bvanaken commited on
Commit
35ebba1
1 Parent(s): be7d9aa

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -2
README.md CHANGED
@@ -14,7 +14,7 @@ thumbnail: "https://core.app.datexis.com/static/paper.png"
14
  The CORe (_Clinical Outcome Representations_) model is introduced in the paper [Clinical Outcome Predictions from Admission Notes using Self-Supervised Knowledge Integration](https://www.aclweb.org/anthology/2021.eacl-main.75.pdf).
15
  It is based on BioBERT and further pre-trained on clinical notes, disease descriptions and medical articles with a specialised _Clinical Outcome Pre-Training_ objective.
16
 
17
- #### How to use
18
 
19
  You can load the model via the transformers library:
20
  ```
@@ -23,8 +23,16 @@ tokenizer = AutoTokenizer.from_pretrained("bvanaken/CORe-clinical-outcome-biober
23
  model = AutoModel.from_pretrained("bvanaken/CORe-clinical-outcome-biobert-v1")
24
  ```
25
 
 
26
 
27
- ### BibTeX entry and citation info
 
 
 
 
 
 
 
28
 
29
  ```bibtex
30
  @inproceedings{vanaken21,
 
14
  The CORe (_Clinical Outcome Representations_) model is introduced in the paper [Clinical Outcome Predictions from Admission Notes using Self-Supervised Knowledge Integration](https://www.aclweb.org/anthology/2021.eacl-main.75.pdf).
15
  It is based on BioBERT and further pre-trained on clinical notes, disease descriptions and medical articles with a specialised _Clinical Outcome Pre-Training_ objective.
16
 
17
+ #### How to use CORe
18
 
19
  You can load the model via the transformers library:
20
  ```
 
23
  model = AutoModel.from_pretrained("bvanaken/CORe-clinical-outcome-biobert-v1")
24
  ```
25
 
26
+ ### Pre-Training Data
27
 
28
+ The model is based on [BioBERT](https://huggingface.co/dmis-lab/biobert-v1.1) pre-trained on PubMed data.
29
+ The _Clinical Outcome Pre-Training_ included discharge summaries from the MIMIC III training set (specified [here](https://github.com/bvanaken/clinical-outcome-prediction/blob/master/tasks/mimic_train.csv)), medical transcriptions from [MTSamples](https://mtsamples.com/) and clinical notes from the i2b2 challenges 2006-2012. It further includes ~10k case reports from PubMed Central (PMC), disease articles from Wikipedia and article sections from the [MedQuAd](https://github.com/abachaa/MedQuAD) dataset extracted from NIH websites.
30
+
31
+ ### More Information
32
+
33
+ For all the details about CORe and contact info, please visit [CORe.app.datexis.com](http://core.app.datexis.com/).
34
+
35
+ ### Cite
36
 
37
  ```bibtex
38
  @inproceedings{vanaken21,