sschet commited on
Commit
a032630
1 Parent(s): 3ceda30

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +63 -0
README.md CHANGED
@@ -1,3 +1,66 @@
1
  ---
2
  license: apache-2.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
+ language:
4
+ - en
5
+ tags:
6
+ - Token Classification
7
+ co2_eq_emissions: 0.0279399890043426
8
+ widget:
9
+ - text: >-
10
+ CASE: A 28-year-old previously healthy man presented with a 6-week history
11
+ of palpitations. The symptoms occurred during rest, 2–3 times per week,
12
+ lasted up to 30 minutes at a time and were associated with dyspnea. Except
13
+ for a grade 2/6 holosystolic tricuspid regurgitation murmur (best heard at
14
+ the left sternal border with inspiratory accentuation), physical examination
15
+ yielded unremarkable findings.
16
+ example_title: example 1
17
+ - text: >-
18
+ A 63-year-old woman with no known cardiac history presented with a sudden
19
+ onset of dyspnea requiring intubation and ventilatory support out of
20
+ hospital. She denied preceding symptoms of chest discomfort, palpitations,
21
+ syncope or infection. The patient was afebrile and normotensive, with a
22
+ sinus tachycardia of 140 beats/min.
23
+ example_title: example 2
24
+ - text: >-
25
+ A 48 year-old female presented with vaginal bleeding and abnormal Pap
26
+ smears. Upon diagnosis of invasive non-keratinizing SCC of the cervix, she
27
+ underwent a radical hysterectomy with salpingo-oophorectomy which
28
+ demonstrated positive spread to the pelvic lymph nodes and the parametrium.
29
+ Pathological examination revealed that the tumour also extensively involved
30
+ the lower uterine segment.
31
+ example_title: example 3
32
+ datasets:
33
+ - tner/bc5cdr
34
+ - jnlpba
35
+ - bc2gm_corpus
36
+ - drAbreu/bc4chemd_ner
37
+ - linnaeus
38
+ - ncbi_disease
39
  ---
40
+
41
+ ## About the Model
42
+ An English Named Entity Recognition model, trained on Maccrobat to recognize the bio-medical entities (107 entities) from a given text corpus (case reports etc.). This model was built on top of distilbert-base-uncased
43
+
44
+ - Dataset: Maccrobat https://figshare.com/articles/dataset/MACCROBAT2018/9764942
45
+ - Carbon emission: 0.0279399890043426 Kg
46
+ - Training time: 30.16527 minutes
47
+ - GPU used : 1 x GeForce RTX 3060 Laptop GPU
48
+
49
+ Checkout the tutorial video for explanation of this model and corresponding python library: https://youtu.be/xpiDPdBpS18
50
+
51
+ ## Usage
52
+ The easiest way is to load the inference api from huggingface and second method is through the pipeline object offered by transformers library.
53
+ ```python
54
+ from transformers import pipeline
55
+ from transformers import AutoTokenizer, AutoModelForTokenClassification
56
+
57
+ tokenizer = AutoTokenizer.from_pretrained("d4data/biomedical-ner-all")
58
+ model = AutoModelForTokenClassification.from_pretrained("d4data/biomedical-ner-all")
59
+
60
+ pipe = pipeline("ner", model=model, tokenizer=tokenizer, aggregation_strategy="simple") # pass device=0 if using gpu
61
+ pipe("""The patient reported no recurrence of palpitations at follow-up 6 months after the ablation.""")
62
+ ```
63
+
64
+ ## Author
65
+ This model is part of the Research topic "AI in Biomedical field" conducted by Deepak John Reji, Shaina Raza. If you use this work (code, model or dataset), please star at:
66
+ > https://github.com/dreji18/Bio-Epidemiology-NER