants = 2549; studies = 8; I2 = 21%; very low-quality evidence). In trials involving only participants with proven acute myocardial infarction, lidocaine versus placebo or no intervention showed no significant differences in all-cause mortality (148/2747 (5.39%) vs 135/2506 (5.39%); RR 1.01, 95% CI 0.79 to 1.30; participants = 5253; studies = 16; I2 = 9%; low-quality evidence). No significant differences were noted between lidocaine and any other antiarrhythmic drug in terms of all-cause mortality and ventricular fibrillation. Data on overall survival 30 days after myocardial infarction were not reported. Lidocaine compared with placebo or no intervention increased risk of asystole (35/3393 (1.03%) vs 14/3443 (0.41%); RR 2.32, 95% CI 1.26 to 4.26; participants = 6826; studies = 4; I2 = 0%; very low-quality evidence) and dizziness/drowsiness (74/1259 (5.88%) vs 16/1274 (1.26%); RR 3.85, 95% CI 2.29 to 6.47; participants = 2533; studies = 6; I2 = 0%; low-quality evidence). Overall, safety data were poorly reported and adverse events may have been underestimated. Trial sequential analyses suggest that additional trials may not be needed for reliable conclusions to be drawn regarding these outcomes. This Cochrane review found evidence of low quality to suggest that prophylactic lidocaine has very little or no effect on mortality or ventricular fibrillation in people with acute myocardial infarction. The safety profile is unclear. This conclusion is based on randomised controlled trials with high risk of bias. However (disregarding the risk of bias), trial sequential analysis suggests that additional trials may not be needed to disprove an intervention effect of 20% relative risk reduction. Smaller risk reductions might require additional higher trials.\nOutput:\n" }, { "from": "agent", "value": "We identified 37 trials conducted between 1969 and 1999. The evidence is current up to April 2015. Trials were conducted in Australia, Belgium, Brazil, Canada, Denmark, France, Germany, Italy, New Zealand, Northern Ireland, Norway, Poland, Sweden, Switzerland, The Netherlands, United Kingdom and United States of America and included 11,948 participants. Trials were conducted in pre-hospital and in-hospital settings and included individuals with or without proved acute myocardial infarction. Some trials did not limit results to acute myocardial infarction only. Lidocaine was given by intravenous (bolus and/or infusion) and intramuscular (alone or in combination with intravenous dosage) routes. Overall, trials included small sample sizes and reported low numbers of events. All trials had high risk of bias. Ten trials were sponsored by the pharmaceutical industry. In people who had known or suspected heart attack, we found that lidocaine compared with placebo, no intervention or any other antiarrhythmic drug had very small or no effects on death, cardiac death and ventricular fibrillation. Our confidence in the results of this review is low because the included trials that we synthesised were of low quality (overestimation of benefits and underestimation of harms) and were conducted with a small number of participants, leading to imprecision of results." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Sixty-one studies (37,250 participants) compared oral sumatriptan with placebo or an active comparator. Most of the data were for the 50 mg and 100 mg doses. Sumatriptan surpassed placebo for all efficacy outcomes. For sumatriptan 50 mg versus placebo the NNTs were 6.1, 7.5, and 4.0 for pain-free at two hours and headache relief at one and two hours, respectively. NNTs for sustained pain-free and sustained headache relief during the 24 hours postdose were 9.5 and 6.0, respectively. For sumatriptan 100 mg versus placebo the NNTs were 4.7, 6.8, 3.5, 6.5, and 5.2, respectively, for the same outcomes. Results for the 25 mg dose were similar to the 50 mg dose, while sumatriptan 100 mg was significantly better than 50 mg for pain-free and headache relief at two hours, and for sustained pain-free during 24 hours. Treating early, during the mild pain phase, gave significantly better NNTs for pain-free at two hours and sustained pain-free during 24 hours than did treating established attacks with moderate or severe pain intensity. Relief of associated symptoms, including nausea, photophobia, and phonophobia, was greater with sumatriptan than with placebo, and use of rescue medication was lower with sumatriptan than with placebo. For the most part, adverse events were transient and mild and were more common with the sumatriptan than with placebo, with a clear dose response relationship (25 mg to 100 mg). Sumatriptan was compared directly with a number of active treatments, including other triptans, paracetamol (acetaminophen), acetylsalicylic acid, non-steroidal anti-inflammatory drugs (NSAIDs), and ergotamine combinations. Oral sumatriptan is effective as an abortive treatment for migraine attacks, relieving pain, nausea, photophobia, phonophobia, and functional disability, but is associated with increased adverse events.\nOutput:\n" }, { "from": "agent", "value": "This review found that a single dose was effective in relieving migraine headache pain and associated symptoms of nausea, sensitivity to light, and sensitivity to sound. Pain was reduced from moderate or severe to no pain by two hours in about 3 in 10 people (32%) taking sumatriptan 100 mg, compared with about 1 in 10 (11%) taking placebo. Pain was reduced from moderate or severe to no worse than mild pain by two hours in 6 in 10 people (61%) taking sumatriptan 100 mg, compared with about 3 in 10 (32%) taking placebo. Almost a quarter (24%) of people taking sumatriptan 100 mg had freedom from pain at two hours which was sustained during 24 hours without the use of rescue medication, compared with fewer than 1 in 10 (8%) taking placebo. In addition to relieving headache pain, sumatriptan also relieved symptoms of nausea and sensitivity to light and sound by two hours in about half of those who took it, compared with about one-third of those taking placebo. Adverse events were mostly of short duration and mild or moderate in severity, and were experienced by about 4 in 10 (43%) of people taking sumatriptan 100 mg, and by 2 in 10 (23%) taking placebo. The 50 mg dose had slightly lower efficacy, but was associated with fewer adverse events. Treating attacks while pain was still mild was more effective than treating established attacks with moderate or severe pain intensity." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: 12 studies (mean duration of eight weeks) in 7439 mostly Caucasian patients (mean age 54 years) with mild-to-moderate uncomplicated hypertension were eligible for inclusion in the review. Aliskiren was the only renin inhibitor evaluated. All included studies were assessed to have high likelihood of attrition, reporting and funding bias. Aliskiren has a dose-related systolic/diastolic blood pressure (SBP/DBP) lowering effect as compared with placebo MD with 95% CI: aliskiren 75 mg (MD -2.97, 95% CI -4.76 to -1.18)/(MD -2.05, 95% CI -3.13 to -0.96) mm Hg (moderate-quality evidence), aliskiren 150 mg (MD -5.95, 95% CI -6.85 to -5.06)/ (MD -3.16, 95% CI -3.74 to -2.58) mm Hg (moderate-quality evidence), aliskiren 300 mg (MD -7.88, 95% CI -8.94 to -6.82)/ (MD -4.49, 95% CI -5.17 to -3.82) mm Hg (moderate-quality evidence), aliskiren 600 mg (MD -11.35, 95% CI -14.43 to -8.27)/ (MD -5.86, 95% CI -7.73 to -3.99) mm Hg (low-quality evidence). There was a dose-dependent decrease in blood pressure for aliskiren 75 mg, 150 mg and 300 mg. The blood pressure lowering effect of aliskiren 600 mg was not different from 300 mg (MD -0.61, 95% CI -2.78 to 1.56)/(MD -0.68, 95% CI -2.03 to 0.67). Aliskiren had no effect on blood pressure variability. Due to very limited information available regarding change in heart rate and pulse pressure, it was not possible to meta-analyze these outcomes. Mortality and non-fatal serious adverse events were not increased. This review found that in studies of eight week duration aliskiren may not increase withdrawal due to adverse events (low-quality evidence). Diarrhoea was increased in a dose-dependent manner (RR 7.00, 95% CI 2.48 to 19.72) with aliskiren 600 mg (low-quality evidence). The most frequent adverse events reported were headache, nasopharyngitis, diarrhoea, dizziness and fatigue. Compared to placebo, aliskiren lowered BP and this effect is dose-dependent. This magnitude of BP lowering effect is similar to that for angiotensin-converting enzyme (ACE) inhibitors and angiotensin receptor blockers (ARBs). There is no difference in mortality, nonfatal serious adverse events or withdrawal due to adverse effects with short term aliskiren monotherapy. Diarrhoea was considerably increased with aliskiren 600 mg.\nOutput:\n" }, { "from": "agent", "value": "We found 12 studies, eight weeks in duration, that randomly assigned 7439 adult people with uncomplicated mild-to-moderate hypertension to aliskiren at doses ranging from 75 mg to 600 mg or placebo. All studies were funded by the manufacturer Novartis. Detailed information regarding adverse events, obtained from nine clinical study reports submitted to regulators, are included in this update. We concluded that aliskiren is better than placebo at lowering blood pressure and that the magnitude of this effect could be similar to other classes of drugs when 300 mg, which is the maximum recommended dose, is used. Aliskiren 300 mg reduced blood pressure by eight points in the upper number (called systolic blood pressure) and five points in the lower number (called diastolic blood pressure). Aliskiren had no effect on blood pressure changeability. Due to very limited information regarding change in heart rate and pulse pressure (difference between upper and lower number) it was not possible to analyze these outcomes. The studies were too short in duration to assess side effects. Aliskiren did not increase death, non-fatal serious adverse events or withdrawal due to side effects. The most common adverse events observed were headache, diarrhoea, dizziness and fatigue. Diarrhoea was considerably increased with aliskiren 600 mg as compared to placebo. The decrease in blood pressure at the recommended dose was rated as moderate-quality evidence and adverse event data was graded as low-quality evidence as included studies were assessed to have high likelihood of reporting and funding bias." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We identified 26 trials (2736 patients). Twenty trials investigated pTE (thymostimulin or thymosin fraction 5) and six trials investigated sTP (thymopentin or thymosin α1). Twenty-one trials reported results for OS, six for DFS, 14 for TR, nine for AE and 10  for safety of pTE and sTP. Addition of pTE conferred no benefit on OS (RR 1.00, 95% CI 0.79 to 1.25); DFS (RR 0.97, 95% CI 0.82 to 1.16); or TR (RR 1.07, 95% CI 0.92 to 1.25). Heterogeneity was moderate to high for all these outcomes. For thymosin α1 the pooled RR for OS was 1.21 (95% CI 0.94 to 1.56, P = 0.14), with low heterogeneity; and 3.37 (95% CI 0.66 to 17.30, P = 0.15) for DFS, with moderate heterogeneity. The pTE reduced the risk of severe infectious complications (RR 0.54, 95% CI 0.38 to 0.78, P = 0.0008; I² = 0%). The RR for severe neutropenia in patients treated with thymostimulin was 0.55 (95% CI 0.25 to 1.23,  P = 0.15). Tolerability of pTE and sTP was good. Most of the trials had at least a moderate risk of bias. Overall, we found neither evidence that the addition of pTE to antineoplastic treatment reduced the risk of death or disease progression nor that it improved the rate of tumour responses to antineoplastic treatment. For thymosin α1, there was a trend for a reduced risk of dying and of improved DFS. There was preliminary evidence that pTE lowered the risk of severe infectious complications in patients undergoing chemotherapy or radiotherapy.\nOutput:\n" }, { "from": "agent", "value": "This review looked at the evidence from 26 clinical trials with a total of 2736 adult cancer patients. Many of the trials were small and of moderate quality. Only three studies were less than 10 years old. Thymosin α1 is a synthetic peptide that shows some promise as a treatment option for patients with metastatic melanoma when used in addition to chemotherapy. Severe problems occur during chemotherapy and radiotherapy due to low white blood cell counts and infections. These were reduced by using purified thymus extracts. However, the use of purified thymus extracts should be investigated more thoroughly before the extracts are used routinely in patients. The findings were not conclusive and caution is advised. Overall, thymic peptides seem to be well tolerated." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Fourteen studies met the inclusion criteria, randomly assigning 2313 people with acute asthma to the comparisons of interest in this review. Most studies were double-blinded trials comparing a single infusion of 1.2 g or 2 g IV MgSO4 over 15 to 30 minutes versus a matching placebo. Eleven were conducted at a single centre, and three were multi-centre trials. Participants in almost all of the studies had already been given at least oxygen, nebulised short-acting beta2-agonists and IV corticosteroids in the ED; in some studies, investigators also administered ipratropium bromide. Ten studies included only adults, and four included both adults and children; these were included because the mean age of participants was over 18 years. Intravenous MgSO4 reduced hospital admissions compared with placebo (odds ratio (OR) 0.75, 95% confidence interval (CI) 0.60 to 0.92; I2 = 28%, P value 0.18; n = 972; high-quality evidence). In absolute terms, this odds ratio translates into a reduction of seven hospital admissions for every 100 adults treated with IV MgSO4 (95% CI two to 13 fewer). The test for subgroup differences revealed no statistical heterogeneity between the three severity subgroups (I2 = 0%, P value 0.73) or between the four studies that administered nebulised ipratropium bromide as a co-medication and those that did not (I2 = 0%, P value 0.82). Sensitivity analyses in which unpublished data and studies at high risk for blinding were removed from the primary analysis did not change conclusions. Within the secondary outcomes, high- and moderate-quality evidence across three spirometric indices suggests some improvement in lung function with IV MgSO4. No difference was found between IV MgSO4and placebo for most of the non-spirometric secondary outcomes, all of which were rated as low or moderate quality (intensive care admissions, ED treatment duration, length of hospital stay, readmission, respiration rate, systolic blood pressure). Adverse events were inconsistently reported and were not meta-analysed. The most commonly cited adverse events in the IV MgSO4 groups were flushing, fatigue, nausea and headache and hypotension (low blood pressure). This review provides evidence that a single infusion of 1.2 g or 2 g IV MgSO4 over 15 to 30 minutes reduces hospital admissions and improves lung function in adults with acute asthma who have not responded sufficiently to oxygen, nebulised short-acting beta2-agonists and IV corticosteroids. Differences in the ways the trials were conducted made it difficult for the review authors to assess whether severity of the exacerbation or additional co-medications altered the treatment effect of IV MgSO4. Limited evidence was found for other measures of benefit and safety. Studies conducted in these populations should clearly define baseline severity parameters and systematically record adverse events. Studies recruiting participants with exacerbations of varying severity should consider subgrouping results on the basis of accepted severity classifications.\nOutput:\n" }, { "from": "agent", "value": "Fourteen studies met the inclusion criteria, involving a total of 2313 people. These studies varied in terms of how bad exacerbations had to be for people to be included and in terms of what other treatments were provided before IV MgSO4was given, but almost all trials gave participants at least oxygen, nebulised short-acting medications and steroid tablets or injection. Overall, IV MgSO4 reduced the need for hospital admission compared with placebo (seven fewer per 100 treated; 95% confidence interval two to 13 fewer). Not enough information was available to show whether the reduction in hospital admissions was associated with severity of the asthma exacerbation, or whether it made a difference what other treatments were given. Evidence suggests that IV MgSO4 improved some lung function parameters, but for other measures such as heart rate, variation among study findings reduced our confidence in the results. We did not find a difference between IV MgSO4 and placebo in most other measures (including time spent in the ED, respiratory rate and blood pressure), and adverse events generally were poorly reported. This review showed that IV MgSO4reduces hospital admissions and improves lung function in adults with exacerbations of asthma when other first-line medications have not relieved the acute symptoms (i.e. oxygen, inhaled short-acting medications and IV steroids). Evidence for other measures of benefit and safety was limited. Researchers should clearly define the severity of the asthma condition among people in their studies while carefully recording adverse events. This plain language summary is current as of May 2014." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We found no randomised controlled trials on this topic. We included six non-randomised studies (five retrospective) that compared laparoscopic versus open transhiatal oesophagectomy (334 patients: laparoscopic = 154 patients; open = 180 patients); five studies (326 patients: laparoscopic = 151 patients; open = 175 patients) provided information for one or more outcomes. Most studies included a mixture of adenocarcinoma and squamous cell carcinoma and different stages of oesophageal cancer, without metastases. All the studies were at unclear or high risk of bias; the overall quality of evidence was very low for all the outcomes. The differences between laparoscopic and open transhiatal oesophagectomy were imprecise for short-term mortality (laparoscopic = 0/151 (adjusted proportion based on meta-analysis estimate: 0.5%) versus open = 2/175 (1.1%); RR 0.44; 95% CI 0.05 to 4.09; participants = 326; studies = 5; I² = 0%); long-term mortality (HR 0.97; 95% CI 0.81 to 1.16; participants = 193; studies = 2; I² = 0%); anastomotic stenosis (laparoscopic = 4/36 (11.1%) versus open = 3/37 (8.1%); RR 1.37; 95% CI 0.33 to 5.70; participants = 73; studies = 1); short-term recurrence (laparoscopic = 1/16 (6.3%) versus open = 0/4 (0%); RR 0.88; 95% CI 0.04 to 18.47; participants = 20; studies = 1); long-term recurrence (HR 1.00; 95% CI 0.84 to 1.18; participants = 173; studies = 2); proportion of people who required blood transfusion (laparoscopic = 0/36 (0%) versus open = 6/37 (16.2%); RR 0.08; 95% CI 0.00 to 1.35; participants = 73; studies = 1); proportion of people with positive resection margins (laparoscopic = 15/102 (15.8%) versus open = 27/111 (24.3%); RR 0.65; 95% CI 0.37 to 1.12; participants = 213; studies = 3; I² = 0%); and the number of lymph nodes harvested during surgery (median difference between the groups varied from 12 less to 3 more lymph nodes in the laparoscopic compared to the open group; participants = 326; studies = 5). The proportion of patients with serious adverse events was lower in the laparoscopic group (10/99, (10.3%) compared to the open group = 24/114 (21.1%); RR 0.49; 95% CI 0.24 to 0.99; participants = 213; studies = 3; I² = 0%); as it was for adverse events in the laparoscopic group = 37/99 (39.9%) versus the open group = 71/114 (62.3%); RR 0.64; 95% CI 0.48 to 0.86; participants = 213; studies = 3; I² = 0%); and the median lengths of hospital stay were significantly less in the laparoscopic group than the open group (three days less in all three studies that reported this outcome; number of participants = 266). There was lack of clarity as to whether the median difference in the quantity of blood transfused was statistically significant favouring laparoscopic oesophagectomy in the only study that reported this information. None of the studies reported post-operative dysphagia, health-related quality of life, time-to-return to normal activity (return to pre-operative mobility without caregiver support), or time-to-return to work. There are currently no randomised controlled trials comparing laparoscopic with open transhiatal oesophagectomy for patients with oesophageal cancers. In observational studies, laparoscopic transhiatal oesophagectomy is associated with fewer overall complications and shorter hospital stays than open transhiatal oesophagectomy. However, this association is unlikely to be causal. There is currently no information to determine a causal association in the differences between the two surgical approaches. Randomised controlled trials comparing laparoscopic transhiatal oesophagectomy with other methods of oesophagectomy are required to determine the optimal method of oesophagectomy.\nOutput:\n" }, { "from": "agent", "value": "Randomised controlled trials are the best types of studies to find out whether one treatment is better than another since it ensures that similar types of people receive the new and the old treatment. But we did not find randomised controlled trials; we identified six relevant non-randomised studies with a total of 334 patients, which compared laparoscopic and open surgeries. Since one of the studies did not provide usable results, five studies, with 326 patients, provided information for this review; laparoscopic surgery = 151 patients and open surgery = 175 patients. In four of these studies, historical information was collected from hospital records. In one study, new information was collected. In general, new information is considered to be more reliable than information from hospital records. The differences between laparoscopic and open transhiatal oesophagectomy were imprecise for: deaths during the short-term and long-term, the percentage of people with major complications, narrowing of the new junction between the gut, created after removing the oesophagus, cancer returning during the short-term and long-term, and the proportion of people who required blood transfusion. The proportion of patients with any complications and the average lengths of hospital stay were less in the key-hole group than the open cut group. There was lack of clarity about the difference in the amount of blood transfused between the two groups. None of the studies reported difficulty in swallowing after surgery, health-related quality of life, the amount of time it took to return to normal activity (same mobility as before surgery), or work. The quality of the evidence was very low. This was mainly because it was not clear whether participants who received laparoscopic surgery were similar to those who had open surgery. This makes the findings unreliable. Well-designed randomised controlled trials are necessary to obtain high-quality evidence on the best method to perform oesophagectomy." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Fifteen trials involving 2022 people were included. Compared to placebo, haloperidol was more effective at reducing manic symptoms, both as monotherapy (Weighted Mean Difference (WMD) -5.85, 95% Confidence Interval (CI) -7.69 to -4.00) and as adjunctive treatment to lithium or valproate (WMD -5.20, 95% CI -9.26 to -1.14). There was a statistically significant difference, with haloperidol being less effective than aripiprazole (Relative Risk (RR) 1.45, 95% CI 1.22 to 1.73). No significant differences between haloperidol and risperidone, olanzapine, carbamazepine or valproate were found. Compared with placebo, a statistically significant difference in favour of haloperidol in failure to complete treatment (RR 0.74, 95% Cl 0.57 to 0.96) was reported. Haloperidol was associated with less weight gain than olanzapine (RR: 0.28, 95% CI 0.12 to 0.67), but with a higher incidence of tremor (RR: 3.01, 95% CI 1.55 to 5.84) and other movement disorders. There is some evidence that haloperidol is an effective treatment for acute mania. From the limited data available, there was no difference in overall efficacy of treatment between haloperidol and olanzapine or risperidone. Some evidence suggests that haloperidol could be less effective than aripiprazole. Referring to tolerability, when considering the poor evidence comparing drugs, clinicians and patients should consider different side effect profiles as an important issue to inform their choice.\nOutput:\n" }, { "from": "agent", "value": "Fifteen trials met the inclusion criteria and are included in the review. Interpretation of the results was hindered by the small total sample size and by the low quality of reporting of the included trials. There was some evidence that haloperidol was more efficacious than placebo in terms of reduction of manic and psychotic symptom scores, when used both as monotherapy and as add-on treatment to lithium or valproate. There is no evidence of difference in efficacy between haloperidol and risperidone, olanzapine, valproate, carbamazepine, sultopride and zuclopentixol. There was a statistically significant difference with haloperidol being probably less effective than aripiprazole. No comparative efficacy data with quetiapine, lithium or chlorpromazine were reported. Haloperidol caused more extrapyramidal symptoms (EPS) than placebo and more movement disorders and EPS but less weight gain than olanzapine. Haloperidol caused more EPS than valproate but no difference was found between haloperidol and lithium, carbamazepine, sultopride and risperidone in terms of side effects profile." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: A total of 43 trials were identified with 1673 participants. All trials used small patient numbers (average trial size of 39 participants); the methods of randomisation and concealment of allocation were poor or not stated in most trials. Blinded assessors were used in just over half of the trials and only 10 stated that they used intention-to-treat analysis. A wide variety of validated and customised outcome measures were used to assess the effectiveness of physiotherapy interventions. The most frequently reported physiotherapy outcomes were gait speed and timed up and go, in 19 and 15 trials respectively. Only five of the 43 trials reported data on falls (12%). The motor subscales of the Unified Parkinson’s Disease Rating Scale and Parkinson’s Disease Questionnaire-39 were the most commonly reported clinician-rated disability and patient-rated quality of life outcome measures, used in 22 and 13 trials respectively. The content and delivery of the physiotherapy interventions varied widely in the trials included within this review, so no quantitative meta-analysis could be performed. Considering the small number of participants examined, the methodological flaws in many of the studies, the possibility of publication bias, and the variety of interventions, formal comparison of the different physiotherapy techniques could not be performed. There is insufficient evidence to support or refute the effectiveness of one physiotherapy intervention over another in PD. This review shows that a wide range of physiotherapy interventions to treat PD have been tested . There is a need for more specific trials with improved treatment strategies to underpin the most appropriate choice of physiotherapy intervention and the outcomes measured.\nOutput:\n" }, { "from": "agent", "value": "Only randomised controlled trials were included in this review. These were studies where a group of participants were given one physiotherapy intervention and were compared with another group who received a different physiotherapy intervention. The participants were assigned to a group in a random fashion to reduce the potential for bias. A total of 43 randomised trials involving 1673 participants (average trial size of just 39 participants) were identified as suitable for this review. The trials assessed various physiotherapy interventions, so they were grouped according to the type of intervention being used (general physiotherapy, exercise, treadmill training, cueing, dance or martial arts). However, despite this grouping, the physiotherapy interventions delivered and the outcomes assessed varied so much that the results of the individual trials could not be combined. This review highlights that a wide range of different physiotherapy techniques have been tested to treat PD. Considering the small number of participants, the wide variety of physiotherapy interventions and the outcomes assessed, there is insufficient evidence to support the use of one approach of physiotherapy intervention over another for the treatment of PD." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Three double-blind, parallel group, randomised, controlled trials have been conducted on 263 patients. The two phase II studies were relatively small, were conducted over the short term (12 weeks), and used relatively low doses of ropinirole (mean administered doses 3.3 and 3.5 mg/d) in a twice daily regime. In view of this clinical heterogeneity and some statistical heterogeneity, the results of these trials have not been included in a meta-analysis. The conclusions of this review are based on the evidence from a single phase III study which was medium term (26 weeks) and used ropinirole doses in line with the current UK licensed maximum in a thrice daily regime. In view of difficulties in assessing changes in off time in Leiberman 98, caused by the initial imbalance between the arms of the trial, it is unsafe to draw any firm conclusion about the effect of ropinirole on off time. However, as an adverse event, dyskinesia was significantly increased in those who received ropinirole (Leiberman 98; odds ratio 2.90; 1.36, 6.19 95% CI; Table 8). Measurements of motor impairments and disability were poor in this study with incomplete information available. Levodopa dose could be reduced in Leiberman 98 with a significantly larger reduction on ropinirole than on placebo (weighted mean difference 180 mg/d; 106, 253 95% CI; Table 2). No significant differences in the frequency of adverse event reports were noted between ropinirole and placebo apart from the increase in dyskinesia with ropinirole. There was a trend towards fewer withdrawals from ropinirole in Leiberman 98 but this did not reach statistical significance. Ropinirole therapy can reduce levodopa dose but at the expense of increased dyskinetic adverse events. No clear effect on off time reduction was found but this may have been due to the under-powering of the single evaluable trial. Inadequate data on motor impairments and disability was collected to assess these outcomes. These conclusions apply to short and medium term treatment, up to 26 weeks. Further longer term trials are required, with measurements of effectiveness, and also studies to compare the newer with the older dopamine agonists.\nOutput:\n" }, { "from": "agent", "value": "Three trials have compared ropinirole with an inactive placebo in 263 patients in the later stages of Parkinson's disease. Two studies were relatively small, were conducted over the short term (12 weeks), and used relatively low doses of ropinirole (maximum allowed 8 and 10 mg/d) in a twice daily administration regime. For these reasons, the results of these trials have not been included in a statistical overview. The other study was medium term (26 weeks) and used ropinirole doses in line with the current UK licensed maximum (24 mg/d) in a three times a day regime. The conclusions of this review are based on this single trial and thus should be viewed with some caution. No clear difference in the time patients spent in the immobile off state was found between ropinirole and placebo. However, this was probably due to there being too few patients in the trial. Measurements of physical difficulties and problems with activities of daily living (such as bathing, shopping, etc.) were poor in these studies with incomplete information available. Levodopa dose reduction was greater with ropinirole than placebo by 180 mg/d. However, dyskinesia was increased in those who received ropinirole (2.9 times more common with ropinirole than placebo). No other differences in side effects or withdrawals from treatment were found. Ropinirole reduces levodopa dose but at the expense of increased dyskinetic side effects. No clear effect on off time reduction was found in this single trial. Side effects were similar with ropinirole and placebo. These conclusions apply to short and medium term treatment, up to 26 weeks. Further longer term trials are required, with measurements of quality of life and costs, and also studies to compare the newer with the older dopamine agonists." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included two RCTs and four CRCTs involving 352 physicians, 48 residents, and 135 allied health practitioners. Overall risk of bias was low as was quality of the evidence. One comparison was supported by three studies and three comparisons were supported by single studies, but outcomes across the three studies were highly heterogeneous. We found no studies to support EHI versus no alternative. Given these factors, it was not possible to determine the relative effectiveness of interventions. All studies reported practitioner use of EHI, two reported on compliance with electronic practice guidelines, and none reported on patient outcomes. One trial (139 participants) measured guideline adherence for an electronic versus printed guideline, but reported no difference between groups (median OR 0.85, IQR 0.74 to 1.08). One small cross-over trial (10 participants) reported increased use of clinical guidelines when provided with a mobile versus stationary, desktop computer (mean use per shift: intervention group (IG) 3.6, standard deviation (SD) 1.7 vs. control group (CG) 2.0 (SD 1.9), P value = 0.033). One cross-over trial (203 participants) reported that using a customized versus a generic interface had little impact on practitioners' use of EHI (mean difference in adjusted end-of-study rate: 0.77 logins/month/user, 95% confidence interval (CI) CI 0.43 to 1.11). Three trials included education or training and reported increased use of EHI by practitioners following training. This review provided no evidence that the use of EHI translates into improved clinical practice or patient outcomes, though it does suggest that when practitioners are provided with EHI and education or training, the use of EHI increases. We have defined use as the activity of logging into an EHI resource, but based on our findings use does not automatically translate to the application of EHI in practice. While using EHI may be an important component of evidence-based medicine, alone it is insufficient to improve patient care or clinical practices. For EHI to be applied in patient care, it will be necessary to understand why practitioners' are reluctant to apply EHI when treating people, and to determine the most effective way(s) to reduce this reluctance.\nOutput:\n" }, { "from": "agent", "value": "We found six studies involving 535 healthcare practitioners. The studies examined strategies encouraging practitioners to use EHI when caring for patients. We measured practitioners' use of EHI by counting the number of times they logged onto it; by measuring whether or not practitioners' followed the guidance provided by EHI; and by improvements experienced by patients. The studies compared the following strategies: EHI versus printed information (one study); EHI on a \"mobile\" (e.g. laptop computer) versus a stationary, desktop computer (one study); EHI presented with different search interfaces (an interface is what a user sees when accessing an online resource, think of Google versus Yahoo) (one study); and EHI provided with training (three studies). The results of this review showed that when provided with a combination of EHI and training, practitioners used the information more often. Two studies measured doctors' use of electronic treatment guidelines, but showed that the electronic aspect of the guidelines did not mean that doctors followed the guidelines. This review provided no information on whether more frequent use of EHI translated into improved clinical practice or whether patients were better off when doctors or nurses used health information when treating them. All included studies were randomized controlled trials (clinical studies where people are randomly put into one of two or more treatment groups), which are considered high-quality sources of evidence. However, three of the four comparisons that we examined were supported by only one study each and single studies do not typically produce high-quality evidence. Overall, we rate the body of evidence in this review as low quality." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included only one study in this review, which compared two surgical interventions: pedicled buccal fat pad flap and buccal flap for the treatment of oro-antral communications. The study involved 20 participants. The risk of bias was unclear. The relevant outcome reported in this trial was successful (complete) closure of oro-antral communication. The quality of the evidence for the primary outcome was very low. The study did not find evidence of a difference between interventions for the successful (complete) closure of an oro-antral communication (RR 1.00, 95% Cl 0.83 to 1.20) one month after the surgery. All oro-antral communications in both groups were successfully closed so there were no adverse effects due to treatment failure. We did not find trials evaluating any other intervention for treating oro-antral communications or fistulae due to dental procedures. We found very low quality evidence from a single small study that compared pedicled buccal fat pad and buccal flap. The evidence was insufficient to judge whether there is a difference in the effectiveness of these interventions as all oro-antral communications in the study were successfully closed by one month after surgery. Large, well-conducted RCTs investigating different interventions for the treatment of oro-antral communications and fistulae caused by dental procedures are needed to inform clinical practice.\nOutput:\n" }, { "from": "agent", "value": "We searched various databases until 23 May 2018. Only one study, which was conducted in Iran, is included in our review. The study ran for two years and involved 20 people with OAC aged between 25 and 56 years. Participants were divided into two groups and two surgical treatments were compared for treating oro-antral communications; one group was treated with pedicled buccal fat pad flap (PBFPF) and the other with buccal flap (BF). The study did not find evidence of a difference between PBFPF and BF in terms of successful (complete) closure of OAC. Both interventions resulted in successful closure by one month after surgery. The study did not therefore report any adverse effects of treatment failure. It may not be possible to generalise these findings because the quality of the evidence was very low, due to unclear risk of bias and the small numbers studied in the single included trial. The evidence currently available is insufficient to draw reliable conclusions regarding the effects of interventions used to treat OAC or fistulae due to dental procedures. More well-designed and well-reported trials evaluating different interventions are needed to provide reliable evidence to inform clinical decisions." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We identified only one randomized controlled trial that met our inclusion criteria and no further trials were identified in subsequent updates. The included study was a trial of moderate intensity, endurance type exercise versus 'usual activities' in 25 patients with amyotrophic lateral sclerosis. The risk of bias was high and no adverse events were reported. At three months patients performing the 15 minute twice daily exercises had significantly less spasticity overall (mean reduction of -0.43, 95% confidence interval (CI) -1.03 to +0.17 in the treatment group versus an increase of +0.25, 95% CI -0.46 to +0.96 in control) but the mean change between groups was not significant (-0.68, 95% CI -1.62 to +0.26), as measured by the Ashworth scale (possible scores 0 to 5, where higher is worse). The single trial performed was too small to determine whether individualized moderate intensity endurance type exercises for the trunk and limbs are beneficial or harmful. No other medical, surgical or alternative treatment and therapy has been evaluated in a randomized fashion in this patient population. More research is needed.\nOutput:\n" }, { "from": "agent", "value": "This review found only one randomized trial of treatment for spasticity in motor neuron disease, which involved 25 participants, and no further trials have been found in subsequent updates. There were a number of issues with the design of the study which unfortunately reduced the certainty of the findings. At three months participants performing the 15 minute twice daily exercises had significantly less spasticity overall than control participants (mean reduction of -0.43, 95% confidence interval (CI) -1.03 to +0.17 in the treatment group versus an increase of +0.25, 95% CI -0.46 to +0.96 in control) but the mean change between groups was not significant, as measured by the Ashworth scale (a scale of spasticity, with a range of 0 to 5, where higher is worse). The trial was too small to determine whether individualized moderate intensity endurance type exercises for the trunk and limbs are beneficial or harmful. No side effects from exercise were reported. No other randomized trials of different treatments or therapies were found. Further research is needed to determine if exercise or other therapies such as anti-spasticity medication are beneficial or harmful." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included five RCTs (285 participants). Three studies were included in the original review and two more in the update. The authors of the included studies reported benefits of acupuncture in managing pancreatic cancer pain; no difference between real and sham electroacupuncture for pain associated with ovarian cancer; benefits of acupuncture over conventional medication for late stage unspecified cancer; benefits for auricular (ear) acupuncture over placebo for chronic neuropathic pain related to cancer; and no differences between conventional analgesia and acupuncture within the first 10 days of treatment for stomach carcinoma. All studies had a high risk of bias from inadequate sample size and a low risk of bias associated with random sequence generation. Only three studies had low risk of bias associated with incomplete outcome data, while two studies had low risk of bias associated with allocation concealment and one study had low risk of bias associated with inadequate blinding. The heterogeneity of methodologies, cancer populations and techniques used in the included studies precluded pooling of data and therefore meta-analysis was not carried out. A subgroup analysis on acupuncture for cancer-induced bone pain was not conducted because none of the studies made any reference to bone pain. Studies either reported that there were no adverse events as a result of treatment, or did not report adverse events at all. There is insufficient evidence to judge whether acupuncture is effective in treating cancer pain in adults.\nOutput:\n" }, { "from": "agent", "value": "We searched a wide range of electronic medical databases up to July 2015 for relevant studies. We included studies written in any language that included adults and compared treatment with acupuncture for cancer pain against no treatment, or usual treatment, or sham acupuncture, or other treatments. Since we were only interested in robust research, we restricted our search to randomised controlled trials (in which participants are randomly allocated to the methods being tested). We found five studies (with a total of 285 participants) that compared acupuncture against either sham acupuncture or pain-killing medicines. All five identified studies had small sample sizes, which reduces the quality of their evidence. One pilot study was well designed, but was too small to identify any differences in pain in women with ovarian cancer after electroacupuncture or a sham treatment. One study found that auricular (ear) acupuncture reduced cancer pain when compared with sham auricular acupuncture that was given at non-acupuncture points. However, the people in the sham acupuncture group could have been aware that they were not in the real acupuncture group and this could have affected the level of pain they reported. Another study found a difference between an electroacupuncture group and sham group in people with pancreatic cancer but again, there was no reported attempt to conceal which group people were in. One study found that acupuncture was as effective as pain-killing medication, and one study found that acupuncture was more effective than medication, but both studies were poorly designed and the study reports lacked detail. None of the studies described in this review were big enough to produce reliable results. None of the studies reported any harm to the participants. We conclude that there is insufficient evidence to judge whether acupuncture is effective in relieving cancer pain in adults. Larger, well-designed studies are needed to provide evidence in this area." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: The 18 included trials tested seven comparisons in a total of 2615 mainly female and older participants with a total of 2619 fractures. All trials had methodological flaws that may affect the validity of their results. Three trials of 355 participants comparing a fixed nail plate (Jewett or McLaughlin) with the sliding hip screw (SHS) found an increased risk of fixation failure for fixed nail plates. The two trials of 433 participants comparing the Resistance Augmented Bateaux (RAB) plate with the SHS had contrasting results, notably in terms of operative complications, fixation failure and anatomical restoration. One trial of 100 participants comparing the Pugh nail and the SHS found no significant difference between implants. Three trials of 458 participants compared the Medoff plate with the SHS. There was a trend to higher blood losses and longer operation times for the Medoff plate along with a trend to a lower risk of fixation failure with the Medoff plate for unstable trochanteric fractures. Two trials of 676 participants compared the Medoff plate with three different screw-plate systems. There were no statistically significant differences in outcome for trochanteric fractures. For subtrochanteric fractures, there was a lower fixation failure rate for the Medoff plate but no evidence for differences in longer-term outcomes. Four trials of 396 participants comparing the Gotfried percutaneous compression plate (PCCP) with a SHS found a trend to lower blood loss and transfusion requirements for the PCCP but no other confirmed differences in outcomes between implants. Three of the trials reported intra-operative problems with the PCCP, some of which precluded its use. Three trials of 200 participants comparing external fixation with a SHS found less operative trauma for the external fixation. Final outcome appeared similar. The markedly increased fixation failure rate of fixed nail plates compared with the SHS is a major consideration and thus the SHS appears preferable. There was insufficient evidence from other comparisons of extramedullary implants or on the use of external fixators to draw definite conclusions.\nOutput:\n" }, { "from": "agent", "value": "The 18 randomised controlled trials included in this review tested seven comparisons in a total of 2615 mainly female and older participants. All trials had methodological flaws that may affect the validity of their results and there was a general lack of evidence on long-term effects and functional recovery. Some extramedullary implants appeared to be associated with an increased risk of fixation complications and reoperation. In particular, three trials comparing a fixed nail plate (Jewett or McLaughlin) with the sliding hip screw (the 'standard' extramedullary device for these fractures) found an increased risk of fixation failure for fixed nail plates. Less invasive implants, such as the external fixator, which require smaller incisions resulted in less blood loss and often quicker operations than the sliding hip screw. We concluded that the sliding hip screw seems preferable to older types of fixed nail plates given their high rate of implant and fixation failure. However, there was not enough evidence to draw conclusions for other comparisons of extramedullary implants or on the use of external fixators." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included one randomised controlled trial involving 64 participants with schizophrenia or schizoaffective disorder. The average age of participants was 54 years; participants had been living with type 2 diabetes for on average nine years, and with their psychiatric diagnosis since they were on average 28 years of age. Investigators evaluated the 24-week Diabetes Awareness and Rehabilitation Training (DART) programme in comparison with usual care plus information (UCI). Follow-up after trial completion was six months. Risk of bias was mostly unclear but was high for selective reporting. Trial authors did not report on diabetes-related complications, all-cause mortality, adverse events, health-related quality of life nor socioeconomic effects. Twelve months of data on self care behaviours as measured by total energy expenditure showed a mean of 2148 kcal for DART and 1496 kcal for UCI (52 participants; very low-quality evidence), indicating no substantial improvement. The intervention did not have a substantial effect on glycosylated haemoglobin A1c (HbA1c) at 6 or 12 months of follow-up (12-month HbA1c data 7.9% for DART vs 6.9% for UCI; 52 participants; very low-quality evidence). Researchers noted small improvements in body mass index immediately after the intervention was provided and at six months, along with improved weight post intervention. Diabetes knowledge and self efficacy improved immediately following receipt of the intervention, and knowledge also at six months. The intervention did not improve blood pressure. Evidence is insufficient to show whether type 2 diabetes self management interventions for people with severe mental illness are effective in improving outcomes. Researchers must conduct additional trials to establish efficacy, and to identify the active ingredients in these interventions and the people most likely to benefit from them.\nOutput:\n" }, { "from": "agent", "value": "We identified one study, which recruited 64 adults with type 2 diabetes and schizophrenia or schizoaffective disorder. Researchers compared usual care plus information leaflets with a 24-week education programme delivered once a week for 90 minutes (Diabetes Awareness and Rehabilitation Training). This programme provided basic diabetes education and information about nutrition and exercise. The average age of participants was 54 years; participants had been living with type 2 diabetes for on average nine years and with their psychiatric diagnosis since they were on average 28 years old. People in the included study were monitored for six months after the programme ended. This evidence is up to date as of 07 March 2016. In summary, few studies have evaluated the effects of diabetes self management programmes for adults with severe mental illness. Study authors of the single included study did not report diabetes-related complications, all-cause mortality, adverse events, health-related quality of life nor socioeconomic effects. They described small improvements in body mass index and body weight, as well as in diabetes knowledge and self efficacy. Current evidence is insufficient to show that these types of programmes can help people with type 2 diabetes and severe mental illness to better manage their diabetes and its consequences. We rated the overall quality of the evidence as very low, mainly because of the small numbers of included studies and participants, and because reported study results showed inconsistency." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Of 39 identified studies, four met the criteria for inclusion. Two of the included studies reported a significant decrease in paediatric burn and scald injury in the intervention compared with the control communities. The failure of the other two studies to show a positive result may have been due to limited time-frame for the intervention and/or failure to adequately implement the counter-measures in the communities. There are a very limited number of research studies allowing conclusions to be drawn about the effectiveness of community-based injury prevention programmes to prevent burns and scalds in children. There is a pressing need to evaluate high-quality community-based intervention programmes based on efficacious counter-measures to reduce burns and scalds in children. It is important that a framework for considering the problem of burns and scalds in children from a prevention perspective be articulated, and that an evidence-based suite of interventions be combined to create programme guidelines suitable for implementation in communities throughout the world.\nOutput:\n" }, { "from": "agent", "value": "The efficacy of this approach is difficult to assess and there have been few research studies of good quality. The current review sought to review studies evaluating the success of community-based programmes specifically intended to reduce burn and scald injury in children. Only four studies were identified that met the inclusion criteria and two of these found a reduction in rates of burns and scalding. More high-quality research studies are needed in this area, therefore, to support the continued use of the community approach." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Six trials involving 907 patients were identified. For 'death (all causes)' the Peto odds ratio of 0.77 with a 95% confidence interval (CI) of 0.48 to 1.24 did not show a statistically significant difference between both treatment groups. For 'stroke (any)' the Peto odds ratio of 0.58 (95% CI: 0.34 to 0.98) indicated a statistically significant benefit in favour of antiplatelet drugs (P = 0.04). For 'vascular death', 'stroke or vascular death', 'serious vascular events', 'death or dependency', 'myocardial infarction', 'major extracranial haemorrhage', 'local haemorrhage requiring surgery', 'restenosis', 'TIA or amaurosis fugax', neither any benefit nor any hazard of antiplatelet drugs could be shown. For the outcome events 'intracranial haemorrhage', 'ischaemic stroke' and 'occurrence or progression of contralateral stenosis', data were either too sparse for meaningful analyses, or not available at all. Our results may indicate that antiplatelet drugs did not significantly change the odds of death but reduce the outcome 'stroke of any cause' in patients undergoing carotid endarterectomy. However, it can not be excluded that the beneficial effect in reducing stroke is due to chance. There is a suggestion that antiplatelets may increase the odds of haemorrhage, but there are currently too few data to quantify this effect.\nOutput:\n" }, { "from": "agent", "value": "This review showed that antiplatelet drugs can also reduce the risk of stroke in patients undergoing carotid endarterectomy. There was limited information on bleeding risk. The review's conclusions supported the routine use of antiplatelet drugs such as aspirin in patients having carotid endarterectomy." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Seventeen trials with 1067 participants met the inclusion criteria. However, the required data from three included trials and some of the data from a fourth trial were not published and not made available. The included trials were highly heterogeneous in terms of subtype and severity of participants' dementia, and type, duration, and frequency of exercise. Only two trials included participants living at home. Our meta-analysis revealed that there was no clear evidence of benefit from exercise on cognitive functioning. The estimated standardized mean difference between exercise and control groups was 0.43 (95% CI -0.05 to 0.92, P value 0.08; 9 studies, 409 participants). There was very substantial heterogeneity in this analysis (I² value 80%), most of which we were unable to explain, and we rated the quality of this evidence as very low. We found a benefit of exercise programs on the ability of people with dementia to perform ADLs in six trials with 289 participants. The estimated standardized mean difference between exercise and control groups was 0.68 (95% CI 0.08 to 1.27, P value 0.02). However, again we observed considerable unexplained heterogeneity (I² value 77%) in this meta-analysis, and we rated the quality of this evidence as very low. This means that there is a need for caution in interpreting these findings. In further analyses, in one trial we found that the burden experienced by informal caregivers providing care in the home may be reduced when they supervise the participation of the family member with dementia in an exercise program. The mean difference between exercise and control groups was -15.30 (95% CI -24.73 to -5.87; 1 trial, 40 participants; P value 0.001). There was no apparent risk of bias in this study. In addition, there was no clear evidence of benefit from exercise on neuropsychiatric symptoms (MD -0.60, 95% CI -4.22 to 3.02; 1 trial, 110 participants; P value .0.75), or depression (SMD 0.14, 95% CI -0.07 to 0.36; 5 trials, 341 participants; P value 0.16). We could not examine the remaining outcomes, quality of life, mortality, and healthcare costs, as either the appropriate data were not reported, or we did not retrieve trials that examined these outcomes. There is promising evidence that exercise programs may improve the ability to perform ADLs in people with dementia, although some caution is advised in interpreting these findings. The review revealed no evidence of benefit from exercise on cognition, neuropsychiatric symptoms, or depression. There was little or no evidence regarding the remaining outcomes of interest (i.e., mortality, caregiver burden, caregiver quality of life, caregiver mortality, and use of healthcare services).\nOutput:\n" }, { "from": "agent", "value": "This review evaluated the results of 17 trials (search dates August 2012 and October 2013), including 1,067 participants, that tested whether exercise programs could improve cognition (which includes such things as memory, reasoning ability and spatial awareness), activities of daily living, behaviour and psychological symptoms (such as depression, anxiety and agitation) in older people with dementia. We also looked for effects on mortality, quality of life, caregivers' experience and use of healthcare services, and for any adverse effects of exercise. There was some evidence that exercise programs can improve the ability of people with dementia to perform daily activities, but there was a lot of variation among trial results that we were not able to explain. The studies showed no evidence of benefit from exercise on cognition, psychological symptoms, and depression. There was little or no evidence regarding the other outcomes listed above. There was no evidence that exercise was harmful for the participants. We judged the overall quality of evidence behind most of the results to be very low. Additional well-designed trials would allow us to enhance the quality of the review by investigating the best type of exercise program for people with different types and severity of dementia and by addressing all of the outcomes." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included 10 trials in the review. Generally, we were unable to assess methodological quality; only one trial reported sufficient detail for analysis. Drugs used were piracetam, bifemalane, piribedil, bromocriptine, idebenone, and Dextran 40. We found weak evidence that patients were more likely to have improved on any language measure at the end of the trial if they had received treatment with piracetam (odds ratio (OR) 0.46, 95% confidence interval (CI) 0.3 to 0.7). Patients who were treated with piracetam were no more likely than those who took a placebo to experience unwanted effects, including death (OR 1.29, 95% CI 0.9 to 1.7). However, the differences in death rates between the two groups give rise to some concerns that there may be an increased risk of death from taking piracetam. We could not determine if drug treatment is more effective than speech and language therapy. We could not determine whether one drug is more effective than another. Drug treatment with piracetam may be effective in the treatment of aphasia after stroke. Further research is needed to explore the effects of drugs for aphasia, in particular piracetam. The safety of the drug should be of primary interest. Researchers should examine the long-term effects and whether it is more effective than speech and language therapy.\nOutput:\n" }, { "from": "agent", "value": "This review of 10 studies evaluated six different drugs. The only drug for which there was any evidence of benefit was piracetam, but the evidence of benefit was weak and there were concerns about its safety. It was not possible to conclude whether piracetam was more effective than speech and language therapy in treating aphasia after stroke. More research is needed into the effects of piracetam on aphasia, and its safety, before it can be recommended for routine use." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: The 19 included trials (involving 1589 older adults) were small, often with methodological flaws. Just two pairs of trials tested similar interventions. Twelve trials evaluated mobilisation strategies started soon after hip fracture surgery. Single trials found improved mobility from, respectively, a two-week weight-bearing programme, a quadriceps muscle strengthening exercise programme and electrical stimulation aimed at alleviating pain. Single trials found no significant improvement in mobility from, respectively, a treadmill gait retraining programme, 12 weeks of resistance training, and 16 weeks of weight-bearing exercise. One trial testing ambulation started within 48 hours of surgery found contradictory results. One historic trial found no significant difference in unfavourable outcomes for weight bearing started at two versus 12 weeks. Of two trials evaluating more intensive physiotherapy regimens, one found no difference in recovery, the other reported a higher level of drop-out in the more intensive group. Two trials tested electrical stimulation of the quadriceps: one found no benefit and poor tolerance of the intervention; the other found improved mobility and good tolerance. Seven trials evaluated strategies started after hospital discharge. Started soon after discharge, two trials found improved outcome after 12 weeks of intensive physical training and a home-based physical therapy programme respectively. Begun after completion of standard physical therapy, one trial found improved outcome after six months of intensive physical training, one trial found increased activity levels from a one year exercise programme, and one trial found no significant effects of home-based resistance or aerobic training. One trial found improved outcome after home-based exercises started around 22 weeks from injury. One trial found home-based weight-bearing exercises starting at seven months produced no significant improvement in mobility. There is insufficient evidence from randomised trials to establish the best strategies for enhancing mobility after hip fracture surgery.\nOutput:\n" }, { "from": "agent", "value": "This review includes evidence from 19 trials involving 1589 participants, generally aged over 65 years. Many of the trials had weak methods, including inadequate follow-up. There was no pooling of data because no two trials were sufficiently alike. Twelve trials evaluated interventions started soon after hip fracture surgery. Single trials found improved mobility from, respectively, a two-week weight-bearing programme, a quadriceps muscle strengthening exercise programme and electrical stimulation aimed at alleviating pain. Single trials found no significant improvement in mobility from, respectively, a treadmill gait retraining programme, 12 weeks of resistance training, and 16 weeks of weight-bearing exercise. One trial testing ambulation started within 48 hours of surgery found contradictory results. One historic trial found no significant difference in unfavourable outcomes for weight bearing started at two versus 12 weeks. Of two trials evaluating more intensive physiotherapy regimens, one found no difference in recovery, the other reported a higher level of drop-out in the more intensive group. Two trials tested electrical stimulation of the quadriceps: one found no benefit and poor tolerance of the intervention; the other found improved mobility and good tolerance. Seven trials evaluated interventions started after hospital discharge. Started soon after discharge, two trials found improved outcome after 12 weeks of intensive physical training and a home-based physical therapy programme respectively. Begun after completion of standard physical therapy, one trial found improved outcome after six months of intensive physical training, one trial found increased activity levels from a one year exercise programme, and one trial found no significant effects of home-based resistance or aerobic training. One trial found improved outcome after home-based exercises started around 22 weeks from injury. One trial found home-based weight-bearing exercises starting at seven months produced no significant improvement in mobility. In summary, the review found there was not enough evidence to determine which are the best strategies, started in hospital or after discharge from hospital, for helping people walk and continue walking after hip fracture surgery." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included 12 RCTs (743 people). Among these RCTs, flexibility exercise training was compared to an untreated control group, land-based aerobic training, resistance training, or other interventions (i.e. Tai Chi, Pilates, aquatic biodanza, friction massage, medications). Studies were at risk of selection, performance, and detection bias (due to lack of adequate randomization and allocation concealment, lack of participant or personnel blinding, and lack of blinding for self-reported outcomes). With the exception of withdrawals and adverse events, major outcomes were self-reported and were expressed on a 0-to-100 scale (lower values are best, negative mean differences (MDs) indicate improvement). We prioritized the findings of flexibility exercise training compared to land-based aerobic training and present them fully here. Very low-certainty evidence showed that compared with land-based aerobic training, flexibility exercise training (five trials with 266 participants) provides no clinically important benefits with regard to HRQoL, pain intensity, fatigue, stiffness, and physical function. Low-certainty evidence showed no difference between these groups for withdrawals at completion of the intervention (8 to 20 weeks). Mean HRQoL assessed on the Fibromyalgia Impact Questionnaire (FIQ) Total scale (0 to 100, higher scores indicating worse HRQoL) was 46 mm and 42 mm in the flexibility and aerobic groups, respectively (2 studies, 193 participants); absolute change was 4% worse (6% better to 14% worse), and relative change was 7.5% worse (10.5% better to 25.5% worse) in the flexibility group. Mean pain was 57 mm and 52 mm in the flexibility and aerobic groups, respectively (5 studies, 266 participants); absolute change was 5% worse (1% better to 11% worse), and relative change was 6.7% worse (2% better to 15.4% worse). Mean fatigue was 67 mm and 71 mm in the aerobic and flexibility groups, respectively (2 studies, 75 participants); absolute change was 4% better (13% better to 5% worse), and relative change was 6% better (19.4% better to 7.4% worse). Mean physical function was 23 points and 17 points in the flexibility and aerobic groups, respectively (1 study, 60 participants); absolute change was 6% worse (4% better to 16% worse), and relative change was 14% worse (9.1% better to 37.1% worse). We found very low-certainty evidence of an effect for stiffness. Mean stiffness was 49 mm to 79 mm in the flexibility and aerobic groups, respectively (1 study, 15 participants); absolute change was 30% better (8% better to 51% better), and relative change was 39% better (10% better to 68% better). We found no evidence of an effect in all-cause withdrawal between the flexibility and aerobic groups (5 studies, 301 participants). Absolute change was 1% fewer withdrawals in the flexibility group (8% fewer to 21% more), and relative change in the flexibility group compared to the aerobic training intervention group was 3% fewer (39% fewer to 55% more). It is uncertain whether flexibility leads to long-term effects (36 weeks after a 12-week intervention), as the evidence was of low certainty and was derived from a single trial. Very low-certainty evidence indicates uncertainty in the risk of adverse events for flexibility exercise training. One adverse effect was described among the 132 participants allocated to flexibility training. One participant had tendinitis of the Achilles tendon (McCain 1988), but it is unclear if the tendinitis was a pre-existing condition. When compared with aerobic training, it is uncertain whether flexibility improves outcomes such as HRQoL, pain intensity, fatigue, stiffness, and physical function, as the certainty of the evidence is very low. Flexibility exercise training may lead to little or no difference for all-cause withdrawals. It is also uncertain whether flexibility exercise training has long-term effects due to the very low certainty of the evidence. We downgraded the evidence owing to the small number of trials and participants across trials, as well as due to issues related to unclear and high risk of bias (selection, performance, and detection biases). While flexibility exercise training appears to be well tolerated (similar withdrawal rates across groups), evidence on adverse events was scarce, therefore its safety is uncertain.\nOutput:\n" }, { "from": "agent", "value": "We searched the literature up to December 2017 and found 12 studies (743 individuals) that met our inclusion criteria. Flexibility interventions were compared with control (treatment as usual), aerobic training interventions (e.g. treadmill walking), resistance-training interventions (e.g. using weight machines that provide resistance to movement), and other interventions (e.g. Pilates). The average age of participants was 48.6 years. Trials were conducted in seven countries, and most studies (58.3%) included only female participants. Exercise trials ranged from 4 to 20 weeks. The stretching exercise programs ranged from 40 to 60 minutes, 1 to 3 times a day. The intensity of the stretches (e.g. how far the stretch was taken in the available range of motion) was not reported in most cases. The time each stretch was held ranged from 6 to 60 seconds. The targeted muscles were usually of both the upper and lower extremities, neck, and back. The flexibility training was either supervised or done at home. Our main comparison was flexibility exercise versus land-based aerobic training. Key results at the end of treatment for our main comparison Compared with land-based aerobic exercise training, flexibility exercise resulted in little benefit at 8 to 20 weeks' follow-up. Each measure below was measured on a scale from 0 to 100, with lower scores better. Health-related quality of life: People who received flexibility exercise training were 4% worse (ranging from 6% better to 14% worse). • People who had flexibility training rated their quality of life as 46 points. • People who had aerobic training rated their quality of life as 42 points. Pain intensity: People who received flexibility exercise training were 5% worse (ranging from 1% better to 11% worse). • People who had flexibility training rated their pain as 57 points. • People who had aerobic training rated their pain as 52 points. Fatigue: People who received flexibility exercise training were 4% better (ranging from 13% better to 5% worse). • People who had flexibility training rated their fatigue as 67 points. • People who had aerobic training rated their fatigue as 71 points. Stiffness: People who received flexibility exercise training were 30% better (ranging from 8% better to 51% better). • People who had flexibility training rated their stiffness as 49 points. • People who had aerobic training rated their stiffness as 79 points. Physical function: People who received flexibility exercise training were 6% worse (ranging from 4% better to 16% worse). • People who had flexibility training rated their physical function as 23 points. • People who had aerobic training rated their physical function as 17 points. Withdrawal from treatment A total of 18 per 100 people dropped out of the flexibility exercise training group for any reason compared to 19 per 100 people from the aerobic training group. Harms We found no clear information on harms. One study reported that one participant had swelling (tendinitis) of an ankle tendon (Achilles), but it is unclear if this was related to participation in the flexibility exercise. Quality of evidence The evidence does not show that flexibility exercise significantly improves health-related quality of life, pain, fatigue, or physical function. The number of people dropping out from each group was similar. Although the evidence suggests that flexibility exercise improves stiffness, caution is advised in interpretation of these results, as this improvement was seen in only one study with very few participants. We considered the overall certainty of the evidence to be low to very low due to study design issues, the small number of participants, and low certainty of results." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Six RCTs ranging from 8 to 26 weeks investigating 1450 participants met the inclusion criteria. Overall, the risk of bias of these trials was unclear or high. All RCTs compared the effects of colesevelam with or without other antidiabetic drug treatments with placebo only (one study) or combined with antidiabetic drug treatments. Colesevelam with add-on antidiabetic agents demonstrated a statistically significant reduction in fasting blood glucose with a mean difference (MD) of -15 mg/dL (95% confidence interval (CI) -22 to - 8), P < 0.0001; 1075 participants, 4 trials, no trial with low risk of bias in all domains. There was also a reduction in glycosylated haemoglobin A1c (HbA1c) in favour of colesevelam (MD -0.5% (95% CI -0.6 to -0.4), P < 0.00001; 1315 participants, 5 trials, no trial with low risk of bias in all domains. However, the single trial comparing colesevelam to placebo only (33 participants) did not reveal a statistically significant difference between the two arms - in fact, in both arms HbA1c increased. Colesevelam with add-on antidiabetic agents demonstrated a statistical significant reduction in low-density lipoprotein (LDL)-cholesterol with a MD of -13 mg/dL (95% CI -17 to - 9), P < 0.00001; 886 participants, 4 trials, no trial with low risk of bias in all domains. Non-severe hypoglycaemic episodes were infrequently observed. No other serious adverse effects were reported. There was no documentation of complications of the disease, morbidity, mortality, health-related quality of life and costs. Colesevelam added on to antidiabetic agents showed significant effects on glycaemic control. However, there is a limited number of studies with the different colesevelam/antidiabetic agent combinations. More information on the benefit-risk ratio of colesevelam treatment is necessary to assess the long-term effects, particularly in the management of cardiovascular risks as well as the reduction in micro- and macrovascular complications of type 2 diabetes mellitus. Furthermore, long-term data on health-related quality of life and all-cause mortality also need to be investigated.\nOutput:\n" }, { "from": "agent", "value": "A total of 1450 patients took part in six studies investigating colesevelam. These studies lasted 8 to 26 weeks. Only one small study compared colesevelam directly to placebo, the other five studies investigated a combination of colesevelam with other antidiabetic agents versus a combination of placebo with other antidiabetic agents. There were no two studies with the same intervention and comparison group. When added to other antidiabetic agents colesevelam showed improvements in the control of blood glucose and blood lipids. However, it is difficult to disentangle the effects of colesevelam from the other antidiabetic agents used because only one study compared colesevelam to placebo. The same is true for adverse effects: three studies reported on just a few non-severe hypoglycaemic episodes, no other serious side effects were observed. No study investigated mortality; complications of type 2 diabetes such as eye disease, kidney disease, heart attack and stroke; health-related quality of life; functional outcomes and costs of treatment. Therefore, long-term data on the efficacy and safety of colesevelam are necessary." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Three trials involving a total of 404, mainly female and older, people with displaced fractures of the distal radius were included. These failed to assess functional outcome, and only one trial reported on complications. One trial found no statistically significant differences between mechanical reduction using finger trap traction and manual reduction in anatomical outcomes. All participants of this trial were given intravenous regional anaesthesia. One trial compared a novel method of manual reduction where the non-anaesthetised patient actively provided counter-traction versus traditional manual reduction under intravenous regional anaesthesia. While participants of the novel method group suffered more, yet not intolerable, pain during the reduction procedure, the latter was shorter in duration. No differences in anatomical outcome were detected. The third study compared mechanical reduction involving a special device without anaesthesia versus manual reduction under haematoma block (local anaesthesia). Less pain during the reduction procedure was recorded for the mechanical traction group. Both methods yielded similar radiological results. Fewer participants of the mechanical traction group had signs of neurological impairment, mainly finger numbness, at five weeks but this difference was not statistically significant by one year. There was insufficient evidence from comparisons tested within randomised controlled trials to establish the relative effectiveness of different methods of closed reduction used in the treatment of displaced fractures of the distal radius in adults.\nOutput:\n" }, { "from": "agent", "value": "Three randomised controlled trials involving a total of 404, mainly female and older, people with displaced fractures of the distal radius are included in this review. None of the trials assessed functional outcome, and only one trial reported on complications. Each trial compared different methods of reduction. One trial, in which all participants had intravenous regional anaesthesia, found no significant differences in anatomical outcomes between mechanical reduction using finger trap traction and manual reduction. The second trial compared two methods of manual reduction. These were a novel method of manual reduction where participants actively provided counter-traction without being given anaesthesia versus traditional manual reduction under intravenous regional anaesthesia. The participants of the novel method group suffered more but not intolerable pain during the reduction procedure, which was shorter in duration. No differences in anatomical outcome were detected. The third trial compared mechanical reduction involving a special device without anaesthesia versus manual reduction under haematoma block (local anaesthesia). Less pain during the reduction procedure was recorded for the mechanical traction group. Both methods yielded similar anatomical results. Fewer participants of the mechanical traction group had signs of neurological impairment, mainly finger numbness, at five weeks but this difference was not statistically significant by one year. The review concluded that there was not enough evidence to decide whether there was any difference between the various methods tested." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included eight studies involving 353 children in the review. These studies reported different types of interventions (lignocaine or bupivacaine), observation times, and forms of measuring and describing the outcomes, making it difficult to conduct meta-analyses. In the comparison of infraorbital nerve block versus placebo, there was a large effect in mean postoperative pain scores (our first primary outcome) favouring the intervention group (standardised mean difference (SMD) -3.54, 95% confidence interval (CI) -6.13 to -0.95; very low-quality evidence; 3 studies; 120 children). Only one study reported the duration of analgesia (in hours) (second primary outcome) with a difference favouring the intervention group (mean difference (MD) 8.26 hours, 95% CI 5.41 to 11.11; very low-quality evidence) and less supplemental analgesic requirements in the intervention group (risk ratio (RR) 0.05, 95% CI 0.01 to 0.18; low-quality evidence). In the comparison of infraorbital nerve block versus intravenous analgesia, there was a difference favouring the intervention group in mean postoperative pain scores (SMD -1.50, 95% CI -2.40 to -0.60; very low-quality evidence; 2 studies; 107 children) and in the time to feeding (MD -9.45 minutes, 95% CI -17.37 to -1.53; moderate-quality evidence; 2 studies; 128 children). No significant adverse events (third primary outcome) were associated with the intervention, although three studies did not report this outcome. Five out of eight studies found no unwanted side effects after the nerve blocks. Overall, the included studies were at low or unclear risk of bias. The reasons for downgrading the quality of the evidence using GRADE related to the lack of information about randomisation methods and allocation concealment in the studies, very small sample sizes, and heterogeneity of outcome reporting. There is low- to very low-quality evidence that infraorbital nerve block with lignocaine or bupivacaine may reduce postoperative pain more than placebo and intravenous analgesia in children undergoing cleft lip repair. Further studies with larger samples are needed. Future studies should standardise the observation time and the instruments used to measure outcomes, and stratify children by age group.\nOutput:\n" }, { "from": "agent", "value": "We included eight studies with a total of 353 boys and girls, who ranged in age from 1 month to 13 years. These studies had been published up to June 2015. Three studies compared nerve block with sham block. Three studies compared nerve block with injected analgesics, and two studies compared nerve block with local anaesthesia. The children who received the infraorbital nerve block (with lignocaine or bupivacaine) had less pain and more time between finishing surgery and needing more analgesics. These children also had less need for analgesics than those who received the sham block. The children who received the infraorbital nerve block also had less pain and were able to eat sooner than those who received injected (intravenous) analgesics. The nerve block did not appear to alter heart rate, breath rate, and blood pressure. Five out of eight studies found no unwanted side effects after the nerve blocks; the other three studies did not mention side effects. The overall quality of the evidence was low or very low due to the small number of children included in the studies and differences between the studies (heterogeneity) regarding the types of intervention, the observation time, and the forms of measuring and describing the outcomes. Further studies with larger numbers of children are needed." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Combining data from 425 reports (307,028 abstracts) resulted in an overall full publication proportion of 37.3% (95% confidence interval (CI), 35.3% to 39.3%) with varying lengths of follow-up. This is significantly lower than that found in our 2007 review (44.5%. 95% CI, 43.9% to 45.1%). Using a survival analyses to estimate the proportion of abstracts that would be published in full by 10 years produced proportions of 46.4% for all studies; 68.7% for randomized and controlled trials and 44.9% for other studies. Three hundred and fifty-three reports were at high risk of bias on one or more items, but only 32 reports were considered at high risk of bias overall. Forty-five reports (15,783 abstracts) with 'positive' results (defined as any 'significant' result) showed an association with full publication (RR = 1.31; 95% CI 1.23 to 1.40), as did 'positive' results defined as a result favoring the experimental treatment (RR =1.17; 95% CI 1.07 to 1.28) in 34 reports (8794 abstracts). Results emanating from randomized or controlled trials showed the same pattern for both definitions (RR = 1.21; 95% CI 1.10 to 1.32 (15 reports and 2616 abstracts) and RR = 1.17; 95% CI, 1.04 to 1.32 (13 reports and 2307 abstracts), respectively. Other factors associated with full publication include oral presentation (RR = 1.46; 95% CI 1.40 to 1.52; studied in 143 reports with 115,910 abstracts); acceptance for meeting presentation (RR = 1.65; 95% CI 1.48 to 1.85; 22 reports with 22,319 abstracts); randomized trial design (RR = 1.51; 95% CI 1.36 to 1.67; 47 reports with 28,928 abstracts); and basic research (RR = 0.78; 95% CI 0.74 to 0.82; 92 reports with 97,372 abstracts). Abstracts originating at an academic setting were associated with full publication (RR = 1.60; 95% CI 1.34 to 1.92; 34 reports with 16,913 abstracts), as were those considered to be of higher quality (RR = 1.46; 95% CI 1.23 to 1.73; 12 reports with 3364 abstracts), or having high impact (RR = 1.60; 95% CI 1.41 to 1.82; 11 reports with 6982 abstracts). Sensitivity analyses excluding reports that were abstracts themselves or classified as having a high risk of bias did not change these findings in any important way. In considering the reports of the methodology research that we included in this review, we found that reports published in English or from a native English-speaking country found significantly higher proportions of studies published in full, but that there was no association with year of report publication. The findings correspond to a proportion of abstracts published in full of 31.9% for all reports, 40.5% for reports in English, 42.9% for reports from native English-speaking countries, and 52.2% for both these covariates combined. More than half of results from abstracts, and almost a third of randomized trial results initially presented as abstracts fail to be published in full and this problem does not appear to be decreasing over time. Publication bias is present in that 'positive' results were more frequently published than 'not positive' results. Reports of methodology research written in English showed that a higher proportion of abstracts had been published in full, as did those from native English-speaking countries, suggesting that studies from non-native English-speaking countries may be underrepresented in the scientific literature. After the considerable work involved in adding in the more than 300 additional studies found by the February 2016 searches, we chose not to update the search again because additional searches are unlikely to change these overall conclusions in any important way.\nOutput:\n" }, { "from": "agent", "value": "We included 425 research reports described in 551 articles, which had studied the subsequent full publication of 307,028 abstracts from a variety of biomedical and social sciences. Fifty-four reports included data from abstracts describing randomized or controlled trials. Of the 425 reports, 376 were published in English, and 49 in other languages. 1. Less than half of all studies, and about two-thirds of randomized trials, initially presented as summaries or abstracts at meetings, are published as journal articles in the 10 years after presentation. 2. Studies with positive results are more likely to be published. 3. Studies with larger sample sizes are more likely to be published. 4. Studies with abstracts presented orally are more likely to be published than those presented as posters. 5. Studies accepted for presentation at a meeting are more likely to be published than those not accepted. 6. Studies describing basic science are more likely to be published that those describing clinical research. 7. Studies describing randomized trials are more likely to be published than those describing other types of studies. 8. Studies that took place in multiple centers are more likely to be published than those at a single center. 9. Studies classified as ‘high quality’ are more likely to be published than ‘low quality’ studies. 10. Studies with authors from an academic setting are more likely to be published than those with authors from other settings. 11. Studies considered by the report authors to have a high impact are more likely to be published than other studies. 12. Studies with funding source reported are more likely to be published than those not reporting funding. 13. Studies originating in North America or Europe are more likely to be published than those originating elsewhere. 14. Studies from English-speaking countries are more likely to be published than studies originating elsewhere. We have confidence in our findings. We considered five criteria to constitute a risk of bias in the included reports, including methods to identify and match full publications to abstracts, and methods to determine whether a factor was associated with full publication. Overall, 7.5% (32/425) of the reports were scored as having an overall high risk of bias, 83.1% (353/425) had at least one criterion at high risk of bias, and 6.1% (26/425) had all criteria at low risk of bias. Our search updated our 2007 review and is current to February 2016. After the considerable work involved in including more than 300 additional studies from the February 2016 searches, we chose not to update the search again because additional searches are unlikely to change our overall conclusions in any important way." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included seven trials reported in 30 references in the review (354 participants). In all trials, G-CSF was compared with placebo preparations. Dosage of G-CSF varied among studies, ranging from 2.5 to 10 microgram/kg/day. Regarding overall risk of bias, data regarding the generation of randomization sequence and incomplete outcome data were at a low risk of bias; however, data regarding binding of personnel were not conclusive. The rate of mortality was not different between the two groups (RR 0.64, 95% CI 0.15 to 2.80, P = 0.55). Regarding safety, the limited amount of evidence is inadequate to reach any conclusions regarding the safety of G-CSF therapy. Moreover, the results did not show any beneficial effects of G-CSF in patients with AMI regarding left ventricular function parameters, including left ventricular ejection fraction (RR 3.41, 95% CI -0.61 to 7.44, P = 0.1), end systolic volume (RR -1.35, 95% CI -4.68 to 1.99, P = 0.43) and end diastolic volume (RR -4.08, 95% CI -8.28 to 0.12, P = 0.06). It should also be noted that the study was limited since the trials included lacked long enough follow up durations. Limited evidence from small trials suggested a lack of benefit of G-CSF therapy in patients with AMI. Since data of the risk of bias regarding blinding of personnel were not conclusive, larger RCTs with appropriate power calculations and longer follow up durations are required in order to address current uncertainties regarding the clinical efficacy and therapy-related adverse events of G-CSF treatment.\nOutput:\n" }, { "from": "agent", "value": "In this review, analysis of seven included studies with low risk of bias using G-CSF to improve the function of damaged heart of patient with heart attack failed to show any beneficial effects of this treatment. The rate of mortality was not different between the two groups (RR 0.64, 95% CI 0.15 to 2.80, P = 0.55). Also, left ventricular parameters including left ventricular ejection fraction (RR 3.41, 95% CI -0.61 to 7.44, P = 0.1), end systolic volume (RR -1.35, 95% CI -4.68 to 1.99, P = 0.43) and end diastolic volume (RR -4.08, 95% CI -8.28 to 0.12, P = 0.06) did not show significant changes between the treatment and the control groups. There was no evidence that the study was associated with serious adverse effects, however it should be noted that the study was limited since the trials included lacked long enough follow up durations. Additionally four studies had either high or unclear risk of bias for blinding. Therefore, based on the results of the current study, G-CSF treatment should not be administered for patients with heart attack." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Thirty-nine RCTs met the inclusion criteria contributing a total of 4615 participants. Most trials enrolled a small number of patients and showed moderate to poor (reporting of) methodological quality, in particular regarding allocation concealment and intention-to-treat analysis. Fifteen systemic acting prokinetic drugs were investigated and ten comparisons could be summarized. Six RCTs support the effect of Alvimopan, a novel peripheral mu receptor antagonist. However, the trials do not meet reporting guidelines and the drug is still in an investigational stage. Erythromycin showed homogenous and consistent absence of effect across all included trials and outcomes. The evidence is insufficient to recommend the use of cholecystokinin-like drugs, cisapride, dopamine-antagonists, propranolol or vasopressin. Effects are either inconsistent across outcomes, or trials are too small and often of poor methodological quality. Cisapride has been withdrawn from the market due to adverse cardiac events in many countries. Intravenous lidocaine and neostigmine might show a potential effect, but more evidence on clinically relevant outcomes is needed. Heterogeneity among included trials was seen in 10 comparisons. No major adverse drug effects were evident. Alvimopan may prove to be beneficial but proper judgement needs adherence to reporting standards. Further trials are needed on intravenous lidocaine and neostigmine. The remaining drugs can not be recommended due to lack of evidence or absence of effect.\nOutput:\n" }, { "from": "agent", "value": "Many of the 39 studies assessed in this review enrolled only a small number of patients and date back to before 1990. The novel drug alvimopan shortened bowel recovery, but many studies failed to report methodology according to current guidelines. Erythromycin, cholecystokinin, cisapride, dopamine-antagonists, propranolol or vasopressin are not supported due to lack of evidence or absence of effect. Intravenous lidocaine and neostigmine might show to be beneficial, but more evidence is needed." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We identified 3745 citations after de-duplication of search results and excluded 3619 records during title and abstract reviews. We assessed 126 full-text papers for inclusion in the review, of which four publications (on three RCTs) providing data from 1100 people met eligibility criteria for this review. All three RCTs had methodological limitations due to high attrition rates. Overall, moderate-quality evidence indicates that bupropion XL is an efficacious intervention for prevention of recurrence of depressive episodes in people with a history of SAD (risk ratio (RR) 0.56, 95% confidence interval (CI) 0.44 to 0.72; 3 RCTs, 1100 participants). However, bupropion XL leads to greater risk of headaches (moderate-quality evidence), insomnia and nausea (both low-quality evidence) when compared with placebo. Numbers needed to treat for additional beneficial outcomes (NNTBs) vary by baseline risks. For a population with a yearly recurrence rate of 30%, the NNTB is 8 (95% CI 6 to 12). For populations with yearly recurrence rates of 50% and 60%, NNTBs are 5 (95% CI 4 to 7) and 4 (95% CI 3 to 6), respectively. We could find no studies on other SGAs and no studies comparing SGAs with other interventions of interest, such as light therapy, psychological therapies, melatonin or agomelatine. Available evidence indicates that bupropion XL is an effective intervention for prevention of recurrence of SAD. Nevertheless, even in a high-risk population, three out of four people will not benefit from preventive treatment with bupropion XL and will be at risk for harm. Clinicians need to discuss with patients advantages and disadvantages of preventive SGA treatment, and might want to consider offering other potentially efficacious interventions, which might confer a lower risk of adverse events. Given the lack of comparative evidence, the decision for or against initiating preventive treatment of SAD and the treatment selected should be strongly based on patient preferences. Future researchers need to assess the effectiveness and risk of harms of SGAs other than bupropion for prevention of SAD. Investigators also need to compare benefits and harms of pharmacological and non-pharmacological interventions.\nOutput:\n" }, { "from": "agent", "value": "In populations with a high risk of developing a new depressive episode in the next winter, results show that antidepressants can prevent winter depression in about one in four people. In populations with a lower risk of recurrence, antidepressants can prevent a new depressive episode in one of eight people. The other seven people suffer from winter depression despite treatment or would not have suffered from winter depression anyway. People using antidepressants are at slightly higher risk of experiencing headaches, nausea or insomnia when compared with people not taking antidepressants. Doctors need to discuss with patients the advantages and disadvantages of antidepressants and other potentially preventive treatments for winter depression, such as light treatment, psychological therapies or lifestyle interventions. As no available studies have compared these treatments, the decision for or against preventive treatment of SAD and the treatment selected should be strongly based on patient preferences. Review authors recommend that future studies should directly compare antidepressants against other treatments, such as light therapy, psychological therapies or other drugs to determine the best treatment for preventing winter depression." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Six studies met the inclusion criteria, with a total of 334 adult participants. We identified no studies that included children as participants. All studies were affected by high risk of bias due to a lack of blinding of participants and personnel; five studies were affected by high risk of bias for lack of blinding of outcome assessors. There was high or unclear risk of biases affecting some studies across all the Cochrane risk of bias measures. Three studies compared a psychological intervention (either cognitive behaviour therapy or mindfulness-based cognitive therapy) with a control intervention. Data regarding depression symptom outcome measures were combined in a meta-analysis, but did not find an effect in favour of treatment (SMD -0.14; 95% CI -0.47 to 0.19; Z = 0.83; P = 0.41). The other comparisons comprised of single studies of depression symptoms and compared; cognitive behaviour therapy versus supportive psychotherapy (SMD -0.09; 95% CI -0.65 to 0.48; Z = 0.30; P = 0.77); repetitive transcranial magnetic stimulation plus tricyclic antidepressant (rTMS + TCA) versus tricyclic antidepressant alone (SMD -0.84; 95% CI -1.36 to -0.32; Z = 3;19, P = 0.001); and a supervised exercise program versus exercise as usual (SMD -0.43; 95% CI -0.88 to 0.03; Z = 1.84; P = 0.07). There was very-low quality evidence, small effect sizes and wide variability of results, suggesting that no comparisons showed a reliable effect for any intervention. Only one study mentioned minor, transient adverse events from repetitive transcranial magnetic stimulation. The review did not find compelling evidence in favour of any intervention. Future studies should focus on participants with a diagnosed TBI and include only participants who have a diagnosis of depression, or who record scores above a clinical cutoff on a depression measure. There is a need for additional RCTs that include a comparison between an intervention and a control that replicates the effect of the attention given to participants during an active treatment.\nOutput:\n" }, { "from": "agent", "value": "We found six studies, with a total of 334 adult participants. We found no studies that included people younger than 18 years of age. Four studies investigated psychological interventions. One study investigated an exercise intervention, and another investigated repetitive transcranial magnetic stimulation (rTMS). Three studies compared a psychological therapy (cognitive behaviour therapy or mindfulness-based cognitive therapy) with a no-treatment control intervention. When the data for these studies were combined, there was no reliable effect in support of psychological therapy. One study compared cognitive behavioural therapy with another psychological intervention (supportive psychotherapy), and did not find an effect in favour of either intervention. One study compared a supervised exercise programme with exercise as usual, but did not find a effect in favour of either intervention. One study compared rTMS plus an antidepressant medication with the antidepressant medication alone. Because the quality of the evidence was very low, it was not possible to draw the conclusion that the addition of rTMS improved outcomes. Only one study, of rTMS, reported any harmful effects and these were relatively minor and resolved quickly. The quality of the evidence was rated very low. All studies were at high risk of bias in some ways, and therefore it was not possible to draw conclusions in support of any intervention. There was a high degree of variability in the main results, which meant we could have little confidence in the findings. Some studies had major methodological flaws. It is not possible to recommend any particular treatment based on the current evidence. The review authors have made some recommendations to improve the quality of the evidence in future studies." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Twenty randomized trials were identified of which thirteen were included in the quantitative analysis with data from 1022 subjects. Although all agents were better than placebo, parenteral high dose methotrexate (not included), sulfasalazine, azathioprine and etretinate were the agents that achieved statistical significance in a global index of disease activity (although it should be noted that only one component variable was available for azathioprine and only one trial was available for etretinate suggesting some caution is necessary in interpreting these results). Analysis of response in individual disease activity markers was more variable with considerable differences between different medications and responses. In all trials the placebo group improved over baseline (pooled improvement 0.39 DI units, 95% CI 0.26-0.54). There was insufficient data to examine toxicity. Parenteral high dose methotrexate and sulfasalazine are the only two agents with well demonstrated published efficacy in psoriatic arthritis. The magnitude of the effect seen with azathioprine, etretinate, oral low dose methotrexate and perhaps colchicine suggests that they may be effective but that further multicentre clinical trials are required to establish their efficacy. Furthermore, the magnitude of the improvement observed in the placebo group strongly suggests that uncontrolled trials should not be used to guide management decisions in this condition.\nOutput:\n" }, { "from": "agent", "value": "The objective was to assess the benefits of the treatment [sulfasalazine, auranofin, etretinate, fumaric acid, IMI gold, azathioprine, methotrexate] for psoriatic arthritis and to assess the side effects. Parenteral methotrexate and sulfasalazine resulted in important benefit in over half the patients for psoriatic arthritis in these studies. There was insufficient data to evaluate other therapies and to examine toxicity. Further multicentre trials are required to establish the efficacy of azathioprine, oral methotrexate, etretinate, and colchicine." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We found no trials comparing one type of support versus another. We included seven RCTs (including one cluster-RCT) involving 831 women. The number of women in each trial ranged from 36 to 226. The trials were conducted in high-income countries: USA (5 trials); Denmark (1 trial) and Australia (1 trial), between 2006 and 2015. Three trials only included women who were obese prior to pregnancy and four trials included both women who were overweight and women who were obese. We judged risk of bias in the included trials to be mixed; only one trial was judged to be low risk of bias for random sequence generation, allocation concealment and attrition bias. Physical breastfeeding support (manual or electric breast pump) versus usual care (no breast pump) Very low-certainty evidence from one small trial (39 women) looking at a physical support intervention (manual or electric breast pump) versus usual care (no pump) means it is unclear whether physical support improves exclusive breastfeeding at four to six weeks (risk ratio (RR) 0.55, 95% confidence interval (CI) 0.20 to 1.51) or any breastfeeding at four to six weeks (RR 0.65, 95% CI 0.41 to 1.03). The trial did not report other important outcomes of interest in this review: non-initiation of breastfeeding, exclusive or any breastfeeding at six months postpartum. Multiple methods of breastfeeding support versus usual care Six trials (involving 792 women) used multiple methods of support including education and social support through telephone or face-to-face contact. One of these trials also provided physical support through providing a breast pump and a baby sling and one trial provided a small gift to the women at each trial visit. Support in the trials was provided by a professional (four trials) or a peer (two trials). One trial provided group support, with the other five trials supporting women individually. One trial (174 women) did not report on any of our main outcomes of interest. We are unclear about the effects of the intervention because we identified very low-certainty evidence for all of the important outcomes in this review: rate of non-initiation of breastfeeding (average RR 1.03, 95% CI 0.07 to 16.11; 3 trials, 380 women); exclusive breastfeeding at four to six weeks (average RR 1.21, 95% CI 0.83 to 1.77; 4 trials, 445 women); any breastfeeding at four to six weeks (average RR 1.04, 95% CI 0.57 to 1.89; 2 trials, 103 women); rate of exclusive breastfeeding at six months postpartum (RR 7.23, 95% CI 0.38 to 137.08; 1 trial, 120 women); and any breastfeeding at six months postpartum (average RR 1.42, 95% CI 1.08 to 1.87; 2 trials, 223 women). The included trials under the above comparisons also reported on some of this review's secondary outcomes but very low-certainty evidence means that we are unclear about the effects of the intervention on those outcomes. There is insufficient evidence to assess the effectiveness of physical interventions, or multiple methods of support (social, educational or physical) for supporting the initiation or continuation of breastfeeding in women who are overweight or obese. We found no RCTs comparing one type of support to another type of support. All of our GRADE assessments resulted in very low-certainty evidence, with downgrading decisions based on limitations in trial design (e.g. risk of attrition bias), imprecision, inconsistency. The available trials were mostly of variable quality with small numbers of participants, confounded by poor adherence within both the intervention and control groups. Well designed, adequately powered research is needed to answer questions about the social, educational, physical support, or any combination of these interventions that could potentially help mothers who are overweight or obese to achieve optimal breastfeeding outcomes. We need trials that examine interventions designed specifically for women who are overweight or obese, delivered by people with training about how to overcome some of the challenges these women face when establishing and maintaining breastfeeding. Particular attention could be given to the assessment of antenatal interventions aimed at improving breastfeeding initiation in women with a raised BMI, and not just focusing on recruiting women who have an intention to breastfeed. Given that the majority of current trials were undertaken in the USA, further trials in a diverse range of countries and settings are required. Future trials need to give consideration to the theoretical basis of the intervention using established frameworks to enable replicability by others and to better determine the components of effective interventions.\nOutput:\n" }, { "from": "agent", "value": "We searched for evidence (January 2019) and identified seven randomised controlled trials (RCTs), involving 831 women (range 36 to 226 women), conducted in high-income countries (USA, Denmark, Australia) between 2006 and 2015. Three trials only included women who were obese prior to pregnancy and four trials included women who were overweight and women who were obese. The trials compared different types of breastfeeding support to usual care. There were a limited number of trials for each type of support, and differences in how much support the women received in the support and usual care groups. One trial (39 women) used a physical support intervention through the loan of an electric or manual breast pump versus usual care (no pump). Very low-certainty evidence means it is unclear whether physical support improves exclusive breastfeeding at four to six weeks; or any breastfeeding at four to six weeks. The trial did not report other important outcomes of interest: non-initiation of breastfeeding, and exclusive or any breastfeeding at six months after birth. Six trials (792 women) used multiple methods of support (including education and social support through telephone or face-to-face contact) versus usual care. One trial (174 women) did not report on any of our main outcomes of interest. One of the trials also provided physical support through providing a breast pump and a baby sling, and another provided a small gift to the women at each trial visit. Support in these trials was provided by a professional (four trials) or a peer (two trials), either in a group (one trial) or individually (five trials). For women receiving an intervention that incorporated multiple methods of support (including social, educational or physical support) versus usual care, we are unclear about the effects of the intervention because we identified very low-certainty evidence for all of the important outcomes in this review: rate of non-initiation of breastfeeding; exclusive breastfeeding at four to six weeks; any breastfeeding at four to six weeks; rate of exclusive breastfeeding at six months after birth; and any breastfeeding at six months after birth. The effectiveness of interventions for supporting women who are overweight or obese to start and continue breastfeeding remains unclear. The methods used by the available trials varied in quality, with small numbers of participants. No trials compared one type of support to another. We need high-quality trials to evaluate whether social, educational, physical support, or any combination of these interventions can give mothers who are overweight or obese the best chance of starting and continuing to breastfeed. The interventions need to be designed specifically for this group of women and delivered by people who understand the challenges these women face when establishing and maintaining breastfeeding." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Five studies met our inclusion criteria; all were retrospective observational studies and therefore at high risk of bias. Meta-analysis of three studies assessing over 9000 women suggested that institutions with gynaecologic oncologists on site may prolong survival in women with ovarian cancer, compared to community or general hospitals: hazard ratio (HR) of death was 0.90 (95% confidence interval (CI) 0.82 to 0.99). Similarly, another meta-analysis of three studies assessing over 50,000 women, found that teaching centres or regional cancer centres may prolong survival in women with any gynaecological cancer compared to community or general hospitals (HR 0.91; 95% CI 0.84 to 0.99). The largest of these studies included all gynaecological malignancies and assessed 48,981 women, so the findings extend beyond ovarian cancer. One study compared community hospitals with semi-specialised gynaecologists versus general hospitals and reported non-significantly better disease-specific survival in women with ovarian cancer (HR 0.89; 95% CI 0.78 to 1.01). The findings of included studies were highly consistent. Adverse event data were not reported in any of the studies. We found low quality, but consistent evidence to suggest that women with gynaecological cancer who received treatment in specialised centres had longer survival than those managed elsewhere. The evidence was stronger for ovarian cancer than for other gynaecological cancers. Further studies of survival are needed, with more robust designs than retrospective observational studies. Research should also assess the quality of life associated with centralisation of gynaecological cancer care. Most of the available evidence addresses ovarian cancer in developed countries; future studies should be extended to other gynaecological cancers within different healthcare systems.\nOutput:\n" }, { "from": "agent", "value": "We used a set of tests to ensure that the evidence the five studies identified reached the quality standard for our analysis.The analysis of three studies combined (meta-analysis), assessing over 9000 women, suggested that institutions with gynaecologic oncologists (specialists in the field of gynaecological cancer treatment) on site may prolong the lives of women with ovarian cancer compared to community or general hospitals. Similarly, another meta-analysis of three studies which assessed well over 50,000 women, found evidence to suggest that teaching centres or regional cancer centres (specialised centres) may prolong the lives of women with gynaecological cancer compared to community or general hospitals. The largest study in this meta-analysis assessed all gynaecological cancers in 48,981 women, so it had major influence on the final result; this means that our findings are likely to be relevant to other gynaecological cancers, besides ovarian cancer. Overall, the findings suggest that centralisation of care may prolong the lives of women with gynaecological cancer, and in particular ovarian cancer. However, the results should be interpreted with caution as all of the studies included in the review could be biased. For example, it is possible that the patients who were treated in specialised centres were less ill to begin with. Another weakness of the review is that only one of the studies included women with gynaecological cancers other than ovarian cancer. Ideally, further studies in this area are needed.  New studies should be designed to avoid the possibility of bias due to the treatment of women at specialist and non-specialist centres being systematically different. Additionally, studies should assess the impact of centralisation of care on the quality of life of patients. Most of the available evidence was about ovarian cancer in developed countries; future studies should be extended to other gynaecological cancers and to less developed countries." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Psychological interventions as a group The SMD for symptom score improvement at 2 and 3 months was 0.97 (95% CI 0.29 to 1.65) and 0.62 (95% CI 0.45 to 0.79) respectively compared to usual care. Against placebo, the SMDs were 0.71 (95% CI 0.08 to 1.33) and -0.17 (95% CI -0.45 to 0.11) respectively. For improvement of abdominal pain, the SMDs at 2 and 3 months were 0.54 (95%CI 0.10 to 0.98) and 0.26 (95% CI 0.07 to 0.45) compared to usual care. The SMD from placebo at 3 months was 0.31 (95% CI -0.16 to 0.79). For improvement in quality of life, the SMD from usual care at 2 and 3 months was 0.47 (95%CI 0.11 to 0.84) and 0.31 (95%CI -0.16 to 0.77) respectively. Cognitive behavioural therapy The SMD for symptom score improvement at 2 and 3 months was 0.75 (95% CI -0.20 to 1.70) and 0.58 (95% CI 0.36 to 0.79) respectively compared to usual care. Against placebo, the SMDs were 0.68 (95% CI -0.01 to 1.36) and -0.17 (95% CI -0.45 to 0.11) respectively. For improvement of abdominal pain, the SMDs at 2 and 3 months were 0.45 (95% CI 0.00 to 0.91) and 0.22 (95% CI -0.04 to -0.49) compared to usual care. Against placebo the SMD at 3 months was 0.33 (95% CI -0.16 to 0.82). For improvement in quality of life, the SMDs at 2 and 3 months compared to usual care were 0.44 (95% CI 0.04 to 0.85) and 0.92 (95% CI 0.07 to 1.77) respectively. Interpersonal psychotherapy The RR for adequate relief of symptoms was 2.02 (95% CI 1.13 to 3.62), RD 0.30 (95% CI 0.13 to 0.46), NNT 4 for comparison with care as usual. The SMD for improvement of symptom score was 0.35 (95% CI -0.75 to 0.05) compared with usual care. Relaxation/Stress management The SMD in symptom score improvement at 2 months was 0.50 (95%CI 0.02 to 0.98) compared with usual care. The SMD in improvement of abdominal pain at 3 months was 0.02 (95%CI -0.56 to 0.61) compared with usual care. Long term results Very few long term follow-up results were available. There was no convincing evidence that treatment effects were sustained following completion of treatment for any treatment modality. Psychological interventions may be slightly superior to usual care or waiting list control conditions at the end of treatment although the clinical significance of this is debatable. Except for a single study, these therapies are not superior to placebo and the sustainability of their effect is questionable. The meta-analysis was significantly limited by issues of validity, heterogeneity, small sample size and outcome definition. Future research should adhere to current recommendations for IBS treatment trials and should focus on the long-term effects of treatment.\nOutput:\n" }, { "from": "agent", "value": "In this review, the effectiveness of psychological therapies for adult patients with irritable bowel syndrome was evaluated. Studies involving cognitive behavioural therapy, interpersonal psychotherapy and relaxation therapy or stress management were reviewed. Although it is difficult to draw conclusions because of differences between studies and quality issues, the results suggest that cognitive behavioural therapy and interpersonal psychotherapy may be effective immediately after finishing treatment. It is unclear whether the effects of these therapies are sustained thereafter. These results have to be interpreted with caution as the quality of the studies was sub-optimal. Physicians should be aware of the limitations of these therapies and should choose an appropriate therapy based on the individual patient's characteristics." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Eleven studies (n = 927 participants) met our inclusion criteria. Eight studies compared CTA with IADSA (n = 526) and three studies compared MRA with IADSA (n = 401). Methodological quality varied considerably among studies, with partial verification bias in 7/11 (64%) and retrospective designs in 5/10 (50%). In studies of CTA, the pooled estimate of sensitivity was 0.95 (95% confidence interval (CI) 0.90 to 0.97) and specificity was 0.99 (95% CI 0.95 to 1.00). The results remained robust in a sensitivity analysis in which only studies evaluating adult patients (≥ 16 years of age) were included. In studies of MRA, the pooled estimate of sensitivity was 0.98 (95% CI 0.80 to 1.00) and specificity was 0.99 (95% CI 0.97 to 1.00). An indirect comparison of CTA and MRA using a bivariate model incorporating test type as one of the parameters failed to reveal a statistically significant difference in sensitivity or specificity between the two imaging modalities (P value = 0.6). CTA and MRA appear to have good sensitivity and specificity following ICH for the detection of intracranial vascular malformations, although several of the included studies had methodological shortcomings (retrospective designs and partial verification bias in particular) that may have increased apparent test accuracy.\nOutput:\n" }, { "from": "agent", "value": "This review looked at different tests used to identify blood vessel abnormalities in the brain. Intra-arterial digital subtraction angiography (IADSA) is the standard test used and involves positioning a tube, introduced through a blood vessel in the groin, into blood vessels near the brain. Dye is directly injected into the brain's blood vessels using this tube. Computed tomographic angiography (CTA) and magnetic resonance angiography (MRA) are newer tests that may be done without any injections (MRA) or only through an injection into the arm (CTA and MRA). This review investigated the accuracy of CTA or MRA, or both, compared with IADSA after intracerebral haemorrhage. We found eight studies (involving 526 participants) that compared CTA with IADSA and three studies (involving 401 participants) that compared MRA with IADSA. Both CTA and MRA appear to have good accuracy when compared with IADSA. However, the studies were small and were limited in many cases by their design. Further research that looks at accuracy, practicality, and costs is needed." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Eight trials recruiting a total of 637 infants met the inclusion criteria for the systematic review. The infants included in the review were mainly formula-fed term infants. The trials were of variable methodological quality. Formula-fed term infants with GOR on feed thickeners had nearly two fewer episodes of regurgitation per day (mean difference -1.97 episodes per day, 95% confidence interval (CI) -2.32 to -1.61; 6 studies, 442 infants, moderate-certainty evidence) and were 2.5 times more likely to be asymptomatic from regurgitation at the end of the intervention period (risk ratio 2.50, 95% CI 1.38 to 4.51; number needed to treat for an additional beneficial outcome 5, 95% CI 4 to 13; 2 studies, 186 infants, low-certainty evidence) when compared to infants with GOR on unthickened feeds. No studies reported failure to thrive as an outcome. We found low-certainty evidence based on 2 studies recruiting 116 infants that use of feed thickeners improved the oesophageal pH probe parameters of reflux index (i.e. percentage of time pH < 4), number of reflux episodes lasting longer than 5 minutes, and duration of longest reflux episode. No major side effects were reported with the use of feed thickeners. Information was insufficient to conclude which type of feed thickener is superior. Gastro-oesophageal reflux is a physiological self resolving phenomenon in infants that does not necessarily require any treatment. However, we found moderate-certainty evidence that feed thickeners should be considered if regurgitation symptoms persist in term bottle-fed infants. The reduction of two episodes of regurgitation per day is likely to be of clinical significance to caregivers. Due to the limited information available, we were unable to assess the use of feed thickeners in infants who are breastfeeding or preterm nor could we conclude which type of feed thickener is superior.\nOutput:\n" }, { "from": "agent", "value": "We examined the research published up to 22 November 2016. We found 8 clinical trials recruiting 637 babies up to 6 months of age who presented with symptoms of GOR. The recruited babies were mainly 'healthy' term babies (i.e. babies born within three weeks of the due date) who were bottle feeding. Three of the studies were funded by a pharmaceutical company, hence the quality of the evidence presented must be interpreted with caution. We found that term babies with GOR given feed thickeners had nearly two fewer reflux episodes per day. Babies with GOR were also 2.5 times more likely to have no reflux symptoms if feed thickeners were used. No studies reported information on failure to thrive (i.e. poor growth). We found that babies with GOR given feed thickeners showed an improvement in an important measure of acid reflux obtained from pH study. Reflux index (i.e. percentage of time of acidic reflux of pH < 4) was 5% lower in babies given feed thickeners. No major harms were reported in the eight studies. Due to study design limitations, we are moderately confident in the evidence for the reduction of two reflux episodes per day. Hence, feed thickeners can be useful in term babies who are bottle feeding and have troublesome GOR. We rated the quality of the evidence for the other outcomes as low due to the small number of studies with small numbers of babies recruited. Further research is needed to determine which type of feed thickener is better and whether feed thickeners are useful in babies with GOR who are breastfeeding or preterm." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We found 9 RCTs involving a total of 421 participants of which 6 were studies of egg and milk exclusion (N=288), 1 was a study of few foods (N=85) and 2 were studies of an elemental diet (N=48). There appears to be no benefit of an egg and milk free diet in unselected participants with atopic eczema. There is also no evidence of benefit in the use of an elemental or few-foods diet in unselected cases of atopic eczema. There may be some benefit in using an egg-free diet in infants with suspected egg allergy who have positive specific IgE to eggs - one study found 51% of the children had a significant improvement in body surface area with the exclusion diet compared to normal diet (RR 1.51, 95% CI 1.07 to 2.11) and change in surface area and severity score was significantly improved in the exclusion diet compared to the normal diet at the end of 6 weeks (MD 5.50, 95% CI 0.19 to 10.81) and end of treatment (MD 6.10, 95% CI 0.06 to12.14). Methodological difficulties have made it difficult to interpret these studies. Poor concealment of randomisation allocation, lack of blinding and high dropout rates without an intention-to-treat analysis indicates that these studies should be interpreted with great caution. There may be some benefit in using an egg-free diet in infants with suspected egg allergy who have positive specific IgE to eggs. Little evidence supports the use of various exclusion diets in unselected people with atopic eczema, but that may be because they were not allergic to those substances in the first place. Lack of any benefit may also be because the studies were too small and poorly reported. Future studies should be appropriately powered focusing on participants with a proven food allergy. In addition a distinction should be made between young children whose food allergies improve with time and older children/adults.\nOutput:\n" }, { "from": "agent", "value": "The general quality of the studies was poor. The main findings of the review suggest that there is some evidence from one study for the use of an egg-free diet in infants with a suspected egg allergy who have positive specific IgE antibodies to eggs in their blood. Other studies that compared a dietary exclusion with ordinary diets did not test the people taking part to see if they were allergic to the foods concerned. There appears to be little benefit in eliminating cows milk from the diet or using an elemental (liquid diet containing only amino acids, carbohydrates, fat, minerals and vitamins) or 'few foods diet' for improving atopic eczema in people who have not undergone any form of testing. Three of the studies used soya based substitute which itself can be allergenic to people with atopic eczema. Adhering to elimination diets is difficult. The studies were performed in different populations with only one study describing the severity of the atopic eczema. The clinical relevance of changes in severity scores obtained in many studies is unknown." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Five RCTs involving 895 sporadic and 52 familial ALS/MND participants were included. There was no statistical evidence for a differential response to treatment in participants with familial ALS/MND compared to those with sporadic ALS/MND. The pooled estimate of the hazard ratio for the interaction term (treatment x familial ALS) suggested a more beneficial response with respect to survival among participants with familial ALS/MND, but the result was not statistically significant. Pooled estimates of the rate of decline on the ALSFRS suggested a slightly better overall response to treatment among those with familial ALS/MND, but the result was not statistically significant. Based on the available data, there is little evidence for a differential response to treatment among people with familial and sporadic ALS/MND. Future randomized controlled trials should document whether people with familial ALS/MND are included and the presence or absence of a mutation in an ALS susceptibility gene amongst those with familial ALS/MND.\nOutput:\n" }, { "from": "agent", "value": "We identified all randomized controlled trials in ALS/MND and wrote to the authors to request the data needed to complete this review. Although many more studies were eligible for inclusion, only five authors were willing and able to share the data from their individual randomized controlled trials. Based on the analyses of these data, we find no evidence to support a statistically significant difference in the response to treatment between people with the familial and sporadic forms of ALS/MND." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Seven studies with a total of 578 patients were included in the first comparison: mean percentage of rebleeding in H. pylori eradication therapy group was 2.9%, and in the non-eradication therapy group without subsequent long-term maintenance antisecretory therapy it was 20% (OR 0.17, 95% CI 0.10 to 0.32; there was no statistical evidence of heterogeneity; NNT was 7, 95% CI 5 to 11). Three studies with a total of 470 patients were included in the second comparison: mean percentage of rebleeding in H. pylori eradication therapy group was 1.6%, and in non-eradication therapy group with long-term maintenance antisecretory therapy it was 5.6% (OR 0.24, 95% CI 0.09 to 0.67; heterogeneity was not demonstrated; NNT was 20, 95% CI 12 to 100). Subgroup analyses were carried out to examine the effect of NSAIDS and of excluding H.pylori eradication failures from the analyses. Treatment of H. pylori infection is more effective than antisecretory non-eradication therapy (with or without long-term maintenance antisecretory therapy) in preventing recurrent bleeding from peptic ulcer. All patients with peptic ulcer bleeding should be tested for H. pylori infection, and eradication therapy should be prescribed to H. pylori-positive patients.\nOutput:\n" }, { "from": "agent", "value": "The review found that, for people who have had a bleeding peptic ulcer caused by Helicobacter pylori, treatment with antibiotics more effectively prevents gastrointestinal re-bleeding than acid-suppressing drugs. Antibiotics when Helicobacter pylori infection is present are also cheaper and more convenient than long-term acid-suppressing drugs." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: The present updated review included 25 RCTs involving 3278 participants. The small number of trials in each comparison group and the heterogeneity of outcome measures precluded quantitative analysis of data for all but one outcome: pain intensity. In two pooled studies, the mean self-reported visual analogue scale (VAS; 0 to 100 mm) score for topical prilocaine-phenylephrine (PP) was higher than the mean self-reported VAS (0 to 100 mm) score for topical tetracaine-epinephrine-cocaine (TAC) by 5.59 points (95% confidence interval (CI) 2.16 to 13.35). Most trials that compared infiltrated and topical anaesthetics were at high risk of bias, which is likely to have affected their results. Researchers found that several cocaine-free topical anaesthetics provided effective analgesic efficacy. However, data regarding the efficacy of each topical agent are based mostly on single comparisons in trials with unclear or high risk of bias. Mild, self-limited erythematous skin induration occurred in one of 1042 participants who had undergone application of TAC. Investigators reported no serious complications among any of the participants treated with cocaine-based or cocaine-free topical anaesthetics. The overall quality of the evidence according to the GRADE system is low owing to limitations in design and implementation, imprecision of results and high probability of publication bias (selective reporting of data). Additional well-designed RCTs with low risk of bias are necessary before definitive conclusions can be reached. We have found two new studies published since the last version of this review was prepared. We have added these studies to those previously included and have conducted an updated analysis, which resulted in the same review conclusions as were presented previously. Mostly descriptive analysis indicates that topical anaesthetics may offer an efficacious, non-invasive means of providing analgesia before suturing of dermal lacerations. Use of cocaine-based topical anaesthetics might be hard to justify, given the availability of other effective topical anaesthetics without cocaine. However, the overall quality of the evidence according to the GRADE system is low owing to limitations in design and implementation, imprecision of results and high probability of publication bias (selective reporting of data). Additional well-designed RCTs with low risk of bias are necessary before definitive conclusions can be reached.\nOutput:\n" }, { "from": "agent", "value": "Study characteristics: The evidence is current to December 2016. We included in this review 25 randomized controlled trials involving 3278 participants. Studies included both adults and children. Fifteen of the included trials used self-reporting of pain intensity by trial participants to determine the effectiveness of local anaesthetics. Key results: Study results suggest that directly applying local anaesthetics to the skin is an effective, non-invasive way of providing pain control during suturing or stapling of skin lacerations. Study findings on the efficacy of individual topical anaesthetics were limited by study design, and data on the efficacy of each topical agent were obtained mostly from single trials. Researchers reported no serious side effects following the use of cocaine-containing or cocaine-free topical anaesthetics. The overall broadly comparable effectiveness of cocaine-free topical anaesthetics for skin laceration repair brings into question the necessity to include cocaine as a component of local anaesthetic solutions. The small number of trials in each comparison group and the range of outcome measures assessed prevented pooling and quantitative analysis of data for all but the single outcome of pain intensity. Additional studies are necessary to directly compare the effectiveness of different formulations of topical anaesthetics. Our review was limited to pain control for repair of superficial lacerations, and our results might not be generalizable to deeper lacerations or more complex procedures performed on intact skin. Further research is needed to strengthen the evidence and to overcome the weakness of the included studies. Quality of the evidence: The overall quality of the evidence was low owing to limitations in study design, ways that studies were carried out (implementation), imprecision of results and high probability of selective data reporting. Most of the trials that compared infiltrated and topical anaesthetics were at high risk of bias, and this was likely to influence measured effects." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included 70 RCTs with a total of 8461 participants randomised to either the intervention or control groups. The number of participants per trial ranged from 16 to 686. Fifty-five trials compared a behaviour-changing intervention with no treatment/usual care control and 15 evaluated the effectiveness of adding an additional component to a behaviour-changing intervention. Sixty-four trials were parallel RCTs, and four were cluster RCTs. Sixty-four trials were multicomponent, two were diet only and four were physical activity only interventions. Ten trials had more than two arms. The overall quality of the evidence was low or very low and 62 trials had a high risk of bias for at least one criterion. Total duration of trials ranged from six months to three years. The median age of participants was 10 years old and the median BMI z score was 2.2. Primary analyses demonstrated that behaviour-changing interventions compared to no treatment/usual care control at longest follow-up reduced BMI, BMI z score and weight. Mean difference (MD) in BMI was -0.53 kg/m2 (95% confidence interval (CI) -0.82 to -0.24); P < 0.00001; 24 trials; 2785 participants; low-quality evidence. MD in BMI z score was -0.06 units (95% CI -0.10 to -0.02); P = 0.001; 37 trials; 4019 participants; low-quality evidence and MD in weight was -1.45 kg (95% CI -1.88 to -1.02); P < 0.00001; 17 trials; 1774 participants; low-quality evidence. Thirty-one trials reported on serious adverse events, with 29 trials reporting zero occurrences RR 0.57 (95% CI 0.17 to 1.93); P = 0.37; 4/2105 participants in the behaviour-changing intervention groups compared with 7/1991 participants in the comparator groups). Few trials reported health-related quality of life or behaviour change outcomes, and none of the analyses demonstrated a substantial difference in these outcomes between intervention and control. In two trials reporting on minutes per day of TV viewing, a small reduction of 6.6 minutes per day (95% CI -12.88 to -0.31), P = 0.04; 2 trials; 55 participants) was found in favour of the intervention. No trials reported on all-cause mortality, morbidity or socioeconomic effects, and few trials reported on participant views; none of which could be meta-analysed. As the meta-analyses revealed substantial heterogeneity, we conducted subgroup analyses to examine the impact of type of comparator, type of intervention, risk of attrition bias, setting, duration of post-intervention follow-up period, parental involvement and baseline BMI z score. No subgroup effects were shown for any of the subgroups on any of the outcomes. Some data indicated that a reduction in BMI immediately post-intervention was no longer evident at follow-up at less than six months, which has to be investigated in further trials. Multi-component behaviour-changing interventions that incorporate diet, physical activity and behaviour change may be beneficial in achieving small, short-term reductions in BMI, BMI z score and weight in children aged 6 to 11 years. The evidence suggests a very low occurrence of adverse events. The quality of the evidence was low or very low. The heterogeneity observed across all outcomes was not explained by subgrouping. Further research is required of behaviour-changing interventions in lower income countries and in children from different ethnic groups; also on the impact of behaviour-changing interventions on health-related quality of life and comorbidities. The sustainability of reduction in BMI/BMI z score and weight is a key consideration and there is a need for longer-term follow-up and further research on the most appropriate forms of post-intervention maintenance in order to ensure intervention benefits are sustained over the longer term.\nOutput:\n" }, { "from": "agent", "value": "We found 70 randomised controlled trials (clinical trials where people are randomly put into one of two or more treatment groups) comparing diet, physical activity, and behavioural (where habits are changed or improved) treatments to a variety of control groups delivered to 8461 overweight or obese children aged 6 to 11 years. We reported on the effects of 64 multicomponent interventions (different combinations of diet and physical activity and behaviour change), four physical activity interventions and two dietary interventions compared with no intervention, 'usual care’ or some other therapy if it was also delivered in the intervention arm. The children in the included studies were followed up between six months and three years. The average age of the children was 10 years. Most studies reported the body mass index (BMI) z score: BMI is a measure of body fat and is calculated by dividing weight (in kilograms) by the square of the body height measured in metres (kg/m²). In children, BMI is often measured in a way that takes into account sex and age, weight, and height changes as children grow older (BMI z score). We summarised the results of 37 trials in 4019 children reporting the BMI z score, which on average was 0.06 units lower in the intervention groups compared with the control groups. We summarised the results of 24 trials in 2785 children reporting BMI, which on average was 0.53 kg/m2 lower in the intervention groups compared with the control groups. We summarised the results of 17 trials in 1774 children reporting weight, which on average was 1.45 kg lower in the intervention groups compared with the control groups. Other effects of the interventions, such as improvements in health-related quality of life were less clear. No study investigated death from any cause, morbidity or socioeconomic effects. Serious adverse events were rare: only two of 31 trials with data reported any serious adverse events (4/2105 participants in the behaviour-changing intervention groups compared with 7/1991 participants in the comparator groups). This evidence is up to date as of July 2016. The overall quality of the evidence was low or very low, mainly because of limited confidence in how studies were performed, and the results were inconsistent between the studies. Also there were just a few studies for some outcomes, with small numbers of included children." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included five RCTs involving 576 people. The trials were largely at low risk of bias, but we considered the quality of the evidence from these trials as moderate to low, largely due to imprecision from small sample sizes. Two out of the five trials reported on improvement in nerve function at one year. These two trials compared prednisolone with placebo. One trial, with 84 participants, treated mild sensory impairment of less than six months' duration, and the other, with 95 participants, treated nerve function impairment of 6 to 24 months' duration. There was no significant difference in nerve function improvement after 12 months between people treated with prednisolone and those treated with placebo. Adverse events were not reported significantly more often with corticosteroids than with placebo. The other three trials did not report on the primary outcome measure. One (334 participants) compared three corticosteroid regimens for severe type 1 reactions. No serious side effects of steroids were reported in any participant during the follow-up period. Another trial (21 participants) compared low-dose prednisone with high-dose prednisone for ulnar neuropathy. Two participants on the higher dose of prednisone reported adverse effects. The last (42 participants) compared intravenous methylprednisolone and oral prednisolone with intravenous normal saline and oral prednisolone. The trial found no significant differences between the groups in the occurrence of adverse events. Corticosteroids are used for treating acute nerve damage in leprosy, but moderate-quality evidence from two RCTs treating either longstanding or mild nerve function impairment did not show corticosteroids to have a superior effect to placebo on nerve function improvement. A third trial showed significant benefit from a five-month steroid regimen over a three-month regimen in terms of response to treatment (need for additional corticosteroids). Further RCTs are needed to establish optimal corticosteroid regimens and to examine the efficacy and safety of adjuvant or new therapies for treating nerve damage in leprosy. Future trials should address non-clinical aspects, such as costs and impact on quality of life, which are highly relevant indicators for both policymakers and participants.\nOutput:\n" }, { "from": "agent", "value": "We conducted a wide search for reports of clinical trials of treatments for nerve damage in leprosy. We found five clinical trials that met our criteria, involving 576 people with leprosy. Two of the included trials compared prednisolone with placebo. One of these trials, with 84 participants, recruited people who had mild abnormality of feeling of less than six months' duration and the other, with 95 participants, assessed treatment effects in people with abnormal nerve function of 6 to 24 months' duration. A third trial, with 334 participants, compared three 12-month corticosteroid regimens for severe type 1 reactions. Type 1 reactions are episodes in which nerves become inflamed. The fourth trial (21 participants) compared a low dose of prednisone with a high dose of prednisone for people with damage to the ulnar nerve (a nerve in the arm). The fifth trial (42 participants) compared intravenous methylprednisolone and oral prednisolone with intravenous normal saline and oral prednisolone in people with a type 1 leprosy reaction or abnormal nerve function of no more than six months' duration. There was no important difference in improvement in nerve function between people treated with prednisolone or with placebo after one year, according to two trials. More people on a three-month course of prednisolone failed to respond to treatment and required extra corticosteroids compared to people on either a high-dose or a low-dose regimen of five months' duration. The trials comparing corticosteroids with placebo and a trial comparing intravenous methylprednisolone and oral prednisolone with intravenous normal saline and oral prednisolone found no differences in the occurrence of adverse events between groups. We considered the quality of the evidence to be moderate to low. Although trials were well conducted and designed, they were largely small and did not always use proven measures to capture the effects of corticosteroids. The evidence in this review is up to date to June 2015." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: The experimental intervention was cup feeding and the control intervention was bottle feeding in all five studies included in this review. One study reported weight gain as g/kg/day and there was no statistically significant difference between the two groups (MD −0.60, 95% CI −3.21 to 2.01); while a second study reported weight gain in the first seven days as grams/day and also showed no statistically significant difference between the two groups (MD −0.10, 95% CI −0.36 to 0.16). There was substantial variation in results for the majority of breastfeeding outcomes, except for not breastfeeding at three months (three studies) (typical RR 0.83, 95% CI 0.71 to 0.97) which favoured cup feeding. Where there was moderate heterogeneity meta-analysis was performed: not breastfeeding at six months (two studies) (typical RR 0.83, 95% CI 0.72 to 0.95); not fully breastfeeding at hospital discharge (four studies) (typical RR 0.61, 95% CI 0.52 to 0.71). Two studies reported average time to feed which showed no difference between the two groups. Two studies assessed length of hospital stay and there was considerable variation in results and in the direction of effect. Only one study has reported gestational age at discharge, which showed no difference between the two groups (MD −0.10, 95% CI −0.54 to 0.34). As the majority of infants in the included studies are preterm infants, no recommendations can be made for cup feeding term infants due to the lack of evidence in this population. From the studies of preterm infants, cup feeding may have some benefits for late preterm infants and on breastfeeding rates up to six months of age. Self-reported breastfeeding status and compliance to supplemental interventions may over-report exclusivity and compliance, as societal expectations of breastfeeding and not wishing to disappoint healthcare professionals may influence responses at interview and on questionnaires. The results for length of stay are mixed, with the study involving lower gestational age preterm infants finding that those fed by cup spent approximately 10 days longer in hospital, whereas the study involving preterm infants at a higher gestational age, who did not commence cup feeding until 35 weeks' gestation, did not have a longer length of stay, with both groups staying on average 26 days. This finding may have been influenced by gestational age at birth and gestational age at commencement of cup feeding, and their mothers' visits; (a large number of mothers of these late preterm infants lived regionally from the hospital and could visit at least twice per week). Compliance to the intervention of cup feeding remains a challenge. The two largest studies have both reported non-compliance, with one study analysing data by intention to treat and the other excluding those infants from the analysis. This may have influenced the findings of the trial. Non-compliance issues need consideration before further large randomised controlled trials are undertaken as this influences power of the study and therefore the statistical results. In addition larger studies with better-quality (especially blinded) outcome assessment with 100% follow-up are needed.\nOutput:\n" }, { "from": "agent", "value": "Our search for eligible studies conducted on 31 January 2016 revealed five studies, all comparing cup and bottle feeding in newborn infants, which we were able to include in this review. These studies were conducted in neonatal and maternity units in hospitals in Australia, the United Kingdom, Brazil and Turkey. The mean gestational age of the infants in most of the studies were similar at the time of entry into the study. In four of the studies the intervention (cup or bottle) commenced from the time of enrolment into the study, when the infants first needed a supplemental feed and were as young as 30 weeks' gestation. In the study conducted in Turkey, supplemental feeding was not commenced on enrolment into the study and at the time of first supplemental feed but delayed until infants were at least 35 weeks of age. For some of the outcomes, the results of the different studies could not be combined. This included not breastfeeding at hospital discharge; not exclusively breastfeeding at three months and at six months; the average time taken for a feed; and the number of days spent in hospital. For each of these outcomes, the results from some studies favoured cup feeding, while the results from other studies favoured bottle feeding. For some of the outcomes, the results of the different studies could be combined: there was no difference in weight gain or gestational age at discharge between those infants who recieved supplemental feeds by cup compared to bottle. However those infants who received supplemental feeds by cup were more likely to be exclusively breastfeeding at hospital discharge and were more likely to be receiving some breastfeeds at three and six months of age. As the studies mostly included preterm infants and few term infants, no recommendations can be made for cup feeding term infants. The quality of evidence for weight gain, length of stay, not breastfeeding at hospital discharge and at six months of age and exclusively breastfeeding at hospital discharge and at six months of age is graded very low to low. In the studies included in this review, it is reported that many infants who were to receive supplemental feeds by cup received supplemental feeds by other means as either the parents or nurses did not like cup feeding." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Twenty-two trials (3142 episodes in 2372 patients) were included in the analyses. The mortality rate was similar when comparing oral to intravenous antibiotic treatment (RR 0.95, 95% CI 0.54 to 1.68, 9 trials, 1392 patients, median mortality 0, range 0% to 8.8%). Treatment failure rates were also similar (RR 0.96, 95% CI 0.86 to 1.06, all trials). No significant heterogeneity was shown for all comparisons but adverse events. The effect was stable in a wide range of patients. Quinolones alone or combined with another antibiotic were used with comparable results. Adverse reactions, mostly gastrointestinal, were more common with oral antibiotics. Based on the present data, oral treatment is an acceptable alternative to intravenous antibiotic treatment in febrile neutropenic cancer patients (excluding patients with acute leukaemia) who are haemodynamically stable, without organ failure, and do not have pneumonia, infection of a central line or a severe soft-tissue infection. The wide CI for mortality allows the present use of oral treatment in groups of patients with an expected low risk for mortality, and further research should be aimed at clarifying the definition of low risk patients.\nOutput:\n" }, { "from": "agent", "value": "This review of randomised controlled trials showed comparable death and failure rates for oral and intravenous antibiotics for low risk patients, those with solid tumours or chronic leukaemia or lymphoma, and independent of age, source of infection and severity of the neutropenia." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: No new trials were identified. This review includes two RCTs with low risk of bias that compared urinary human chorionic gonadotrophin (hCG) versus no treatment in anovulatory women receiving clomiphene citrate. Urinary hCG did not result in an increase in live birth rate over no hCG (OR 0.97, 95% CI 0.52 to 1.83; two trials, 305 participants, I2 = 16%; low-quality evidence), but very serious imprecision around the effect estimate reduces our confidence in the apparent lack of effect of hCG as an ovulation trigger in clomiphene-induced cycles in anovulatory women. Among this review's secondary outcomes, urinary hCG may not increase ovulation rate (OR 0.99, 95% CI 0.36 to 2.77; two trials, 305 participants, I2 = 55%; low-quality evidence), clinical pregnancy rate (OR 1.02, 95% CI 0.56 to 1.89; two trials, 305 participants, I2 = 35%; low-quality evidence) or miscarriage rate in pregnant women (OR 1.19, 95% CI 0.17 to 8.23; two trials, 54 participants, I2 = 0%; low-quality evidence). Multiple pregnancies and preterm deliveries were uncommon, and ovarian hyperstimulation syndrome, adverse events and deaths were not reported as outcomes in either trial. We found no trials evaluating other ovulation triggers. Evidence is inadequate to recommend or refute the use of urinary hCG as an ovulation trigger in anovulatory women treated with clomiphene citrate. We found no trials evaluating the use of ovulation triggers in anovulatory women treated with other ovulation-inducing agents.\nOutput:\n" }, { "from": "agent", "value": "The two studies included in this review randomly assigned 305 women being treated with clomiphene citrate to help eggs to develop to additionally receive a medicine (urinary hCG) to trigger their release or to receive no additional treatment. We found no trials comparing other ovulation triggers given with other medicines used for ovulation induction. The evidence is current to November 2013. Giving women on clomiphene citrate additional urinary hCG may not increase their chances of delivering live babies, ovulating or becoming pregnant. Multiple pregnancies, miscarriages and preterm deliveries were not more common with or without an ovulation trigger. No serious adverse events were reported in either study. We cannot be certain whether ovulation triggers are better or worse than no ovulation triggers in women undergoing ovulation induction because not enough women were included in the two trials for definite results to be obtained. Larger trials in women undergoing ovulation induction that compare different ovulation triggers versus no additional treatment are needed." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Of 493 records that we identified from databases as a result of the search (excluding duplicates), we regarded 70 abstracts/titles as potentially relevant studies. Independent scrutiny of these 70 titles and abstracts identified 29 potentially relevant studies. Of the 29 potentially relevant studies, one study met the criteria for inclusion. This study was a RCT that compared participants undergoing RSI and endotracheal intubation in the context of elective surgery requiring a general anaesthetic. Forty participants were recruited, 20 of whom had cricoid pressure applied and 20 of whom had cricoid pressure simulated. The main outcomes reported were systolic arterial pressure and heart rate after laryngoscopy and tracheal intubation. We did not consider these outcomes relevant for the purposes of this systematic review. The search also identified one study that could potentially be included in an updated systematic review in the future, but was at the time of the search a proposal for a trial only and had no reported outcomes at this time. There is currently no information available from published RCTs on clinically relevant outcome measures with respect to the application of cricoid pressure during RSI in the context of endotracheal intubation. On the basis of the findings of non-RCT literature, however, cricoid pressure may not be necessary to undertake RSI safely, and therefore well-designed and conducted RCTs should nonetheless be encouraged to properly assess the safety and effectiveness of cricoid pressure.\nOutput:\n" }, { "from": "agent", "value": "Our search strategy was designed to identify randomized controlled trials (RCTs) where RSI was undertaken to secure an artificial airway for a general anaesthetic with or without the application of cricoid pressure. Vomiting or regurgitation of stomach contents during anaesthesia was to be assessed either by looking directly down the airway or by various laboratory and imaging (radiological) methods. We also set out to determine whether applying cricoid pressure caused any harm. We searched the databases until May 2015. Only one RCT met our inclusion criteria but unfortunately this trial did not report on any clinically relevant results. We classified one other trial as ongoing. The researchers have reported on their planned protocol for the clinical trial, where cricoid pressure applied using a measured force will be compared with cricoid pressure without measuring the force applied. The number of patients who vomit is to be monitored. This systematic review shows an absence of evidence regarding the effectiveness and risks of cricoid pressure during RSI for intubation. Little can be said therefore about whether this technique should be continued in clinical practice. One current ongoing study shows promise that it will provide useful information in the future." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: For this second updated version we identified only one small trial reporting grade 4 toxicity results, without disease-free or overall survival data with a median follow-up of 16 months. From the first updated version, we identified three trials that were ongoing, and remain so in 2016. Four trials including 401 women with evaluable results with early cervical cancer were included in the meta-analyses. The median follow-up period in these trials ranged from 29 to 42 months. All women had undergone surgery first. Three trials compared chemotherapy combined with radiotherapy versus radiotherapy alone; and one trial compared chemotherapy followed by radiotherapy versus radiotherapy alone. It was not possible to perform subgroup analyses by stage or tumour size. Compared with adjuvant radiotherapy, chemotherapy combined with radiotherapy significantly reduced the risk of death (two trials, 297 women; hazard ratio (HR) = 0.56, 95% confidence interval (CI): 0.36 to 0.87) and disease progression (two trials, 297 women; HR = 0.47, 95% CI 0.30 to 0.74), with no heterogeneity between trials (I² = 0% for both meta-analyses). Acute grade 4 toxicity occurred significantly more frequently in the chemotherapy plus radiotherapy group than in the radiotherapy group (three trials, 321 women; risk ratio (RR) 6.26, 95% CI 2.50 to 15.67). We considered the evidence for all three outcomes to be of a moderate quality, using the GRADE approach due to small numbers and limited follow-up in the included studies. In addition, it was not possible to separate data for bulky early stage disease. In the one small trial that compared adjuvant chemotherapy followed by radiotherapy with adjuvant radiotherapy alone there was no difference in disease recurrence between the groups (one trial, 71 women; HR = 1.34; 95% CI 0.24 to 7.66) and overall survival was not reported. We considered this evidence to be of a low quality. No trials compared adjuvant platinum-based chemotherapy with no adjuvant chemotherapy after surgery for early cervical cancer with risk factors for recurrence. The addition of platinum-based chemotherapy to adjuvant radiotherapy (chemoradiation) may improve survival in women with early stage cervical cancer (IA2-IIA) and risk factors for recurrence. Adjuvant chemoradiation is associated with an increased risk of severe acute toxicity, although it is not clear whether this toxicity is significant in the long term due to a lack of long-term data. This evidence is limited by the small numbers and low to moderate methodological quality of the included studies. We await the results of three ongoing trials, which are likely to have an important impact on our confidence in this evidence.\nOutput:\n" }, { "from": "agent", "value": "In this review, we analysed data from four small trials of unclear quality. It was not possible to separate data of bulky early stage disease (stage IB2 and IIA lesions greater than 4 cm) from the overall results. We found limited evidence to suggest that the addition of cisplatin chemotherapy to radiotherapy prolongs survival (time to death) and delays progression of the cancer when given after surgery to women with cervical cancer stage IA2 to IIA with risk factors for recurrence. The combined therapy was associated with more severe side effects than radiotherapy alone. This evidence is limited by the small numbers and moderate quality methodological quality of included studies. ?We conclude that it seems appropriate to offer these women chemotherapy plus radiotherapy after surgery, however, more evidence regarding the relative benefits and risks is needed; this will hopefully be provided by the results of three ongoing trials." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Nine studies enrolling 645 infants met inclusion criteria. There were substantial methodological concerns in all studies comparing an opiate with a sedative. Two small studies comparing different opiates were of good methodology. Opiate (morphine) versus supportive care (one study): A reduction in time to regain birth weight and duration of supportive care and a significant increase in hospital stay was noted. Opiate versus phenobarbitone (four studies): Meta-analysis found no significant difference in treatment failure. One study reported opiate treatment resulted in a significant reduction in treatment failure in infants of mothers using only opiates. One study reported a significant reduction in days treatment and admission to the nursery for infants receiving morphine. One study reported a reduction in seizures, of borderline statistical significance, with the use of opiate. Opiate versus diazepam (two studies): Meta-analysis found a significant reduction in treatment failure with the use of opiate. Different opiates (six studies): there is insufficient data to determine safety or efficacy of any specific opiate compared to another opiate. Opiates compared to supportive care may reduce time to regain birth weight and duration of supportive care but increase duration of hospital stay. When compared to phenobarbitone, opiates may reduce the incidence of seizures but there is no evidence of effect on treatment failure. One study reported a reduction in duration of treatment and nursery admission for infants on morphine. Compared to diazepam, opiates reduce the incidence of treatment failure. A post-hoc analysis generates the hypothesis that initial opiate treatment may be restricted to infants of mothers who used opiates only. In view of the methodologic limitations of the included studies the conclusions of this review should be treated with caution.\nOutput:\n" }, { "from": "agent", "value": "Trials of opiates compared to sedatives or other non-pharmacological treatments have generally been of poor quality. Individual trials have reported that using an opiate compared to phenobarbitone may reduce the incidence of seizures, duration of treatment and nursery admission rate. However, no overall effect was found on treatment failure rate. When compared to diazepam, opiates reduced the incidence of treatment failure. Opiates such as morphine or dilute tincture of opium should probably be used as initial treatment for opiate withdrawal in newborn infants." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included nine trials with 1007 participants. Three trials compared rotator cuff repair with subacromial decompression followed by exercises with exercise alone. These trials included 339 participants with full-thickness rotator cuff tears diagnosed with magnetic resonance imaging (MRI) or ultrasound examination. One of the three trials also provided up to three glucocorticoid injections in the exercise group. All surgery groups received tendon repair with subacromial decompression and the postoperative exercises were similar to the exercises provided for the non-operative groups. Five trials (526 participants) compared repair with acromioplasty versus repair alone; and one trial (142 participants) compared repair with subacromial decompression versus subacromial decompression alone. The mean age of trial participants ranged between 56 and 68 years, and females comprised 29% to 56% of the participants. Symptom duration varied from a mean of 10 months up to 28 months. Two trials excluded tears with traumatic onset of symptoms. One trial defined a minimum duration of symptoms of six months and required a trial of conservative therapy before inclusion. The trials included mainly repairable full-thickness supraspinatus tears, six trials specifically excluded tears involving the subscapularis tendon. All trials were at risk of bias for several criteria, most notably due to lack of participant and personnel blinding, but also for other reasons such as unclearly reported methods of random sequence generation or allocation concealment (six trials), incomplete outcome data (three trials), selective reporting (six trials), and other biases (six trials). Our main comparison was rotator cuff repair with or without subacromial decompression versus non-operative treatment. We identified three trials for this comparison, that compared rotator cuff repair with subacromial decompression followed by exercises with exercise alone with or without glucocorticoid injections, and results are reported here for the 12 month follow up. At one year, moderate-certainty evidence (downgraded for bias) from 3 trials with 258 participants indicates that surgery probably provides little or no improvement in pain; mean pain (range 0 to 10, higher scores indicate more pain) was 1.6 points with non-operative treatment and 0.87 points better (0.43 better to 1.30 better) with surgery. Mean function (zero to 100, higher score indicating better outcome) was 72 points with non-operative treatment and 6 points better (2.43 better to 9.54 better) with surgery (3 trials; 269 participants), low-certainty evidence (downgraded for bias and imprecision). Participant-rated global success rate was 48/55 after non-operative treatment and 52/55 after surgery corresponding to risk ratio (RR) 1.08, 95% confidence interval (CI) 0.96 to 1.22; low-certainty evidence (downgraded for bias and imprecision). Health-related quality of life was 57.5 points (SF-36 mental component score, 0 to 100, higher score indicating better quality of life) with non-operative treatment and 1.3 points worse (4.5 worse to 1.9 better) with surgery (1 trial; 103 participants), low-certainty evidence (downgraded for bias and imprecision). We were unable to estimate the risk of adverse events and serious adverse events as only one event was reported across the trials (very low-certainty evidence; downgraded once due to bias and twice due to very serious imprecision). At the moment, we are uncertain whether rotator cuff repair surgery provides clinically meaningful benefits to people with symptomatic tears; it may provide little or no clinically important benefits with respect to pain, function, overall quality of life or participant-rated global assessment of treatment success when compared with non-operative treatment. Surgery may not improve shoulder pain or function compared with exercises, with or without glucocorticoid injections. The trials included have methodology concerns and none included a placebo control. They included participants with mostly small degenerative tears involving the supraspinatus tendon and the conclusions of this review may not be applicable to traumatic tears, large tears involving the subscapularis tendon or young people. Furthermore, the trials did not assess if surgery could prevent arthritic changes in long-term follow-up. Further well-designed trials in this area that include a placebo-surgery control group and long follow-up are needed to further increase certainty about the effects of surgery for rotator cuff tears.\nOutput:\n" }, { "from": "agent", "value": "This Cochrane Review is current to January 2019. We found nine trials with 1007 participants. Participants mean age was 56 to 68 years, and females comprised 29% to 56% of the participants. The participants had symptoms for several months or years and were diagnosed with a full-thickness tear with magnetic resonance imaging or ultrasound examination. Studies were conducted in Finland, Norway, Canada, USA, France, the Netherlands, Italy and South Korea. Our primary analysis included three trials with 339 participants who received either surgery (tendon repair and removal of bone from undersurface of acromion) or non-operative therapy (exercises with or without glucocorticoid injection). Three studies received funding however none of them reported using the funds directly for these trials. Compared with non-operative treatment, surgery resulted in little or no benefit in people with rotator cuff tears for up to one year. Pain (lower scores mean less pain) Improved by 9% (4% better to 13% better) or 0.9 points on a zero to 10 scale • People who had non-operative treatment rated their pain as 1.6 points • People who had surgery rated their pain as 0.7 points. Function (0 to 100; higher scores mean better function)Improved by 6% (2% better to 10% better) or 6 points on a zero to 100 scale • People who had non-operative treatment scored 72 points • People who had surgery scored 78 points Participant-rate global treatment success (participants satisfied with the outcome) 7% more people rated their treatment a success (4% fewer to 13% more), or seven more people out of 100. • 48/55 (873/1000) of people considered treatment as successful with non-operative treatment • 51/54 (943/1000) of people considered treatment as successful with surgery Overall quality of life (higher scores mean better quality of life)Worsened 1% (4% worse to 2% better) or 1.3 points on a zero to 100 scale • People who had non-operative treatment rated their quality of life 58 • People who had surgery (subacromial decompression) rated their quality of life 57 Adverse events • One adverse event (frozen shoulder) was reported in the trials in exercise group. Thus, we are unable to estimate comparative risk. Serious adverse events • No serious adverse events were reported in the trials. As compared with non-operative treatment, moderate-certainty evidence (downgraded due to risk of bias) indicates that surgery (rotator cuff repair with or without subacromial decompression) probably provides little or no benefit in pain and low-certainty evidence indicates that it may provide little or no improvement in function, participant-rated global treatment success or overall quality of life (downgraded due to bias and imprecision) in people with rotator cuff tears. Due to only one reported adverse event across the trials, we cannot estimate if there is higher risk for adverse events after either treatment (very low-certainty evidence)." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included two randomized controlled trials (218 eyes of 216 participants) comparing the effectiveness of pneumatic retinopexy versus scleral buckle for eyes with RRD. We identified no studies investigating the comparison of pneumatic retinopexy versus a combination treatment of scleral buckle and vitrectomy. Of the two included studies, one was a small study with 20 participants enrolled in Ireland and followed for an average of 16 months. The second study was larger with 196 participants (198 eyes) enrolled in the United States and followed for at least 6 months. Cautious interpretation of the results is warranted, since we graded the evidence as low to moderate quality due to insufficient reporting of study methods and imprecision and inconsistency among study results. Both studies showed fewer eyes achieving retinal reattachment in the pneumatic retinopexy group compared with the scleral buckle group by six-months follow-up (risk ratio (RR) 0.89, 95% confidence interval (CI) 0.77 to 1.02, 218 eyes); however, we are uncertain as to whether the intervention has an important effect on reattachment because the results are imprecise. Eyes in the pneumatic retinopexy group also were more likely to have had a recurrence of retinal detachment by six-months follow-up (RR 1.80, 95% CI 1.00 to 3.24, 218 eyes); however, we are uncertain as to whether the intervention has an important effect on recurrence because the lower CI equals no difference. Neither study reported mean change in visual acuity, quality of life data, or economic measures. Differences between the pneumatic retinopexy group and scleral buckle group were uncertain due to small numbers of events with respect to operative ocular adverse events (RR 0.67, 95% CI 0.32 to 1.42, 218 eyes), development of cataract (RR 0.92, 95% CI 0.06 to 14.54, 198 eyes), glaucoma (RR 0.31, 95% CI 0.03 to 2.91, 198 eyes), macular pucker (RR 0.74, 95% CI 0.20 to 2.67, 198 eyes), and proliferative vitreoretinopathy (RR 0.94, 95% CI 0.30 to 2.96, 218 eyes). Fewer eyes in the pneumatic retinopexy group compared with the scleral buckle group experienced choroidal detachment (RR 0.17, 95% CI 0.05 to 0.57, 198 eyes) or myopic shift equal to or greater than 1 diopter spherical equivalent (RR 0.04, 95% CI 0.01 to 0.13, 198 eyes). The evidence suggests that pneumatic retinopexy may result in lower rates of reattachment and higher rates of recurrence than scleral buckle for eyes with RRD, but does not rule out no difference between procedures. The relative safety of the procedures is uncertain and the relative effects of these procedures in terms of other patient-important outcomes, such as visual acuity and quality of life, is unknown. Due to the limited information available between pneumatic retinopexy and scleral buckle procedures, future research addressing these evidence gaps are warranted.\nOutput:\n" }, { "from": "agent", "value": "We found two randomized trials that had enrolled a total of 216 participants (218 eyes) from Ireland and the United States. Both studies evaluated whether pneumatic retinopexy or scleral buckle was a better treatment for RRD. The study in the US had 198 participants with 6 months to 2 years of follow-up. The study in Ireland had 20 participants with 5 to 27 months of follow-up. The evidence is current to 13 January 2015. Results from both studies suggested that scleral buckle may perform better or as well as pneumatic retinopexy in terms of reattachment rates and reducing the risk of recurrence of detachment. Few ocular adverse events occurred during either procedure and differences in some adverse events occurring after the surgeries could not be determined. More eyes in the scleral buckle group experienced choroidal detachment (separation of the choroid, the layer between the retina and sclera, from the sclera) and myopic shift (change to nearsightedness that may be a sign of developing cataract) than eyes in the pneumatic retinopexy group. The quality of the evidence was assessed as low to moderate due to poor reporting of how the studies were done. Further, there was lack of information regarding important outcomes that may be useful when choosing which procedure to use in terms of vision, quality of life, and cost." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: This review includes two RCTs (154 children aged 32 months to 11 years) of communication interventions for ASD in minimally verbal children compared with a control group (treatment as usual). One RCT used a verbally based intervention (focused playtime intervention; FPI) administered by parents in the home, whereas the other used an alternative and augmentative communication (AAC) intervention (Picture Exchange Communication System; PECS) administered by teachers in a school setting. The FPI study took place in the USA and included 70 participants (64 boys) aged 32 to 82 months who were minimally verbal and had received a diagnosis of ASD. This intervention focused on developing coordinated toy play between child and parent. Participants received 12 in-home parent training sessions for 90 minutes per session for 12 weeks, and they were also invited to attend parent advocacy coaching sessions. This study was funded by the National Institute of Child Health and Human Development, the MIND Institute Research Program and a Professional Staff Congress-City University of New York grant. The PECS study included 84 minimally verbal participants (73 boys) aged 4 to 11 years who had a formal diagnosis of ASD and who were not using PECS beyond phase 1 at baseline. All children attended autism-specific classes or units, and most classes had a child to adult ratio of 2:1. Teachers and parents received PECS training (two-day workshop). PECS consultants also conducted six half-day consultations with each class once per month over five months. This study took place in the UK and was funded by the Three Guineas Trust. Both included studies had high or unclear risk of bias in at least four of the seven 'Risk of bias' categories, with a lack of blinding for participants and personnel being the most problematic area. Using the GRADE approach, we rated the overall quality of the evidence as very low due to risk of bias, imprecision (small sample sizes and wide confidence intervals) and because there was only one trial identified per type of intervention (i.e. verbally based or AAC). Both studies focused primarily on communication outcomes (verbal and non-verbal). One of the studies also collected information on social communication. The FPI study found no significant improvement in spoken communication, measured using the expressive language domain of the Mullen Scale of Early Learning expressive language, at postintervention. However, this study found that children with lower expressive language at baseline (less than 11.3 months age-equivalent) improved more than children with better expressive language and that the intervention produced expressive language gains in some children. The PECS study found that children enrolled in the AAC intervention were significantly more likely to use verbal initiations and PECS symbols immediately postintervention; however, gains were not maintained 10 months later. There was no evidence that AAC improved frequency of speech, verbal expressive vocabulary or children's social communication or pragmatic language immediately postintervention. Overall, neither of the interventions (PECS or FPI) resulted in maintained improvements in spoken or non-verbal communication in most children. Neither study collected information on adverse events, other communication skills, quality of life or behavioural outcomes. There is limited evidence that verbally based and ACC interventions improve spoken and non-verbal communication in minimally verbal children with ASD. A substantial number of studies have investigated communication interventions for minimally verbal children with ASD, yet only two studies met inclusion criteria for this review, and we considered the overall quality of the evidence to be very low. In the study that used an AAC intervention, there were significant gains in frequency of PECS use and verbal and non-verbal initiations, but not in expressive vocabulary or social communication immediately postintervention. In the study that investigated a verbally based intervention, there were no significant gains in expressive language postintervention, but children with lower expressive language at the beginning of the study improved more than those with better expressive language at baseline. Neither study investigated adverse events, other communication skills, quality of life or behavioural outcomes. Future RCTs that compare two interventions and include a control group will allow us to better understand treatment effects in the context of spontaneous maturation and will allow further comparison of different interventions as well as the investigation of moderating factors.\nOutput:\n" }, { "from": "agent", "value": "We identified two trials involving 154 minimally verbal children who had ASD (aged 32 months to 11 years). The studies randomly divided participants into those that received a communication intervention and a control group that did not receive the intervention but received treatment as usual in the community. Both studies focused primarily on communication outcomes (verbal and non-verbal). One of the studies also collected information on social communication. Neither study collected information on adverse events, other communication skills, quality of life or behavioural outcomes. One study looked at an alternative and augmentative communication (ACC) intervention (Picture Exchange Communication System; PECS), which teachers gave the children in school. This intervention was conducted over five months and involved teacher training and consultation. PECS is a staged approach where children are taught to exchange a single picture of a desired item or action to another person who then responds to the request. The system progresses toward putting pictures together in sentences and using these sentences in a variety of ways such as commenting and answering questions. This study included 84 participants (73 boys) aged 4 to 11 years and was funded by the Three Guineas Trust. The other study looked at a verbally based intervention (focused playtime intervention; FPI), which is a home-based parent education programme that aims to promote coordinated play with toys between parents and their children. This study included 70 participants (64 boys) aged 32 months to 82 months and was funded by a Clinical and Patient Educators Association grant (HD35470) from the National Institute of Child Health and Human Development, the MIND Institute Research Program, and a Professional Staff Congress-City University of New York grant. There is limited evidence that verbally based and AAC interventions improve spoken and non-verbal communication in minimally verbal children with ASD. Both studies included in this review reported gains in aspects of verbal or non-verbal communication (or both) for some children immediately after the intervention. Neither of the interventions resulted in improvements in verbal or non-verbal communication that were maintained over time for most children. We rated the overall quality of the evidence as very low because we only found two eligible studies, and they involved few participants. Furthermore, both studies had some methodological limitations that increased their risk of bias. There is currently limited evidence that verbally based and ACC interventions improve expressive communication skills in minimally verbal children with ASD aged 32 months to 11 years. Additional trials that use communication interventions and compare the effects of these interventions to a control group are urgently required to build the evidence base." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included 21 trials and identified eight ongoing trials. The included trials evaluated metformin (11 trials), sibutramine (six trials), orlistat (four trials), and one trial arm investigated the combination of metformin and fluoxetine. The ongoing trials evaluated metformin (four trials), topiramate (two trials) and exenatide (two trials). A total of 2484 people participated in the included trials, 1478 participants were randomised to drug intervention and 904 to comparator groups (91 participants took part in two cross-over trials; 11 participants not specified). Eighteen trials used a placebo in the comparator group. Two trials had a cross-over design while the remaining 19 trials were parallel RCTs. The length of the intervention period ranged from 12 weeks to 48 weeks, and the length of follow-up from baseline ranged from six months to 100 weeks. Trials generally had a low risk of bias for random sequence generation, allocation concealment and blinding (participants, personnel and assessors) for subjective and objective outcomes. We judged approximately half of the trials as having a high risk of bias in one or more domain such as selective reporting. The primary outcomes of this review were change in body mass index (BMI), change in weight and adverse events. All 21 trials measured these outcomes. The secondary outcomes were health-related quality of life (only one trial reported results showing no marked differences; very low certainty evidence), body fat distribution (measured in 18 trials), behaviour change (measured in six trials), participants' views of the intervention (not reported), morbidity associated with the intervention (measured in one orlistat trial only reporting more new gallstones following the intervention; very low certainty evidence), all-cause mortality (one suicide in the orlistat intervention group; low certainty evidence) and socioeconomic effects (not reported). Intervention versus comparator for mean difference (MD) in BMI change was -1.3 kg/m2 (95% confidence interval (CI) -1.9 to -0.8; P < 0.00001; 16 trials; 1884 participants; low certainty evidence). When split by drug type, sibutramine, metformin and orlistat all showed reductions in BMI in favour of the intervention. Intervention versus comparator for change in weight showed a MD of -3.9 kg (95% CI -5.9 to -1.9; P < 0.00001; 11 trials; 1180 participants; low certainty evidence). As with BMI, when the trials were split by drug type, sibutramine, metformin and orlistat all showed reductions in weight in favour of the intervention. Five trials reported serious adverse events: 24/878 (2.7%) participants in the intervention groups versus 8/469 (1.7%) participants in the comparator groups (risk ratio (RR) 1.43, 95% CI 0.63 to 3.25; 1347 participants; low certainty evidence). A total 52/1043 (5.0%) participants in the intervention groups versus 17/621 (2.7%) in the comparator groups discontinued the trial because of adverse events (RR 1.45, 95% CI 0.83 to 2.52; 10 trials; 1664 participants; low certainty evidence). The most common adverse events in orlistat and metformin trials were gastrointestinal (such as diarrhoea, mild abdominal pain or discomfort, fatty stools). The most frequent adverse events in sibutramine trials included tachycardia, constipation and hypertension. The single fluoxetine trial reported dry mouth and loose stools. No trial investigated drug treatment for overweight children. This systematic review is part of a series of associated Cochrane reviews on interventions for obese children and adolescents and has shown that pharmacological interventions (metformin, sibutramine, orlistat and fluoxetine) may have small effects in reduction in BMI and bodyweight in obese children and adolescents. However, many of these drugs are not licensed for the treatment of obesity in children and adolescents, or have been withdrawn. Trials were generally of low quality with many having a short or no post-intervention follow-up period and high dropout rates (overall dropout of 25%). Future research should focus on conducting trials with sufficient power and long-term follow-up, to ensure the long-term effects of any pharmacological intervention are comprehensively assessed. Adverse events should be reported in a more standardised manner specifying amongst other things the number of participants experiencing at least one adverse event. The requirement of regulatory authorities (US Food and Drug Administration and European Medicines Agency) for trials of all new medications to be used in children and adolescents should drive an increase in the number of high quality trials.\nOutput:\n" }, { "from": "agent", "value": "We found 21 randomised controlled studies (clinical studies where people are randomly put into one of two or more treatment groups) comparing various drugs plus a behaviour changing intervention such as diet, exercise or both (= intervention groups) usually with placebo (a pretend drug) plus a behaviour changing intervention (= control groups). We also identified eight ongoing studies (studies which are currently running but not completed yet). A total of 2484 children and adolescents took part in the included studies. The length of the intervention period ranged from 12 weeks to 48 weeks, and the length of follow-up ranged from six months to 100 weeks. The included studies investigated metformin (10 studies), sibutramine (six studies), orlistat (four studies) and one study group evaluated the combination of metformin and fluoxetine. The ongoing studies are investigating metformin (four studies), topiramate (two studies) and exenatide (two studies). Most studies reported on body mass index (BMI) and bodyweight: BMI is a measure of body fat and is calculated from weight and height measurements (kg/m2). In children, BMI is often measured in a way that takes into account sex, weight and height as children grow older (BMI z score). The average change in BMI across control groups was between a 1.8 kg/m2 reduction to a 0.9 kg/m2 increase, while across all intervention groups the average reduction was more pronounced (1.3 kg/m2 reduction). The same effect was observed for weight change: on average, children and adolescents in the intervention groups lost 3.9 kg more weight than the children and adolescents in the control groups. Study authors reported an average of serious side effects in 24 per 1000 participants in the intervention groups compared with an average of 17 per 1000 participants in the control groups. The numbers of participants dropping out of the study because of side effects were 40 per 1000 in the intervention groups and 27 per 1000 in the control groups. The most common side effects in the orlistat and metformin studies were gut (such as diarrhoea and mild tummy pain). Common side effects in the sibutramine trials included increased heart rate (tachycardia), constipation and high blood pressure. The fluoxetine study reported dry mouth and loose stools. One study reported health-related quality of life (a measure of physical, mental, emotional and social functioning) and found no marked differences between intervention and control. No study reported the participants' views of the intervention or socioeconomic effects. Only one study reported on morbidity (how often a disease occurs in a specific area) associated with the intervention, where there were more gallstones after the orlistat treatment. Study authors reported one suicide in the orlistat intervention group. However, studies were not long enough to reliably investigate death from any cause. No study investigated drug treatment for children who were only overweight (obese children have a much higher weight, BMI or BMI z score than children being overweight). This evidence is up to date to March 2016. The overall certainty of the evidence was low or very low, mainly because there were only a few studies per outcome measurement, the number of included children or adolescents was small, and due to variation in the results of the studies. In addition, many children or adolescents left the studies before the study had finished." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: The searches identified 17 trials; four are included (287 participants aged five to 39 years; maximum follow-up of four years) and one is currently awaiting classification pending publication of the full trial report and two are ongoing. Three trials compared ibuprofen to placebo (two from the same center with some of the same participants); one trial assessed piroxicam versus placebo. The three ibuprofen trials were deemed to have good or adequate methodological quality, but used various outcomes and summary measures. Reviewers considered measures of lung function, nutritional status, radiological assessment of pulmonary involvement, intravenous antibiotic usage, hospital admissions, survival and adverse effects. Combined data from the two largest ibuprofen trials showed a lower annual rate of decline for lung function, % predicted forced expiratory volume in one second (FEV1), mean difference (MD) 1.32 (95% confidence interval (CI) 0.21 to 2.42) (moderate-quality evidence); forced vital capacity (FVC), MD 1.27 (95% CI 0.26 to 2.28) (moderate-quality evidence); forced expiratory flow (FEF25%-75%), MD 1.80 (95% CI 0.15 to 3.45). The post hoc analysis of data from two trials split by age showed a slower rate of annual decline of FEV1 % predicted and FVC in the ibuprofen group in younger children, MD 1.41% (95% CI 0.03 to 2.80) (moderate-quality evidence) and MD 1.32% (95% CI 0.04 to 2.60) (moderate-quality evidence) respectively. Data from four trials demonstrated the proportion of participants with at least one hospitalization may be slightly lower in the ibuprofen group compared to placebo, Peto odds ratio 0.61 (95% CI 0.37 to 1.01) (moderate-quality evidence). In one trial, long-term use of high-dose ibuprofen was associated with reduced intravenous antibiotic usage, improved nutritional and radiological pulmonary status. No major adverse effects were reported, but the power of the trials to identify clinically important differences in the incidence of adverse effects was low. We did not have any concerns with regards to risk of bias for the trial comparing piroxicam to placebo. However, the trial did not report many data in a form that we could analyze in this review. No data were available for the review's primary outcome of lung function; available data for hospital admissions showed no difference between the groups. No analyzable data were available for any other review outcome. High-dose ibuprofen can slow the progression of lung disease in people with cystic fibrosis, especially in children, which suggests that strategies to modulate lung inflammation can be beneficial for people with cystic fibrosis.\nOutput:\n" }, { "from": "agent", "value": "We looked for trials comparing oral non-steroidal anti-inflammatory drugs to a a placebo (a tablet that contained no active medicine). We looked for any dose level. but the trial had to run for at least two months in people with cystic fibrosis. We found 17 trials and included four of these with a total of 287 people aged five to 39 years; one further trial has not yet been published in full and two are still ongoing; we will assess these when we have more information. Three of the four included trials compared ibuprofen to a placebo; two of these trials were run in the same center and used some of the same people. One trial compared a drug called piroxicam to placebo. The longest trial lasted four years. We aimed to report on lung function, nutritional status, lung x-rays, how often intravenous antibiotics were needed, details about hospital admissions, survival and side effects. We combined results from the two largest ibuprofen trials and showed that those taking ibuprofen had a lower annual rate of decline in lung function which was consistent across three lung function measurements. We then looked at these results split by age (even though we did not originally plan to do this) and found that two of the measurements showed a slower rate of annual decline in lung function in younger children. Results from four trials showed that fewer participants in the ibuprofen group were admitted to hospital at least once compared to placebo, although it was not clear if the difference was just chance or not. In one trial, people taking a long-term high dose of ibuprofen were less likely to need intravenous antibiotics, had better nutritional status and healthier lungs as seen by X-ray. No major side effects were reported in the trials, but they had not been designed to show differences in the rates of side effects. To summarize, we found evidence showing that a high dose of a non-steroidal anti-inflammatory drug, most notably ibuprofen, may slow the progression of lung damage in people with cystic fibrosis, especially in younger people. The long-term safety results are limited but we feel that there is enough evidence to suggest that non-steroidal anti-inflammatory drugs be temporarily stopped when people with cystic fibrosis are receiving intravenous aminoglycosides or other drugs that may badly damage the kidneys. The trial of the drug piroxicam did not report many results in a form that we could analyse in the review. We did not have any results for our main outcome of lung function. The only results we had reported no difference between the piroxicam group and the placebo group for the number of hospital admissions. We judged the evidence to be of moderate quality overall. We thought the three ibuprofen trials had a good or adequate level of methodological quality with little risk of bias to the results, but used a range of different outcomes and summary measures. We did not have any concerns with regards to risks of bias for the trial comparing piroxicam to placebo." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: One new trial was identified and included in this update bringing the total to eight trials involving 787 women. Three small trials compared a mechanical device with no treatment and although they suggested that use of a mechanical device might be better than no treatment, the evidence for this was inconclusive. Four trials compared one mechanical device with another. Quantitative synthesis of data from these trials was not possible because different mechanical devices were compared in each trial using different outcome measures. Data from the individual trials showed no clear difference between devices, but with wide confidence intervals. One trial compared three groups: a mechanical device alone, behavioural therapy (pelvic floor muscle training) alone and behavioural therapy combined with a mechanical device. While at three months there were more withdrawals from the device-only group, at 12 months differences between the groups were not sustained on any measure. The place of mechanical devices in the management of urinary incontinence remains in question. Currently there is little evidence from controlled trials on which to judge whether their use is better than no treatment and large well-conducted trials are required for clarification. There was also insufficient evidence in favour of one device over another and little evidence to compare mechanical devices with other forms of treatment.\nOutput:\n" }, { "from": "agent", "value": "This review of trials found that using mechanical devices might be better than no treatment but the evidence is weak. There was not enough evidence to recommend any specific type of device or to show whether mechanical devices are better than other forms of treatment such as pelvic floor muscle training." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: A comprehensive search of the literature yielded the following results: CENTRAL (1022 references), MEDLINE (2874 references), and Embase (2820 references). After de-duplication, we screened titles and abstracts of 4880 references and excluded 4864 that did not meet the review inclusion criteria. Of the 16 references that potentially met the review inclusion, we excluded all 16 reports after reviewing the full texts. We did not identify any ongoing trials. There is currently an absence of evidence to indicate the effectiveness of health education interventions involving healthcare providers or individuals or both to promote early presentation and referral for women with endometrial cancer symptoms. High-quality RCTs are needed to assess whether health education interventions enhance early presentation and referral. If health education interventions can be shown to reduce treatment delays in endometrial cancer, further studies would be required to determine which interventions are most effective.\nOutput:\n" }, { "from": "agent", "value": "We planned to include randomised controlled trials (studies in which people or groups of people are allocated by chance to two or more groups, treating them differently). In the absence of randomised controlled trials, we planned to include studies where participants were not randomised but that included an assessment of the benefits of health education compared to no health education. We searched scientific databases and checked the titles and abstracts of 4880 possibly relevant articles and assessed the full text of 16 of these references. However, we found no studies that met our inclusion criteria. There is currently an absence of evidence to indicate whether providing health education to healthcare providers, or individuals or both, promotes early presentation and referral for women with symptoms of endometrial cancer." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We identified 14 eligible studies which randomised a total of 5,500 women. Median follow-up ranged from 18 to 124 months. Eight studies described a satisfactory method of randomisation. Data, based on 1139 estimated deaths in 4620 women available for analysis, show equivalent overall survival rates with a HR of 0.98 (95% CI, 0.87 to 1.09; p, 0.67; no heterogeneity). Preoperative chemotherapy increases breast conservation rates, yet at the associated cost of increased loco regional recurrence rates. However, this rate was not increased as long as surgery remains part of the treatment even after complete tumour regression (HR, 1.12; 95% CI, 0.92 to 1.37; p, 0.25; no heterogeneity. Preoperative chemotherapy was associated with fewer adverse effects. Pathological complete response is associated with better survival than residual disease (HR, 0.48; 95% CI, 0.33 to 0.69; p, < 10-4). This review suggests safe application of preoperative chemotherapy in the treatment of women with early stage breast cancer in order to down-stage surgical requirement, to evaluate chemosensitivity and to facilitate translational research.\nOutput:\n" }, { "from": "agent", "value": "This review identified 14 randomised controlled trials involving 5,500 women addressing this question. The analyses revealed no difference in overall survival and disease-free survival for women who received either preoperative or postoperative chemotherapy. Preoperative treatment makes more breast-conserving surgery possible because of shrinkage of the tumour before surgical intervention (relative risk, 0.82; 95% confidence interval, 0.76 to 0.89). However, this also results in a increase of loco-regional recurrence (recurrence in the same area) rate (hazard ratio, 1.12; 95% confidence interval, 0.92 to 1.37). Preoperative chemotherapy provides the possibility of monitoring tumour response and making appropriate regimen changes once the tumour appears to be resistant to the primary therapy. Adverse effects, which were reported in only half of the studies, were fewer in women receiving preoperative chemotherapy. Although, postoperative complications, nausea and vomiting, and alopecia were equally distributed, events of cardiotoxicity were less likely (relative risk, 0.74; 95% confidence interval, 0.53 to 1.04) in women receiving preoperative chemotherapy. Also, serious infection (analysed in 2799 women) was less likely to occur in women receiving preoperative chemotherapy (relative risk, 0.69; 95% confidence interval, 0.56 to 0.84)." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Seventeen studies were included in the review, involving 3097 participants. Based on all 17 studies, SSRIs as a group were more effective than placebo in reducing the symptoms of OCD between 6 and 13 weeks post-treatment, measured using the Yale-Brown Obsessive Compulsive Scale (YBOCS) (WMD -3.21, 95% CI -3.84 to -2.57). The WMD for individual SSRI drugs were similar and not statistically different. Based on 13 studies (2697 participants), SSRIs were more effective than placebo in achieving clinical response at post-treatment (RR 1.84, 95% CI 1.56 to 2.17). The pooled RR was shown to be similar between individual SSRI drugs. Although reported adverse effects data were more limited, with few exceptions, the overall and individual adverse effects for the different SSRIs were always worse than for placebo and, in the majority of cases, the difference was statistically significant. Nausea, headache and insomnia were always reported amongst the most common adverse effects in trials of each of the drugs. SSRIs are more effective than placebo for OCD, at least in the short-term, although there are differences between the adverse effects of individual SSRI drugs. The longer term efficacy and tolerability of different SSRI drugs for OCD has yet to be established.\nOutput:\n" }, { "from": "agent", "value": "Individual randomised controlled trials have demonstrated that antidepressants are effective for OCD. This review summarises all the available evidence for one class of antidepressant drugs, the selective serotonin re-uptake inhibitors (SSRIs) (including citalopram, fluoxetine, fluvoxamine, paroxetine and sertraline) compared to placebo in the treatment of OCD in adults. The review included 17 studies (3097 participants), and showed that SSRIs were effective in reducing the symptoms of OCD. Based on 13 studies (2697 participants), the review showed that people receiving SSRIs were nearly twice as likely as those receiving placebo to achieve clinical response (defined as a 25% or more reduction in symptoms). Indirect comparisons of effectiveness suggested that although individual SSRI drugs were similar in their effectiveness, they differed in terms of their adverse effects. The most common adverse effect reported by participants was nausea. Further studies involving head to head comparisons between different SSRI drugs are required to obtain more reliable information on differences between SSRIs, both in terms of effectiveness and adverse effects." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: The risk of bias was high in many of the included studies. Random sequence generation and allocation concealment was reported in three (12%) and four studies (16%), respectively. Participants and personnel were blinded in 13 studies (52%), and outcome assessors were blinded in five studies (20%). Complete outcome reporting occurred in nine studies (36%). Adverse events were only reported in nine studies (36%); 11 studies (44%) reported industry funding. We included 25 studies (8289 participants) in this latest update; 23 studies (24 comparisons, 8166 participants) compared statins with placebo or no treatment, and two studies (123 participants) compared statins directly with one or more other statins. Statins had little or no effect on major cardiovascular events (4 studies, 7084 participants: RR 0.95, 95% CI 0.88 to 1.03), all-cause mortality (13 studies, 4705 participants: RR 0.96, 95% CI 0.90 to 1.02), cardiovascular mortality (13 studies, 4627 participants: RR 0.94, 95% CI 0.84 to 1.06) and myocardial infarction (3 studies, 4047 participants: RR 0.87, 95% CI 0.71 to 1.07); and uncertain effects on stroke (2 studies, 4018 participants: RR 1.29, 95% CI 0.96 to 1.72). Risks of adverse events from statin therapy were uncertain; these included effects on elevated creatine kinase (5 studies, 3067 participants: RR 1.25, 95% CI 0.55 to 2.83) or liver function enzymes (4 studies, 3044 participants; RR 1.09, 95% CI 0.41 to 1.25), withdrawal due to adverse events (9 studies, 1832 participants: RR 1.04, 95% CI 0.87 to 1.25) or cancer (2 studies, 4012 participants: RR 0.90, 95% CI 0.72 to 1.11). Statins reduced total serum cholesterol (14 studies, 1803 participants; MD -44.86 mg/dL, 95% CI -55.19 to -34.53) and low-density lipoprotein cholesterol (12 studies, 1747 participants: MD -39.99 mg/dL, 95% CI -52.46 to -27.52) levels. Data comparing statin therapy directly with another statin were sparse. Statins have little or no beneficial effects on mortality or cardiovascular events and uncertain adverse effects in adults treated with dialysis despite clinically relevant reductions in serum cholesterol levels.\nOutput:\n" }, { "from": "agent", "value": "In 2009 we identified 14 studies, enrolling 2086 patients, and found that while statins were generally safe and reduced cholesterol levels, they did not prevent death or clinical cardiac events in people treated with dialysis. This latest update analysed a total or 25 studies (8289 patients), and included the results from two new large studies. We found that statins lowered cholesterol in people treated with dialysis but did not prevent death, heart attack, or stroke. Evidence for side-effects was incomplete, and potential harms from statin therapy remain uncertain. Current study data did not address whether statin treatment should be stopped when a person starts dialysis, although the benefits associated with continued treatment are likely to be small. Limited information was available for people treated with peritoneal dialysis, suggesting that more research is needed in this setting." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included 12 studies reporting data on 1642 participants (intervention = 833, control = 809). Eight studies targeted adults with epilepsy, one study included participants of all ages, one study included participants older than two years, one study targeted caregivers of children with epilepsy, and one study targeted families of children with epilepsy. We identified six ongoing trials. Follow-up time was generally short in most trials, ranging from one to 12 months. The trials examined three main types of interventions: educational interventions, behavioural interventions and mixed interventions. All studies compared treatment versus usual care or 'no intervention', except for two studies. Due to heterogeneity between studies in terms of interventions, methods used to measure adherence and the way the studies were reported, we did not pool the results and these findings were inappropriate to be included in a meta-analysis. Education and counselling of participants with epilepsy resulted in mixed success (moderate-quality evidence). Behavioural interventions such as use of intensive reminders provided more favourable effects on adherence (moderate-quality evidence). The effect on adherence to antiepileptic drugs described by studies of mixed interventions showed improved adherence in the intervention groups compared to the control groups (high-quality evidence). Behavioural interventions such as intensive reminders and the use of mixed interventions demonstrate some positive results; however, we need more reliable evidence on their efficacy, derived from carefully-designed randomised controlled trials before we can draw a firm conclusion. Since the last version of this review, none of the new relevant studies have provided additional information that would lead to significant changes in our conclusions. This current update includes 12 studies, of which six came from the latest searches.\nOutput:\n" }, { "from": "agent", "value": "We searched scientific databases for clinical trials looking at ways of improving adherence to drug treatment in people with epilepsy. We limited our search to randomised controlled trials involving people with a clinical diagnosis of epilepsy of any age and treated with antiepileptic drugs in a primary care, outpatient or other community setting. The results are up-to-date to February 2016. We identified twelve trials (1642 participants). The trials were conducted in different countries with the majority from the United States. The trials examined three main types of interventions: i) education and counselling of participants about topics such as epilepsy and medication used to control epilepsy, ii) behavioural interventions such as asking epileptic patients to link the intention of taking their medication with a particular time, place and other routine activity and iii) the use of more than one intervention (mixed interventions). Behavioural interventions and mixed interventions resulted in an improved adherence in the intervention groups compared to the control groups. Four trials showed that when adherence improved in the intervention groups, seizure frequency or seizure severity was decreased. Many of the included trials are of moderate quality and have limitations in the design. Therefore, it is difficult to draw firm conclusions. We need carefully-designed randomised controlled trials involving more people with longer follow-up periods to identify the best intervention to improve adherence to antiepileptic medication." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Forty-four eligible trials, involving 8436 participants were identified. Compared to placebo, adjuvant therapy significantly reduced off-time (-1.05 hours/day, 95% confidence interval (CI) -1.19 to -0.90; P<0.00001), the required levodopa dose (-55.65 mg/day, CI -62.67 to -48.62; P<0.00001) and improved UPDRS scores (UPDRS ADL score: -1.31 points, CI -1.62 to -0.99; P<0.00001; UPDRS motor score: -2.84 points, CI -3.36 to -2.32; P<0.00001; UPDRS total score: -3.26 points, CI -4.52 to -2.00; P<0.00001). However, dyskinesia (odds ratio (OR) 2.50, CI 2.21 to 2.84; P<0.00001) and side-effects including constipation (OR 3.19, CI 2.17 to 4.68; P<0.00001), dizziness (OR 1.57, CI 1.30 to 1.90; P<0.00001), dry mouth (OR 2.33, CI 1.22 to 4.47; P=0.01), hallucinations (OR 2.16, CI 1.70 to 2.74; P<0.00001), hypotension (OR 1.47, CI 1.18 to 1.83; P=0.0007), insomnia (OR 1.38, CI 1.09 to 1.74; P=0.007), nausea (OR 1.78, CI 1.53 to 2.07; P<0.00001), somnolence (OR 1.87, CI 1.40 to 2.51; P<0.0001) and vomiting (OR 2.56, CI 1.67 to 3.93; P<0.0001) were all increased with adjuvant therapy. Indirect comparisons of the three drug classes suggested that dopamine agonists were more efficacious in reducing off-time (dopamine agonist: -1.54 hours/day; COMTI: -0.83 hours/day; MAOBI: -0.93 hours/day; test for heterogeneity between drug classes P=0.0003) and levodopa dose (dopamine agonist: -116 mg/day; COMTI: -52 mg/day; MAOBI: -29 mg/day; test for heterogeneity between drug classes P<0.00001). UPDRS scores also improved more with dopamine agonists than with COMTI or MAOBI (UPDRS total scores - dopamine agonist: -10.01 points versus COMTI: -1.46 points versus MAOBI: -2.20 points; test for heterogeneity between drug classes P<0.00001), although more dyskinesia were seen with dopamine agonists (OR 2.70) and COMTI (OR 2.50) than with MAOBI (OR 0.94) (test for heterogeneity between drug classes P=0.009). Although the increase in the overall incidence of side-effects was generally more marked with dopamine agonists (OR 1.52) and COMTI (OR 2.0) than with MAOBI (OR 1.32), heterogeneity between drug classes was only of borderline significance (P=0.07). Compared to placebo, adjuvant therapy reduces off-time, levodopa dose, and improves UPDRS scores in PD patients who develop motor complications on levodopa therapy. However, this is at the expense of increased dyskinesia and numerous other side-effects. Indirect comparisons suggest that dopamine agonist therapy may be more effective than COMTI and MAOBI therapy, which have comparable efficacy. However, as indirect comparisons should be interpreted with caution, direct head-to-head randomised trials assessing the impact of these different drug classes on overall patient-rated quality of life are needed.\nOutput:\n" }, { "from": "agent", "value": "This review assesses data from randomised trials of the three classes of drugs commonly used as add-on (adjuvant) treatment to levodopa therapy in people with PD who have motor complications. Forty-four randomised trials, involving 8436 participants were identified as suitable for this review. The review confirms reports from individual trials that, compared to placebo, add-on therapy (on a background of levodopa) significantly reduces patient off-time, reduces the required levodopa dose and improves overall disability scores (measured on the Unified Parkinson's Disease Rating Scale - UPDRS). However, dyskinesia and other side-effects such as constipation, hallucinations and vomiting are increased with adjuvant therapy. Indirect comparisons of the three drug classes (dopamine agonists, COMTIs and MAOBIs) suggest that dopamine agonists may provide more effective symptomatic control than COMTI and MAOBI therapy. COMTI and MAOBI have comparable efficacy. There was no significant evidence of differences in efficacy between individual drugs within the drug classes, other than tolcapone appearing more effective than entacapone. However these observations are based on indirect comparisons between trials, so could be due to other factors, e.g. differences in the types of people included in the trials, and so should to be interpreted with caution. This review highlights the need for large randomised studies that directly compare the different drug classes with patient-rated overall quality of life and health economic measures as the primary outcomes." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included six RCTs with a total of 248 participants; none of the trials were determined to have overall low risk of bias. We found 12 ongoing trials, from which we were unable to retrieve any data. Only two trials provided data on mortality, and one was a zero event study; thus the meta-analysis showed no statistically significant effect on overall mortality (2.6% vs 9.5%, RR 0.28, 95% CI 0.03 to 2.33). Our analyses on blood transfusion data suggest a beneficial effect of fibrinogen concentrate in reducing the incidence of allogenic transfusions (RR 0.47, 95% CI 0.31 to 0.72) but show no effect on other predefined outcomes, including adverse events such as thrombotic episodes. In the six available RCTs of elective surgery, fibrinogen concentrate appears to reduce transfusion requirements, but the included trials are of low quality with high risk of bias and are underpowered to detect mortality, benefit or harm. Furthermore, data on mortality are lacking, heterogeneity is high and acute or severe bleeding in a non-elective surgical setting remains unexplored. Currently, weak evidence supports the use of fibrinogen concentrate in bleeding patients, as tested here in primarily elective cardiac surgery. More research is urgently needed.\nOutput:\n" }, { "from": "agent", "value": "In the present Cochrane systematic review, we set out to assess the benefits and harms of fibrinogen concentrate in patients with bleeding. We searched the databases to August 2013, we identified six randomized trials in cardiac and elective surgical settings that compared fibrinogen concentrate (248 participants) with placebo/other sources or no treatment. Additionally, we found 12 ongoing trials, but we were unable to retrieve any data from them. We could not identify beneficial effects of fibrinogen concentrate on patient survival. In our predefined outcomes, we identified a reduced proportion of patients requiring donor blood transfusion. We could not identify reduced blood loss or any harms or adverse events caused by treatment with fibrinogen concentrate. However, all trials were of low quality and were small, so evidence in support of fibrinogen concentrate in patients with bleeding remains weak." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included seven RCTs (667 women) in this updated review. Most studies were at a low or moderate risk of bias and all compared methotrexate with actinomycin D. Three studies compared weekly intramuscular (IM) methotrexate with bi-weekly pulsed intravenous (IV) actinomycin D (393 women), one study compared five-day IM methotrexate with bi-weekly pulsed IV actinomycin D (75 women), one study compared eight-day IM methotrexate-folinic acid (MTX-FA) with five-day IV actinomycin D (49 women), and one study compared eight-day IM MTX-FA with bi-weekly pulsed IV actinomycin D. One study contributed no data. Moderate-certainty evidence indicates that actinomycin D is probably more likely to lead to primary cure than methotrexate (risk ratio (RR) 0.65, 95% confidence interval (CI) 0.57 to 0.75; six trials, 577 participants; I2 = 26%), and first-line methotrexate treatment is probably more likely to fail than actinomycin D treatment (RR 3.55, 95% CI 1.81 to 6.95; six trials, 577 participants; I2 = 61%; moderate-certainty evidence) Low-certainty evidence suggests that there may be little or no difference between methotrexate and actinomycin D treatment with respect to nausea (four studies, 466 women; RR 0.61, 95% CI 0.29 to 1.26) or any of the other individual side-effects reported, although data for all of these outcomes were insufficient and too inconsistent to be conclusive. Low-certainty evidence suggests that there may be little or no difference in the risk of severe adverse events (SAEs) between the groups overall (five studies, 515 women; RR 0.35, 95% CI 0.08 to 1.66; I² = 60%); however, the direction of effect favours methotrexate and more evidence is needed. Furthermore, evidence from subgroup analyses suggests that actinomycin D may be associated with a greater risk of SAEs than methotrexate (low-certainty evidence). We found no evidence on the effect of these treatments on future fertility. Actinomycin D is probably more likely to achieve a primary cure in women with low-risk GTN, and less likely to result in treatment failure, than a methotrexate regimen. There may be little or no difference between the pulsed actinomycin D regimen and the methotrexate regimen with regard to side-effects. However, actinomycin D may be associated with a greater risk of severe adverse events (SAEs) than a methotrexate regimen. Higher-certainty evidence is still needed on treating low-risk GTN and the four ongoing trials are likely to make a significant contribution to this field. Given the variety of treatment regimens, findings from these trials could facilitate a network meta-analysis in the next version of this review to help women and clinicians determine the best treatment options for low-risk GTN.\nOutput:\n" }, { "from": "agent", "value": "This is an updated version of a review that was first published in 2009. Since undertaking this review, we have searched the literature three times (2008, 2012 and 2016), and have identified seven completed randomised controlled trials (RCTs) and four ongoing trials. The completed trials compared three different treatment methotrexate regimens with two different actinomycin D regimens that differed by drug dose and dosing frequency. We assessed these trials as being at low to moderate risk of bias. We extracted and pooled data where possible, grouping the studies according to the treatments compared in the studies. What did we find? Overall, and for each treatment regimen compared, the review evidence shows that actinomycin D is probably more likely to achieve a cure in the first instance than methotrexate, and less likely to fail. Side-effects were reported to be relatively mild with either treatment and the most commonly experienced side-effects among women in the studies were nausea, fatigue and anaemia. However, the evidence on side-effects and serious adverse events is uncertain. Low-certainty evidence suggests that severe adverse events may be more common with actinomycin D, particularly with the five-day regimen. Conclusions Actinomycin D is probably a more effective treatment than methotrexate but the evidence on side-effects and severe adverse effects is uncertain and more evidence is needed. More evidence is also needed on the effects of these treatments on future fertility. Four RCTs comparing methotrexate and actinomycin D regimen are currently underway and these will make an important contribution to this field." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Nine studies (484 patients) met the pre-specified inclusion criteria (Kappa 1.00). Six studies were rated as low risk of bias. Three studies were rated as high risk of bias due to blinding (two open label and one single-blind). The total daily dose of rectal 5-ASA ranged from 0.5 g to 4 g, and dose frequency ranged from once to three times daily. 5-ASA was delivered as liquid enema in five studies or as a suppository in four studies. Follow-up ranged from 6 to 24 months. Rectal 5-ASA was significantly superior to placebo for maintenance of symptomatic remission over a period of 12 months.Sixty-two per cent of patients in the rectal 5-ASA group maintained symptomatic remission compared to 30% of patients in the placebo group (4 studies; 301 patients; RR 2.22, 95% CI 1.26 to 3.90; I2 = 67%; P < 0.01). A GRADE analysis indicated that the overall quality of the evidence for the primary outcome was low due to imprecision (i.e. sparse data 144 events) and inconsistency (i.e. unexplained heterogeneity). Rectal 5-ASA was significantly superior to placebo for maintenance of endoscopic remission over a 12 month period. Seventy-five per cent of patients in the rectal 5-ASA group maintained endoscopic remission compared to 15% of patients in the placebo group (1 study; 25 patients; RR 4.88, 95% CI 1.31 to 18.18; P < 0.05). There was no statistically significant difference in the proportion of patients who experienced at least one adverse event. Sixteen per cent of patients in the rectal 5-ASA group experienced at least one adverse compared to 12% of placebo patients (2 studies; 160 patients; RR 1.35, 95% CI 0.63 to 2.89; I2 = 0%; P = 0.44). The most commonly reported adverse events were anal irritation and abdominal pain. No statistically significant differences between rectal and oral 5-ASA were identified for either symptomatic or endoscopic remission over a period of six months. Eighty per cent of patients in the rectal 5-ASA group maintained symptomatic remission compared to 65% of patients in the oral 5-ASA group (2 studies; 69 patients; RR 1.24, 95% CI 0.92 to 1.66; I2 = 0%; P = 0.15). A GRADE analysis indicated that the overall quality of the evidence for the primary outcome was low due to imprecision (i.e. sparse data 50 events) and high risk of bias (i.e. both studies in the pooled analysis were open label). Eighty per cent of patients in the rectal 5-ASA group maintained endoscopic remission compared to 70% of patients in the oral 5-ASA group (2 studies; 91 patients; RR 1.14, 95% CI 0.90 to 1.45; I2 = 0%; P = 0.26). In two small trials, one comparing 2 g/day 5-ASA enemas to 4 g/day 5-ASA enemas and the other comparing 0.5 g/day 5-ASA suppositories to 1 g/day 5-ASA suppositories no dose response relationship was observed. The limited data available suggest that rectal 5-ASA is effective and safe for maintenance of remission of mild to moderately active distal UC. Well designed randomized trials are needed to establish the optimal dosing regimen for rectal 5-ASA, to compare rectal 5-ASA with rectal corticosteroids and to identify subgroups of patients who are more or less responsive to specific rectal 5-ASA regimens. The combination of oral and rectal 5-ASA appears to be more effective than either oral or rectal monotherapy for induction of remission. The efficacy of combination therapy for maintenance of remission has not been assessed and could be evaluated in future trials.\nOutput:\n" }, { "from": "agent", "value": "This review includes nine randomized trials with a total of 484 participants. The limited data available suggest that rectal 5-ASA is effective and safe for maintenance of remission in UC. Rectal 5-ASA was found to be superior to placebo (e.g. enema or suppository with no active medicine). There was no difference in the incidence of side effects between rectal 5-ASA and placebo groups. Side effects were generally mild in nature and common side effects included anal irritation and abdominal pain. Studies comparing rectal 5-ASA with oral 5-ASA (pills) found no differences in effectiveness for maintenance therapy. Well designed randomized trials are needed to investigate different doses of rectal 5-ASA for maintenance therapy, Future studies should assess the effectiveness of combination therapy of oral 5-ASA with rectal 5-ASA as this has been found to be effective in active UC and has not been investigated for maintenance therapy. Future studies should also compare rectal 5-ASA with rectal corticosteroids." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included 27 trials, enrolling 16,382 adults and children, and conducted between 2002 and 2010. Most trials excluded infants aged less than six months and pregnant women. DHA-P versus artemether-lumefantrine In Africa, over 28 days follow-up, DHA-P is superior to artemether-lumefantrine at preventing further parasitaemia (PCR-unadjusted treatment failure: RR 0.34, 95% CI 0.30 to 0.39, nine trials, 6200 participants, high quality evidence), and although PCR-adjusted treatment failure was below 5% for both ACTs, it was consistently lower with DHA-P (PCR-adjusted treatment failure: RR 0.42, 95% CI 0.29 to 0.62, nine trials, 5417 participants, high quality evidence). DHA-P has a longer prophylactic effect on new infections which may last for up to 63 days (PCR-unadjusted treatment failure: RR 0.71, 95% CI 0.65 to 0.78, two trials, 3200 participants, high quality evidence). In Asia and Oceania, no differences have been shown at day 28 (four trials, 1143 participants, moderate quality evidence), or day 63 (one trial, 323 participants, low quality evidence). Compared to artemether-lumefantrine, no difference was seen in prolonged QTc (low quality evidence), and no cardiac arrhythmias were reported. The frequency of other adverse events is probably similar with both combinations (moderate quality evidence). DHA-P versus artesunate plus mefloquine In Asia, over 28 days follow-up, DHA-P is as effective as artesunate plus mefloquine at preventing further parasitaemia (PCR-unadjusted treatment failure: eight trials, 3487 participants, high quality evidence). Once adjusted by PCR to exclude new infections, treatment failure at day 28 was below 5% for both ACTs in all eight trials, but lower with DHA-P in two trials (PCR-adjusted treatment failure: RR 0.41 95% CI 0.21 to 0.80, eight trials, 3482 participants, high quality evidence). Both combinations contain partner drugs with very long half-lives and no consistent benefit in preventing new infections has been seen over 63 days follow-up (PCR-unadjusted treatment failure: five trials, 2715 participants, moderate quality evidence). In the only trial from South America, there were fewer recurrent parastaemias over 63 days with artesunate plus mefloquine (PCR-unadjusted treatment failure: RR 6.19, 95% CI 1.40 to 27.35, one trial, 445 participants, low quality evidence), but no differences were seen once adjusted for new infections (PCR-adjusted treatment failure: one trial, 435 participants, low quality evidence). DHA-P is associated with less nausea, vomiting, dizziness, sleeplessness, and palpitations compared to artesunate plus mefloquine (moderate quality evidence). DHA-P was associated with more frequent prolongation of the QTc interval (low quality evidence), but no cardiac arrhythmias were reported. In Africa, dihydroartemisinin-piperaquine reduces overall treatment failure compared to artemether-lumefantrine, although both drugs have PCR-adjusted failure rates of less than 5%. In Asia, dihydroartemisinin-piperaquine is as effective as artesunate plus mefloquine, and is better tolerated.\nOutput:\n" }, { "from": "agent", "value": "This review summarises trials evaluating the effects of dihydroartemisinin-piperaquine (DHA-P) compared to other artemisinin-based combination therapies recommended by the World Health Organization. After searching for relevant trials up to July 2013, we included 27 randomized controlled trials, enrolling 16,382 adults and children and conducted between 2002 and 2010. What is uncomplicated malaria and how might dihydroartemisinin-piperaquine work Uncomplicated malaria is the mild form of malaria which usually causes a fever, with or without headache, tiredness, muscle pains, abdominal pains, nausea, and vomiting. If left untreated, uncomplicated malaria can develop into severe malaria with kidney failure, breathing difficulties, fitting, unconsciousness, and eventually death. DHA-P is one of five artemisinin-based combination therapies the World Health Organization currently recommends to treat malaria. These combinations contain an artemisinin component (such as dihydroartemisinin) which works very quickly to clear the malaria parasite from the person's blood, and a longer acting drug (such as piperaquine) which clears the remaining parasites from the blood and may prevent new infections with malaria for several weeks. What the research says DHA-P versus artemether lumefantrine In studies of people living in Africa, both DHA-P and artemether-lumefantrine are very effective at treating malaria (high quality evidence). However, DHA-P cures slightly more patients than artemether-lumefantrine, and it also prevents further malaria infections for longer after treatment (high quality evidence). DHA-P and artemether-lumefantrine probably have similar side effects (moderate quality evidence). DHA-P versus artesunate plus mefloquine In studies of people living in Asia, DHA-P is as effective as artesunate plus mefloquine at treating malaria (moderate quality evidence). Artesunate plus mefloquine probably causes more nausea, vomiting, dizziness, sleeplessness, and palpitations than DHA-P (moderate quality evidence). Overall, in some people, DHA-P has been seen to cause short term changes in electrocardiographs tracing the conduction of the heart rhythm (low quality evidence), but these small changes on the electrocardiograph resolved within one week without serious consequences." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We found 19 RCTs that met our eligibility criteria. Eleven trials compared different combined oral contraceptives (COCs) or regimens of COCs; five examined an injectable versus another injectable, implant, or IUD; two studied implants, and one compared the transdermal patch versus the vaginal ring. No trial had fracture as an outcome. BMD was measured in 17 studies and 12 trials assessed biochemical markers of bone turnover. Depot medroxyprogesterone acetate (DMPA) was associated with decreased bone mineral density (BMD). The placebo-controlled trials showed BMD increases for DMPA plus estrogen supplement and decreases for DMPA plus placebo supplement. COCs did not appear to negatively affect BMD, and some formulations had more positive effects than others. However, no COC trial was placebo-controlled. Where studies showed differences between groups in bone turnover markers, the results were generally consistent with those for BMD. For implants, the single-rod etonogestrel group showed a greater BMD decrease versus the two-rod levonorgestrel group but results were not consistent across all implant comparisons. The sensitivity analysis included 11 trials providing evidence of moderate or high quality. Four trials involving DMPA showed some positive effects of an estrogen supplement on BMD, a negative effect of DMPA-subcutaneous on lumbar spine BMD, and a negative effect of DMPA on a bone formation marker. Of the three COC trials, one had a BMD decrease for the group with gestodene plus EE 15 μg. Another indicated less bone resorption in the group with gestodene plus EE 30 μg versus EE 20 μg. Whether steroidal contraceptives influence fracture risk cannot be determined from existing information. The evidence quality was considered moderate overall, largely due to the trials of DMPA, implants, and the patch versus ring. The COC evidence varied in quality but was low overall. Many trials had small numbers of participants and some had large losses. Health care providers and women should consider the costs and benefits of these effective contraceptives. For example, injectable contraceptives and implants provide effective, long-term birth control yet do not involve a daily regimen. Progestin-only contraceptives are considered appropriate for women who should avoid estrogen due to medical conditions.\nOutput:\n" }, { "from": "agent", "value": "Through April 2014, we did computer searches for studies of birth control methods containing hormones and risk of fractures. Outcomes could also be bone mineral density or markers of bone changes. Birth control pills included types with both estrogen and progestin. Also included were implants and injectables with only progestin. We wrote to researchers to find other trials. We included randomized trials in any language that had at least three treatment cycles. The studies had to compare two types of birth control or one type of birth control or a supplement with a placebo or 'dummy' method. We found 19 trials. Fifteen studies compared one birth control method with another hormone method. Two trials used a placebo or 'dummy.' One compared a hormone method to a method without hormones. None had fractures as an outcome and most looked at bone density. Birth control methods with both estrogen and progestin did not appear to affect bone health. However, 'depo,' which is injected and has only progestin, was related to lower bone density. The two depo trials with placebos showed increased bone density when some estrogen was given to women on depo. Bone density decreased in women who got a 'dummy' with the depo. Whether this decrease is important to the woman's health is not known. For implants, an etonogestrel implant with one rod showed a greater decrease in bone density than a two-rod levonorgestrel implant. However, other implants studied did not show the same pattern. The studies had data of moderate quality. Whether hormonal contraceptives affect fracture risk cannot be judged from current information. These contraceptive methods work well for birth control. Health-care providers and women should think about the costs and benefits. For instance, injectable use can occur without a partner's knowledge, and is simpler than taking pills every day. Also, progestin-only methods are suggested for some women with health problems who should avoid estrogen." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Six trials met the inclusion criteria. We have not found any new studies since the initial review. In the trial comparing the desogestrel versus levonorgestrel progestin-only pill, desogestrel was not associated with a significantly lower risk of accidental pregnancy; the rate ratio was 0.27 (95% CI 0.06 to 1.19). However, the desogestrel progestin-only pill caused more bleeding problems, although this difference was not statistically significant. The trial comparing low-dose mifepristone versus a levonorgestrel progestin-only pill found similar pregnancy rates. In the trial comparing ethynodiol diacetate versus a combined oral contraceptive, irregular cycles occurred in all women assigned to the progestin-only pill (odds ratio 135.96; 95% CI 7.61 to 2421.02). In a trial comparing two progestin-only and two combined oral contraceptives, the progestin-only pill containing levonorgestrel 30 μg had higher efficacy than did the pill containing norethisterone 350 μg. An early trial found megestrol acetate inferior to other progestin-only pills in terms of efficacy. A study of the timing of pill initiation after birth found no important differences, but high losses to follow up undermined the trial. Evidence is insufficient to compare progestin-only pills to each other or to combined oral contraceptives.\nOutput:\n" }, { "from": "agent", "value": "We found six trials for the initial review. We have not found any more studies since then. Some studies are several decades old and not very relevant to pills available today. A newer pill containing the progestin desogestrel may work better to prevent pregnancy than an older pill with levonorgestrel. The newer pill caused more bleeding problems. Pills with levonorgestrel may be more effective than pills with other progestins that are no longer used. These studies are not adequate to tell how progestin-only pills compare to each other or to combined (two-hormone) pills. Larger studies with currently used pills are needed to answer these questions." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We identified 26 studies (8835 participants). Risk of bias was high in 17, unclear in 6and low in three studies. There was high risk of attrition bias in six studies. Only two studies measured AKI. The use of NSAIDs had uncertain effects on the incidence of AKI compared to placebo (7066 participants: RR 1.79, 95% CI 0.40 to 7.96; I2 = 59%; very low certainty evidence). One study was stopped early by the data monitoring committee due to increased rates of AKI in the NSAID group. Moreover, both of these studies were examining NSAIDs for indications other than analgesia and therefore utilised relatively low doses. Compared to placebo, NSAIDs may slightly increase serum SCr (15 studies, 794 participants: MD 3.23 μmol/L, 95% CI -0.80 to 7.26; I2 = 63%; low certainty evidence). Studies displayed moderate to high heterogeneity and had multiple exclusion criteria including age and so were not representative of patients undergoing surgery. Three of these studies excluded patients if their creatinine rose post-operatively. NSAIDs may make little or no difference to post-operative urine output compared to placebo (6 studies, 149 participants: SMD -0.02, 95% CI -0.31 to 0.27). No reliable conclusions could be drawn from these studies due to the differing units of measurements and measurement time points. It is uncertain whether NSAIDs leads to the need for RRT because the certainty of this evidence is very low (2 studies, 7056 participants: RR 1.57, 95% CI 0.49 to 5.07; I2 = 26%); there were few events and the results were inconsistent. It is uncertain whether NSAIDs lead to more deaths (2 studies, 312 participants: RR 1.44, 95% CI 0.19 to 11.12; I2 = 38%) or increased the length of hospital stay (3 studies, 410 participants: MD 0.12 days, 95% CI -0.48 to 0.72; I2 = 24%). Overall NSAIDs had uncertain effects on the risk of post-operative AKI, may slightly increase post-operative SCr, and it is uncertain whether NSAIDs lead to the need for RRT, death or increases the length of hospital stay. The available data therefore does not confirm the safety of NSAIDs in patients undergoing surgery. Further larger studies using the Kidney Disease Improving Global Outcomes definition for AKI including patients with co-morbidities are required to confirm these findings. .\nOutput:\n" }, { "from": "agent", "value": "We identified 26 studies studying 8835 participants. Risk of bias was high in 17, unclear in six studies and low in three studies. The use NSAIDs had uncertain effects on the incidence of AKI compared to placebo. Quality of evidence was very low due to inconsistencies between the two studies. One study was stopped early by the data monitoring committee due to increased rates of AKI in the NSAID group and both of these studies examined much lower doses of NSAIDs than would usually be used for pain relief. NSAIDs may slightly increase serum creatinine (a marker of kidney function which rises in kidney failure) compared with placebo. Quality of evidence was low. These studies only included fit, healthy patients. No reliable conclusions could be drawn from the studies examining urine output due to the different methods of measuring this. It is uncertain whether the use of NSAIDs leads to an increased need for renal replacement therapy (dialysis), more deaths, or increased length of hospital stay. NSAIDs have uncertain effects on the rates of AKI when used in patients with normal kidney function following surgery. It is uncertain whether NSAIDs increase the need for dialysis. The available data therefore does not confirm the safety of NSAIDs in patients undergoing surgery. Further studies including patients with other health problems are required." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included 22 studies (total of 2761 participants). Of those 22 studies, 12 were included in the original published review and 10 were newly identified. Eleven trials compared the use of fluconazole to placebo or no antifungal treatment. Three trials compared ketoconazole versus placebo. One trial compared anidulafungin with placebo. One trial compared caspofungin to placebo. Two trials compared micafungin to placebo. One trial compared amphotericin B to placebo. Two trials compared nystatin to placebo and one trial compared the effect of clotrimazole, ketoconazole, nystatin and no treatment. We found two new ongoing studies and four new studies awaiting classification. The RCTs included participants of both genders with wide age range, severity of critical illness and clinical characteristics. Funding sources from pharmaceutical companies were reported in 11 trials and one trial reported funding from a government agency. Most of the studies had an overall unclear risk of bias for key domains of this review (random sequence generation, allocation concealment, incomplete outcome data). Two studies had a high risk of bias for key domains. Regarding the other domains (blinding of participants and personnel, outcome assessment, selective reporting, other bias), most of the studies had a low or unclear risk but four studies had a high risk of bias. There was moderate grade evidence that untargeted antifungal treatment did not significantly reduce or increase total (all-cause) mortality (RR 0.93, 95% CI 0.79 to 1.09, P value = 0.36; participants = 2374; studies = 19). With regard to the outcome of proven invasive fungal infection, there was low grade evidence that untargeted antifungal treatment significantly reduced the risk (RR 0.57, 95% CI 0.39 to 0.83, P value = 0.0001; participants = 2024; studies = 17). The risk of fungal colonization was significantly reduced (RR 0.71, 95% CI 0.52 to 0.97, P value = 0.03; participants = 1030; studies = 12) but the quality of evidence was low. There was no difference in the risk of developing superficial fungal infection (RR 0.69, 95% CI 0.37 to 1.29, P value = 0.24; participants = 662; studies = 5; low grade of evidence) or in adverse events requiring cessation of treatment between the untargeted treatment group and the other group (RR 0.89, 95% CI 0.62 to 1.27, P value = 0.51; participants = 1691; studies = 11; low quality of evidence). The quality of evidence for the outcome of total (all-cause) mortality was moderate due to limitations in study design. The quality of evidence for the outcome of invasive fungal infection, superficial fungal infection, fungal colonization and adverse events requiring cessation of therapy was low due to limitations in study design, non-optimal total population size, risk of publication bias, and heterogeneity across studies. There is moderate quality evidence that the use of untargeted antifungal treatment is not associated with a significant reduction in total (all-cause) mortality among critically ill, non-neutropenic adults and children compared to no antifungal treatment or placebo. The untargeted antifungal treatment may be associated with a reduction of invasive fungal infections but the quality of evidence is low, and both the heterogeneity and risk of publication bias is high. Further high-quality RCTs are needed to improve the strength of the evidence, especially for more recent and less studied drugs (e.g. echinocandins). Future trials should adopt standardized definitions for microbiological outcomes (e.g. invasive fungal infection, colonization) to reduce heterogeneity. Emergence of resistance to antifungal drugs should be considered as outcome in studies investigating the effects of untargeted antifungal treatment to balance risks and benefit.\nOutput:\n" }, { "from": "agent", "value": "We included 22 randomized controlled trials (RCTs) (total of 2761 participants). Eleven trials compared the use of fluconazole to placebo or no antifungal treatment. Three trials compared ketoconazole versus placebo. One trial compared anidulafungin with placebo. One trial compared caspofungin to placebo. Two trials compared micafungin to placebo. One trial compared amphotericin B to placebo. Two trials compared nystatin to placebo and one trial compared the effect of clotrimazole, ketoconazole, nystatin and no treatment. The RCTs included participants of both genders with a wide age range and severity of critical illness. The evidence is current as of February 2015. Funding sources from drug manufacturers were reported in 11 out of 22 studies. Another study was funded by a government agency. Results of 19 from 22 randomized trials involved 2374 participants and showed that antifungal medications given before definitive diagnosis of fungal infection did not reduce mortality from all causes. None of the studied drugs were associated with a significant reduction of mortality from all causes. However, results from 17 randomized studies involving 2024 participants showed that antifungal drugs significantly reduced the risk of developing invasive fungal infections. We also reviewed the evidence from five trials (662 participants) about the effect of antifungal treatment on the development of superficial fungal infections but we did not find any significant difference. However, we found evidence from 12 trials (1020 participants) of a significant reduction of fungi in body sites (excluding blood) not causing an infection. Eleven trials (1691 participants) reported serious adverse events requiring cessation of therapy. We found no evidence of differences in serious adverse events requiring interruption of antifungal medications between people who received and those who did not receive them. The quality of evidence for the outcome of mortality (all-cause) was moderate due to limitations in study design. The quality of evidence for the outcome of invasive fungal infection, superficial fungal infection, fungal colonization and adverse events requiring cessation of therapy was low due to limitations in study design, non-optimal total number of patients studied and results inconsistent across studies. There is moderate quality evidence that the use of antifungal treatment given before definitive diagnosis of fungal infection is not associated with a significant reduction in mortality from all causes among critically ill adults and children with a normal number of neutrophils in the blood. This type of antifungal treatment may be associated with a reduction of invasive fungal infections but the quality of evidence on this point is low. Further studies with high-quality design are needed to improve the evidence." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Sixteen studies with a combined total of 34,369 participants with an acute medical illness were included in this review. We identified 10 studies comparing heparin with placebo or no treatment and six studies comparing LMWH to UFH. Just under half of the studies had an open-label design, putting them at a risk of performance bias. Descriptions of random sequence generation and allocation concealment were missing in most of the studies. Heparin reduced the odds of deep vein thrombosis (DVT) (OR 0.41, 95% CI 0.25 to 0.67; P = 0.0004) . The estimated reductions in symptomatic non-fatal pulmonary embolism (PE) (OR 0.46; 95% CI 0.20 to 1.07; P = 0.07), fatal PE (OR 0.71; 95% CI 0.43 to 1.15; P = 0.16) and in combined non-fatal PE and fatal PE (OR 0.66, 95% CI 0.43 to 1.02; P = 0.06) associated with heparin were imprecise. Heparin resulted in an increase in major haemorrhage (OR 1.65, 95% CI 1.01 to 2.71; P = 0.05). There was no clear evidence that heparin had an effect on all-cause mortality and thrombocytopaenia. Compared with UFH, LMWH reduced the risk of DVT (OR 0.77; 95% CI 0.62 to 0.96; P = 0.02) and major bleeding (OR 0.43; 95% CI 0.22 to 0.83; P = 0.01). There was no clear evidence that the effects of LMWH and UFH differed for the PE outcomes, all-cause mortality and thrombocytopaenia. The data from this review describe a reduction in the risk of DVT in patients presenting with an acute medical illness who receive heparin thromboprophylaxis. This needs to be balanced against an increase in the risk of bleeding associated with thromboprophylaxis. The analysis favoured LMWH compared with UFH, with a reduced risk of both DVT and bleeding.\nOutput:\n" }, { "from": "agent", "value": "This review of 16 trials in 34,369 non-surgical patients who suffered an acute medical illness found that heparin reduced the number of patients suffering DVTs but also increased the risk of bleeding complications when compared to participants that received a placebo or no medication. We had some concerns over how reliable the results were from the unblinded studies, which made up just under half of the studies. Also, most of the studies were lacking explanations of how the allocation of the treatments was performed. The lower risk of PEs (when combining those that caused death and those that did not) with heparin could have been a chance effect. There was no clear evidence of a difference in the rate of death or thrombocytopaenia. The review also found that patients who were given LMWH developed fewer DVTs and fewer bleeding complications compared with those given UFH, leading to the conclusion that LMWH is more effective and carries a lower risk of adverse events in preventing blood clots than with UFH. There was no clear evidence of differences between LMWH and UFH for PE, death or thrombocytopaenia." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Our search retrieved 1311 unique citations, of which 1289 were excluded after title and abstract screening. Of the remaining 22, we excluded 19 because they were empirical studies that were not randomized, quasi-randomized or cluster-randomized controlled trials (n = 12), because they were review articles (n = 3), because they described protocols only (n = 2), they were conducted among cigarette smokers only (n = 1), or they had only a three-month follow-up (n = 1). We identified three controlled trials which tested cessation interventions for waterpipe smokers. Studies were carried out in Egypt (Mohlman 2013), Pakistan (Dogar 2014), and the US (Lipkus 2011). One was a randomized controlled trial and two were cluster-randomized trials. Two studies tested individual-level interventions, and one tested a community-level intervention. Two studies included only behavioural interventions, and one study (Dogar 2014) included two intervention groups: one behavioural, and the other behavioural with bupropion. The Lipkus and Mohlman studies delivered waterpipe-specific interventions, and the Dogar study delivered a non-specific tobacco intervention. Due to study variation we did not pool results, and intervention effects are reported descriptively. Compared to control groups, waterpipe smoking cessation rates were higher in the intervention groups in all three studies, with a significant difference in two studies. For the Dogar study, the RRs for waterpipe smoking abstinence at 25 weeks among waterpipe-only smokers were 2.2 (95% confidence interval (CI) 1.3 to 3.8; 180 participants) in the behavioural group, and 2.5 (95% CI 1.3 to 4.7; 84 participants) in the behavioural plus bupropion group. In our analysis we have combined both groups, to give a RR of 2.28 (95% CI 1.36 to 3.83; 200 participants). The Mohlman study delivered a RR in male waterpipe-smokers at one year in favour of the intervention of 3.25 (95% CI 1.19 to 8.89). Although the literature on waterpipe cessation interventions remains sparse, the reviewed studies provide a basis for developing interventions in this area. The lack of statistically significant effects in one of the three studies is not unexpected, given the small and pilot nature of the studies. The studies highlight important design and content issues that need to be considered for future cessation trials in waterpipe smokers. These include building on the vast experience developed in the study of smoking cessation interventions in cigarette smokers, whilst including components and assessment tools that address the specific aspects of waterpipe smoking, such as its social dimension, unique experiences, and cues.\nOutput:\n" }, { "from": "agent", "value": "We searched for controlled trials in the Cochrane Tobacco Addiction Review Group specialized register, in June 2015. We also searched a number of electronic databases, including MEDLINE, EMBASE, PsycINFO and CINAHL, using a variety of names and spellings for waterpipe use ('waterpipe' or 'narghile' or 'arghile' or 'shisha' or 'goza' or 'narkeela' or 'hookah' or 'hubble bubble'). We searched for published and unpublished trials in any language, and especially in areas where waterpipe use is widespread. We identified three studies that tested behavioural methods to help waterpipe smokers to quit. Two were waterpipe-specific interventions and one was a non-specific tobacco intervention.One small, pilot study was set in the USA, and delivered a Powerpoint presentation online to 91 college students who were using waterpipe. One study was a secondary analysis of data from 264 waterpipe smokers who were part of a trial that enrolled people suspected of having tuberculosis from 33 healthcare clinics in Pakistan. Clinics were randomly assigned to deliver a behavioural intervention versus control (usual care), or a behavioural intervention plus medication (bupropion) versus control (usual care). The third study, set in Egypt, targeted both cigarette and waterpipe smokers, and was a community-based programme. In all three trials, the percentage of participants who stopped smoking waterpipe was higher in the intervention groups than in the control groups, although this was a statistically significant finding in only two of the trials. People who received either behavioural treatment or behavioural treatment plus buproprion were more likely to quit waterpipe smoking at six months follow-up than those who received usual care. Men smoking waterpipe in the Egyptian study were more likely to have quit at one year follow-up in the intervention villages than in the control villages. These studies provide support to suggest that cessation interventions may help waterpipe smokers to quit. However, further larger studies are needed to build on this. The trials were all rated at very low quality of evidence, as they were relatively small studies, with at least one high risk of bias." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Eleven trials that randomized 1838 participants met the study inclusion criteria. Seven of the trials included femoropopliteal arterial lesions, three included tibial arterial lesions, and one included both. The trials were carried out in Europe and in the USA and all used the taxane drug paclitaxel in the DEB arm. Nine of the 11 trials were industry-sponsored. Four companies manufactured the DEB devices (Bard, Bavaria Medizin, Biotronik, and Medtronic). The trials examined both anatomic and clinical endpoints. There was heterogeneity in the frequency of stent deployment and the type and duration of antiplatelet therapy between trials. Using GRADE assessment criteria, the quality of the evidence presented was moderate for the outcomes of target lesion revascularization and change in Rutherford category, and high for amputation, primary vessel patency, binary restenosis, death, and change in ankle-brachial index (ABI). Most participants were followed up for 12 months, but one trial reported outcomes at five years. There were better outcomes for DEBs for up to two years in primary vessel patency (odds ratio (OR) 1.47, 95% confidence interval (CI) 0.22 to 9.57 at six months; OR 1.92, 95% CI 1.45 to 2.56 at 12 months; OR 3.51, 95% CI 2.26 to 5.46 at two years) and at six months and two years for late lumen loss (mean difference (MD) -0.64 mm, 95% CI -1.00 to -0.28 at six months; MD -0.80 mm, 95% CI -1.44 to -0.16 at two years). DEB were also superior to uncoated balloon angioplasty for up to five years in target lesion revascularization (OR 0.28, 95% CI 0.17 to 0.47 at six months; OR 0.40, 95% CI 0.31 to 0.51 at 12 months; OR 0.28, 95% CI 0.18 to 0.44 at two years; OR 0.21, 95% CI 0.09 to 0.51 at five years) and binary restenosis rate (OR 0.44, 95% CI 0.29 to 0.67 at six months; OR 0.38, 95% CI 0.15 to 0.98 at 12 months; OR 0.26, 95% CI 0.10 to 0.66 at two years; OR 0.12, 95% CI 0.05 to 0.30 at five years). There was no significant difference between DEB and uncoated angioplasty in amputation, death, change in ABI, change in Rutherford category and quality of life (QoL) scores, or functional walking ability, although none of the trials were powered to detect a significant difference in these clinical endpoints. We carried out two subgroup analyses to examine outcomes in femoropopliteal and tibial interventions as well as in people with CLI (4 or greater Rutherford class), and showed no advantage for DEBs in tibial vessels at six and 12 months compared with uncoated balloon angioplasty. There was also no advantage for DEBs in CLI compared with uncoated balloon angioplasty at 12 months. Based on a meta-analysis of 11 trials with 1838 participants, there is evidence of an advantage for DEBs compared with uncoated balloon angioplasty in several anatomic endpoints such as primary vessel patency (high-quality evidence), binary restenosis rate (moderate-quality evidence), and target lesion revascularization (low-quality evidence) for up to 12 months. Conversely, there is no evidence of an advantage for DEBs in clinical endpoints such as amputation, death, or change in ABI, or change in Rutherford category during 12 months' follow-up. Well-designed randomized trials with long-term follow-up are needed to compare DEBs with uncoated balloon angioplasties adequately for both anatomic and clinical study endpoints before the widespread use of this expensive technology can be justified.\nOutput:\n" }, { "from": "agent", "value": "Our review included 11 clinical trials that randomized 1838 participants (current until December 2015). The trials included thigh and leg arteries above and below the knee. The trials were carried out in Europe and the USA, and all used DEBs that contained paclitaxel. Four companies manufactured the DEB devices: Bard, Bavaria Medizin, Biotronik, and Medtronic. Most participants were followed for 12 or more months (called follow-up). At six and 12 months of follow-up, DEBs were associated with improved primary vessel patency, which is an indicator of whether a vessel is still patent without any further interventions (blood flowing well), late lumen loss, which is the difference in millimeters between the angioplastied segment and how narrow it is on follow-up, target lesion revascularization, which is an indicator of whether a person received more than one treatment to the same artery during the period covered by the study, and binary restenosis, which occurs when a treated artery becomes narrowed again after being previously treated. Unfortunately, early anatomic (structural) advantages of DEBs were not accompanied by improvements in quality of life, functional walking ability, or in the occurrence of amputation or death. When we specifically examined arteries below the knee and people who had very advanced PAD, we found no clinical or angiographic advantage for DEBs at 12 months of follow-up compared with uncoated balloon angioplasty. In summary, DEBs have several anatomic advantages over uncoated balloons for the treatment of lower limb PAD for up to 12 months after undergoing the procedure. However, more data are needed to assess the long-term results of this treatment option adequately. All the trials had differences in the way in which they inserted the balloons, and in the type and duration of additional antiplatelet (anticlotting) therapy, leading to downgrading of the quality of the evidence. The quality of the evidence presented was moderate for target lesion revascularization and change in Rutherford category (a way of classifying PAD), and high for amputation, primary vessel patency, binary restenosis, death, and change in ankle-brachial index (which is used to predict the severity of PAD)." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We deemed six studies (309 participants), based on adult populations with intellectual disabilities, suitable for inclusion in the current version of this review. These studies examined a range of cognitive-behavioural therapy (CBT) approaches: anger management (three studies (n = 235); one individual therapy and two group-based); relaxation (one study; n = 12), mindfulness based on meditation (one study; n = 34), problem solving and assertiveness training (one study; n = 28). We were unable to include any studies using behavioural interventions. There were no studies of children. Only one study reported moderate quality of evidence for outcomes of interest as assessed by the Grades of Recommendations, Assessment, Development and Evaluation (GRADE) approach. We judged the evidence for the remaining studies to be of very low to low quality. Most studies were at risk of bias in two or more domains: one study did not randomly allocate participants and in two studies the process of randomisation was unclear; in one study there was no allocation concealment and in three studies this was unclear; blinding of assessors did not occur in three studies; incomplete outcome data were presented in one study and unclear in two studies; there was selective reporting in one study; and other biases were present in one study and unclear in four studies. Three of the six studies showed some benefit of the intervention on improving anger ratings. We did not conduct a meta-analysis, as we considered the studies too heterogeneous to combine (e.g. due to differences in the types of participants, sample size interventions, and outcome measures). Follow-up data for anger ratings for both the treatment and control groups were available for two studies. Only one of these studies (n = 161) had adequate long-term data (10 months), which found some benefit of treatment at follow-up (continued improvement in anger coping skills as rated by key workers; moderate-quality evidence). Two studies (n = 192) reported some evidence that the intervention reduces the number of incidents of aggression and one study (n = 28) reported evidence that the intervention improved mental health symptoms. One study investigated the effects of the intervention on quality of life and cost of health and social care utilisation. This study provided moderate-quality evidence, which suggests that compared to no treatment, behavioural or cognitive-behavioural interventions do not improve quality of life at 16 weeks (n = 129) or at 10 months follow-up (n = 140), or reduce the cost of health service utilisation (n = 133). Only one study (n = 28) assessed adaptive functioning. It reported evidence that assertiveness and problem-solving training improved adaptive behaviour. No studies reported data on adverse events. The existing evidence on the effectiveness of behavioural and cognitive-behavioural interventions on outwardly-directed aggression in children and adults with intellectual disabilities is limited. There is a paucity of methodologically sound clinical trials and a lack of long-term follow-up data. Given the impact of such behaviours on the individual and his or her support workers, effective interventions are essential. We recommend that randomised controlled trials of sufficient power are carried out using primary outcomes that include reduction in outward-directed aggressive behaviour, improvement in quality of life, and cost effectiveness.\nOutput:\n" }, { "from": "agent", "value": "We searched a number of electronic databases in April 2014 to ensure that the review was up-to-date. We included six studies in the review with a total number of 309 participants. Three studies examined anger management, one study examined assertiveness training and problem solving, one study examined 'mindfulness' based on meditation, and one study examined modified relaxation. All the studies were conducted in community settings apart from one, which was conducted in a forensic inpatient setting. Five of these studies were small, comprising between 12 and 40 participants, and one was a large study of 179 participants, which was funded by the National Institute for Health Research (NIHR) Health Technology Assessment (HTA) programme. Information on funding was not available for the other studies. Follow-up data were available only for two studies. We found improved outcomes in five studies, including reduction in anger ratings and in aggressive incidents, at the end of treatment. One study found improvements in anger coping skills as reported by key workers at 16 weeks and 10 months, but no other long-term benefit. One large study did not find improvements in quality of life or reduced costs to health services. Due to differences in the types of interventions, populations and assessments, we could not combine the results of the studies. There was one large study which presented moderate-quality data on the outcomes of interest. The other included studies were small and of poor methodological quality. Based on a 'Grades of Recommendation, Assessment, Development and Evaluation' (GRADE) assessment, we judged the quality of evidence on the outcomes of interest to range from very low to moderate quality. Moreover, the diversity of the interventions and participant groups makes it difficult for us to draw firm conclusions about the effectiveness of any particular approach. Therefore, more good-quality studies with longer-term follow-up data are needed." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included 28 trials, involving 5855 participants, comparing stroke unit care with an alternative service. More-organised care was consistently associated with improved outcomes. Twenty-one trials (3994 participants) compared stroke unit care with care provided in general wards. Stroke unit care showed reductions in the odds of death recorded at final (median one year) follow-up (odds ratio (OR) 0.81, 95% Confidence Interval (CI) 0.69 to 0.94; P = 0.005), the odds of death or institutionalised care (OR 0.78, 95% CI 0.68 to 0.89; P = 0.0003) and the odds of death or dependency (OR 0.79, 95% CI 0.68 to 0.90; P = 0.0007). Sensitivity analyses indicated that the observed benefits remained when the analysis was restricted to securely randomised trials that used unequivocally blinded outcome assessment with a fixed period of follow-up. Outcomes were independent of patient age, sex, initial stroke severity or stroke type, and appeared to be better in stroke units based in a discrete ward. There was no indication that organised stroke unit care resulted in a longer hospital stay. Stroke patients who receive organised inpatient care in a stroke unit are more likely to be alive, independent, and living at home one year after the stroke. The benefits were most apparent in units based in a discrete ward. We observed no systematic increase in the length of inpatient stay.\nOutput:\n" }, { "from": "agent", "value": "This review of 28 trials, involving 5855 participants, showed that patients who receive this care are more likely to survive their stroke, return home and become independent in looking after themselves. A variety of different types of stroke unit have been developed. The best results appear to come from those which are based in a dedicated ward." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Five trials, which together enrolled 4965 infants, were eligible for inclusion. The investigators of these five trials had prospectively planned to combine their data as part of the NeOProM (Neonatal Oxygen Prospective Meta-analysis) Collaboration. We graded the quality of evidence as high for the key outcomes of death, major disability, the composite of death or major disability, and necrotising enterocolitis; and as moderate for blindness and retinopathy of prematurity requiring treatment. When an aligned definition of major disability was used, there was no significant difference in the composite primary outcome of death or major disability in extremely preterm infants when targeting a lower (SpO₂ 85% to 89%) versus a higher (SpO₂ 91% to 95%) oxygen saturation range (typical RR 1.04, 95% confidence interval (CI) 0.98 to 1.10; typical RD 0.02, 95% CI -0.01 to 0.05; 5 trials, 4754 infants) (high-quality evidence). Compared with a higher target range, a lower target range significantly increased the incidence of death at 18 to 24 months corrected age (typical RR 1.16, 95% CI 1.03 to 1.31; typical RD 0.03, 95% CI 0.01 to 0.05; 5 trials, 4873 infants) (high-quality evidence) and necrotising enterocolitis (typical RR 1.24, 95% 1.05 to 1.47; typical RD 0.02, 95% CI 0.01 to 0.04; 5 trials, 4929 infants; I² = 0%) (high-quality evidence). Targeting the lower range significantly decreased the incidence of retinopathy of prematurity requiring treatment (typical RR 0.72, 95% CI 0.61 to 0.85; typical RD -0.04, 95% CI -0.06 to -0.02; 5 trials, 4089 infants; I² = 69%) (moderate-quality evidence). There were no significant differences between the two treatment groups for major disability including blindness, severe hearing loss, cerebral palsy, or other important neonatal morbidities. A subgroup analysis of major outcomes by type of oximeter calibration software (original versus revised) found a significant difference in the treatment effect between the two software types for death (interaction P = 0.03), with a significantly larger treatment effect seen for those infants using the revised algorithm (typical RR 1.38, 95% CI 1.13 to 1.68; typical RD 0.06, 95% CI 0.01 to 0.10; 3 trials, 1716 infants). There were no other important differences in treatment effect shown by the subgroup analyses using the currently available data. In extremely preterm infants, targeting lower (85% to 89%) SpO₂ compared to higher (91% to 95%) SpO₂ had no significant effect on the composite outcome of death or major disability or on major disability alone, including blindness, but increased the average risk of mortality by 28 per 1000 infants treated. The trade-offs between the benefits and harms of the different oxygen saturation target ranges may need to be assessed within local settings (e.g. alarm limit settings, staffing, baseline outcome risks) when deciding on oxygen saturation targeting policies.\nOutput:\n" }, { "from": "agent", "value": "The studies we included were randomised trials that enrolled babies born at less than 28 weeks' gestation, at birth or soon thereafter, and targeted oxygen saturation (SpO₂) ranges of either 85% to 89% or 91% to 95%, for at least the first two weeks of life. We included five trials, which together enrolled 4965 infants, in this review. There were benefits and harms associated with both the target ranges tested. Neither the lower nor the higher target range had a significant effect on the rate of death or major disability (the main outcome), on major disability alone or on blindness. However, infants in whom the lower oxygen range was targeted had, on average, a 2.8% increased risk of death, compared to the infants in whom the higher oxygen range was targeted. They also had a 2.2% increase in the rate of a serious bowel condition known as necrotising enterocolitis. Conversely, the infants in whom the lower oxygen range was targeted had a 4.2% decrease in the rate of a serious eye problem, retinopathy of prematurity, requiring surgery or other treatments. The trade-offs between these benefits and harms may need to be assessed within local settings when deciding on oxygen saturation targeting policies. We rated the quality of the evidence as high for the key outcomes of death, major disability, the composite of death or major disability, and necrotising enterocolitis. We rated the quality of evidence as moderate for the two eye-related outcomes (blindness, retinopathy of prematurity requiring treatment), giving us confidence that the overall results are reliable." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included one study involving 15 participants from the UK. The included participants were diagnosed with delirium based on the Confusion Assessment Method (CAM) criteria. Eight males and seven females were included, with a mean age of 82.5 years. Seven of the 15 participants had comorbid dementia at baseline. The risk of bias was low in all domains. The study compared rivastigmine with placebo. We did not find any clear differences between the two groups in terms of duration of delirium (MD -3.6, 95% CI -15.6 to 8.4), adverse events (nausea, RR 0.30, 95% CI 0.01 to 6.29), use of rescue medications (RR 0.13, 95% CI 0.01 to 2.1), mortality (RR 0.10, 95% CI 0.01 to 1.56), and leaving the study early (RR 0.88, 95% CI 0.07 to 11.54). Evidence was not available regarding the severity of delirium, persistent cognitive impairment, length of hospitalisation, cost of intervention, or other predefined secondary outcomes. The quality of evidence is low due to the very small sample size. There is insufficient evidence to support or refute the use of cholinesterase inhibitors for the treatment of delirium in non-ICU settings. No clear benefits or harms associated with cholinesterase inhibitors were observed when compared with placebo due to the lack of data. More trials are required.\nOutput:\n" }, { "from": "agent", "value": "We found one trial from the UK, which included 15 participants with delirium. The average age of the participants was 82.5 years; eight participants were male and seven were female. Seven participants also had a history of dementia. This trial compared rivastigmine (a type of cholinesterase inhibitor used in the treatment of dementia) with an inactive treatment (placebo). The trial did not show any difference in effect between those participants given rivastigmine and those given placebo. The study was conducted and reported appropriately, but the small number of participants limits any conclusions that could be made about rivastigmine as a treatment for delirium." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Four studies enrolling 318 infants were included. All studies enrolled preterm infants on the basis of gestational age criteria. All studies commenced treatment in the first 48 hours, but used different regimens, dose and durations of treatment. All four studies used thyroxine (T4). Valerio 2004 incorporated one arm with an early short course of T3, then T4 for 6 weeks. Only two studies with neurodevelopmental follow-up were of good methodology (van Wassenaer 1997; Vanhole 1997). All studies were small with the largest (van Wassenaer 1997) enrolling 200 infants. No significant difference was found in neonatal morbidity, mortality or neurodevelopmental outcome in infants who received thyroid hormones compared to control. van Wassenaer 1997 reported no significant difference in abnormal mental development at 6, 12, 24 months (RR 0.67, 95% CI 0.28, 1.56) or five years (RR 0.66, 95% CI 0.22, 1.99) or cerebral palsy assessed at five years (RR 0.72, 95% CI 0.28, 1.84). Meta-analysis of two studies (van Wassenaer 1997, Vanhole 1997) found no significant difference in the Bayley MDI (WMD -1.14, 95% CI -5.46, 3.19) and PDI (WMD 0.22, 95% CI -4.80, 5.24) at 7 - 12 months. van Wassenaer 1997 reported no significant difference in the Bayley MDI (MD -3.50, 95% CI -11.21, 4.21) and PDI (MD 3.10, 95% CI -3.31, 9.51) at 24 months, IQ scores at 5 years (MD -2.10, 95% CI -7.91, 3.71) and children in special schooling at 10 years (RR 0.88, 95% CI 0.43, 1.83). Meta-analysis of all four trials found no significant difference in mortality to discharge (typical RR 0.76, 95% CI 0.46 to 1.24). van Wassenaer 1997 reported no significant difference in death or cerebral palsy at five years (RR 0.70, 95% CI 0.43 to 1.14). No significant differences were reported for neonatal morbidities, including the need for mechanical ventilation, duration of mechanical ventilation, air leak, CLD in survivors at 28 days or 36 weeks, intraventricular haemorrhage, severe intraventricular haemorrhage, periventricular leucomalacia, patent ductus arteriosus, sepsis, necrotising enterocolitis or retinopathy of prematurity. This review does not support the use of prophylactic thyroid hormones in preterm infants to reduce neonatal mortality, neonatal morbidity or improve neurodevelopmental outcomes. An adequately powered clinical trial of thyroid hormone supplementation with the goal of preventing the postnatal nadir of thyroid hormone levels seen in very preterm infants is required.\nOutput:\n" }, { "from": "agent", "value": "A systematic review of the data from randomised controlled trials provides no evidence that routine thyroid hormone therapy is effective in preventing problems in preterm babies or improves their developmental outcomes. Thyroid hormones are needed for the normal growth and maturity of the central nervous system, as well as the heart and lungs. Children born without sufficient thyroid hormones can develop serious mental retardation. It is believed that low levels of thyroid hormones in the first few weeks after birth (transient hyperthyroxinaemia) in preterm babies born before 34 weeks may contribute to this abnormal development. The review of trials found no evidence that using thyroid hormones routinely in preterm babies is effective in reducing the risk of problems caused by transiently low levels of thyroid hormones." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included four studies (2350 women). The overall risk of bias for the included studies was assessed as acceptable in two studies and good in two studies. No statistically significant differences were observed between women who received group antenatal care and those given standard individual antenatal care for the primary outcome of preterm birth (risk ratio (RR) 0.75, 95% confidence interval (CI) 0.57 to 1.00; three trials; N = 1888). The proportion of low-birthweight (less than 2500 g) babies was similar between groups (RR 0.92, 95% CI 0.68 to 1.23; three trials; N = 1935). No group differences were noted for the primary outcomes small-for-gestational age (RR 0.92, 95% CI 0.68 to 1.24; two trials; N = 1473) and perinatal mortality (RR 0.63, 95% CI 0.32 to 1.25; three trials; N = 1943). Satisfaction was rated marginally higher among women who were allocated to group antenatal care, but this 5 point difference is not clinically meaningful on the scale used (mean difference 4.90, 95% CI 3.10 to 6.70; one study; N = 993). No differences in neonatal intensive care admission, initiation of breastfeeding or spontaneous vaginal birth were observed between groups. Several outcomes related to stress and depression were reported in one trial. No differences between groups were observed for any of these outcomes. No data were available on the effects of group antenatal care on care provider satisfaction. We used the GRADE (Grades of Recommendation, Assessment, Development and Evaluation) approach to assess evidence for seven prespecified outcomes; results ranged from low quality (perinatal mortality) to moderate quality (preterm birth, low birthweight, neonatal intensive care unit admission, breastfeeding initiation) to high quality (satisfaction with antenatal care, spontaneous vaginal birth). Available evidence suggests that group antenatal care is acceptable to women and is associated with no adverse outcomes for them or for their babies. No differences in the rate of preterm birth were reported when women received group antenatal care. This review is limited because of the small numbers of studies and women, and because one study contributed 42% of the women. Most of the analyses are based on a single study. Additional research is required to determine whether group antenatal care is associated with significant benefit in terms of preterm birth or birthweight.\nOutput:\n" }, { "from": "agent", "value": "We undertook a systematic review of trials that compared the effects of group pregnancy care versus conventional individual pregnancy care on psychosocial, physiological, labour and birth outcomes for women and their babies as well as on care provider satisfaction. Four randomised controlled trials (involving 2350 women) were included: two were undertaken in the USA, one in Sweden and one in Iran. We found no differences between women who received group pregnancy care and those given one-to-one care in terms of important pregnancy outcomes such as preterm birth, infant birthweight or death of the baby. Women who attended group pregnancy care were no more likely to initiate breastfeeding than those receiving standard care. In one trial, women who attended group pregnancy care rated their satisfaction as similar to women receiving individual care. Major differences between trials were noted. One trial targeted young women 14 to 25 years of age in a setting with many African American women who had limited financial resources. The main purpose was to reduce human immunodeficiency virus (HIV) risk behaviour and sexually transmitted infections. Another trial was mainly looking at family readiness in a military setting, and another focused on women's satisfaction and emotional aspects of their care. This review is limited owing to the small numbers of studies and women, with one study contributing 42% of the women. More research is required to determine whether group pregnancy care is associated with significant benefits." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Of 1041 publications obtained from the search strategy, we examined nine studies. Four studies were excluded, and five studies with 211 participants were eligible for inclusion. There was no difference in the immediate success rate of IAL when compared with IVAS in the closed manual reduction of acute anterior shoulder dislocation (RR 0.95; 95% CI 0.83 to 1.10). There were significantly fewer adverse effects associated with IAL compared with IVAS (RR 0.16; 95% CI 0.06 to 0.43). The mean time spent in the emergency department was significantly less with IAL compared with IVAS (MD 109.46 minutes; 95% CI 84.60 to 134.32). One trial reported significantly less time for reduction with IVAS (105 seconds; 95% CI 84.0 to 126.1) compared with IAL (284.6 seconds; 95% CI 185.3 to 383.9). One trial reported no joint infection associated with intra-articular lignocaine injection and no mortality associated with either IAL or IVAS. We observed no significant difference between IAL and IVAS with regard to the immediate success rate of reduction, pain during reduction, post-reduction pain relief and reduction failure. Compared to IVAS, IAL may be less expensive and may be associated with fewer adverse effects and a shorter recovery time.\nOutput:\n" }, { "from": "agent", "value": "The review authors searched the medical literature and identified five studies comparing these two methods. The studies included 211 patients with acute anterior shoulder dislocation; 113 patients underwent intra-articular lignocaine injection and 98 underwent intravenous analgesia with sedation. The review found that there may be no difference in the immediate success of manual reduction of the dislocated shoulder between patients receiving intra-articular lignocaine injection and those who received intravenous analgesia and sedation. However, intra-articular lignocaine injection may be associated with fewer side effects and a shorter stay in the emergency department before discharge from hospital. Compared with intravenous analgesia and sedation, intra-articular lignocaine may also be cheaper. However, the relatively small number of studies included in the review and the relatively small number of patients in each study means that the results of the review preclude definitive conclusions regarding the superiority of either method.." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Eleven studies met the criteria for inclusion in this review, all were randomised clinical trials, two were double-blind. There were a total number of 1969 participants. The sequence generation was inadequate in one study, adequate in five studies and unclear in the remaining studies. The allocation of concealment was adequate in three studies and unclear in the remaining studies. Methadone appeared statistically significantly more effective than non-pharmacological approaches in retaining patients in treatment and in the suppression of heroin use as measured by self report and urine/hair analysis (6 RCTs, RR = 0.66 95% CI 0.56-0.78), but not statistically different in criminal activity (3 RCTs, RR=0.39; 95%CI: 0.12-1.25) or mortality (4 RCTs, RR=0.48; 95%CI: 0.10-2.39). Methadone is an effective maintenance therapy intervention for the treatment of heroin dependence as it retains patients in treatment and decreases heroin use better than treatments that do not utilise opioid replacement therapy. It does not show a statistically significant superior effect on criminal activity or mortality.\nOutput:\n" }, { "from": "agent", "value": "However the review found that people have withdrawn from trials when they are assigned to a drug-free program. Consequently, there are no trials comparing methadone maintenance treatment with drug-free methods other than methadone placebo trials, or comparing methadone maintenance with methadone for detoxification only. These trials show that methadone can reduce the use of heroin in dependent people, and keep them in treatment programs." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Two studies (involving 286 women) from amniocentesis (but none from CVS) compared the impact of communicating results of rapid testing with waiting for definitive karyotype. Unfortunately, it was not possible to perform pooled analysis because one study reported only median (interquartile range) data, presumably because the data were not normally distributed. One study reported a statistically significant reduction in the average anxiety during the waiting period for women who had had a rapid test compared with those who had not (mean difference (MD) -2.30, 95% confidence intervals (CI) -3.08 to - 1.52). The other study compared median (interquartile range) for the trait- and state-anxiety scores and found no difference between the two groups. We found no conclusive evidence that, while waiting for the full karyotype following amniocentesis, issuing results from a rapid analysis reduces maternal anxiety. The limited evidence from the two trials included in this review does not help resolve the dilemma about whether full karyotyping should be abandoned in favour of limited rapid testing for women undergoing Down's syndrome screening. This choice will rest on clinical arguments and cost-effectiveness rather than impact on anxiety. There is also no evidence to support the view that issuing amniocentesis results as soon as they are available is more user friendly than using a pre-defined fixed date. Studies evaluating the effect of different strategies for disclosing results on women anxiety for CVS are needed.\nOutput:\n" }, { "from": "agent", "value": "One study reported a statistically significant reduction in the average anxiety during the waiting period for women who had had a rapid test, but the other found no difference between the two groups. There was also no evidence to support the view that issuing amniocentesis results as soon as they are available is more user friendly than informing women on a pre-defined fixed date. The results remain inconclusive and, therefore, for the time being the choice of communication strategies should be influenced by clinical arguments and cost-effectiveness rather than impact on anxiety. Studies evaluating the effect of different strategies for disclosing results on women anxiety for chorionic villous sampling are needed." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: In this review, we included 37 trials involving 15,813 children and adolescents. All trials tested supervised use of fluoride mouthrinse in schools, with two studies also including home use. Almost all children received a fluoride rinse formulated with sodium fluoride (NaF), mostly on either a daily or weekly/fortnightly basis and at two main strengths, 230 or 900 ppm F, respectively. Most studies (28) were at high risk of bias, and nine were at unclear risk of bias. From the 35 trials (15,305 participants) that contributed data on permanent tooth surface for meta-analysis, the D(M)FS pooled PF was 27% (95% confidence interval (CI), 23% to 30%; I2 = 42%) (moderate quality evidence). We found no significant association between estimates of D(M)FS prevented fractions and baseline caries severity, background exposure to fluorides, rinsing frequency or fluoride concentration in metaregression analyses. A funnel plot of the 35 studies in the D(M)FS PF meta-analysis indicated no relationship between prevented fraction and study precision (no evidence of reporting bias). The pooled estimate of D(M)FT PF was 23% (95% CI, 18% to 29%; I² = 54%), from the 13 trials that contributed data for the permanent teeth meta-analysis (moderate quality evidence). We found limited information concerning possible adverse effects or acceptability of the treatment regimen in the included trials. Three trials incompletely reported data on tooth staining, and one trial incompletely reported information on mucosal irritation/allergic reaction. None of the trials reported on acute adverse symptoms during treatment. This review found that supervised regular use of fluoride mouthrinse by children and adolescents is associated with a large reduction in caries increment in permanent teeth. We are moderately certain of the size of the effect. Most of the evidence evaluated use of fluoride mouthrinse supervised in a school setting, but the findings may be applicable to children in other settings with supervised or unsupervised rinsing, although the size of the caries-preventive effect is less clear. Any future research on fluoride mouthrinses should focus on head-to-head comparisons between different fluoride rinse features or fluoride rinses against other preventive strategies, and should evaluate adverse effects and acceptability.\nOutput:\n" }, { "from": "agent", "value": "We included 37 studies in which more than 15,000 children (aged six to 14 years) were treated with fluoride mouthrinse or placebo (a mouthrinse with no active ingredient) or received no treatment. All studies assessed supervised use of fluoride mouthrinse in school settings, with two studies also including home use. Most children received a sodium fluoride (NaF) solution, given at 230 parts per million of fluoride (ppm F) daily or a higher concentration of 900 ppm F weekly or fortnightly. Studies lasted from two to three years. Reports were published between 1965 and 2005, and studies took place in several countries. This review update confirmed that supervised regular use of fluoride mouthrinse can reduce tooth decay in children and adolescents. Combined results of 35 trials showed that, on average, there is a 27% reduction in decayed, missing and filled tooth surfaces in permanent teeth with fluoride mouthrinse compared with placebo or no mouthrinse. This benefit is likely to be present even if children use fluoride toothpaste or live in water-fluoridated areas. Combined results of 13 trials found an average 23% reduction in decayed, missing and filled teeth (rather than tooth surfaces) in permanent teeth with fluoride mouthrinse compared with placebo or no mouthrinse. No trials have looked at the effect of fluoride rinse on baby teeth. We found little information about unwanted side effects or about how well children were able to cope with the use of mouthrinses. Regular use of fluoride mouthrinse under supervision results in a large reduction in tooth decay in children's permanent teeth. We found little information about potential adverse effects and acceptability. Available evidence for permanent teeth is of moderate quality. This means we are moderately confident in the size of the effect. Very little evidence is available to assess adverse effects." } ]