sarahmiller137 commited on
Commit
d23478f
1 Parent(s): 5364c7e

update readme

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -11,13 +11,13 @@ datasets:
11
  ---
12
 
13
  ## Model information:
14
- scibert-scivocab-uncased model finetuned using radiology reports from the MIMIC-III database. The finetuning task performed was to establised if various BERT models could classify MIMIC-III radiology report texts based upon two classes. Labels of [0,1] were assigned to radiology reports linked to an ICD9 diagnosis codes for lung cancer = 1 and a random sample of reports which were not linked to any type of cancer diagnosis code at all = 0.
15
 
16
  ## Intended uses:
17
- This model is intended to be used for to classify texts to identify the presence of lung cancer. The model will predict lables of [0,1] based upon the ICD9 codes for lung cancer found in the MIMIC-III database, please see the dataset information for details.
18
 
19
  ## Limitations:
20
- Note that the dataset and model may not be fully represetative or suitable for all needs it is recommended that the paper for the dataset and the base model card should be reviewed before using the model -
21
  - [MIMIC-III](https://www.nature.com/articles/sdata201635.pdf)
22
  - [scibert_scivocab_uncased](https://huggingface.co/allenai/scibert_scivocab_uncased)
23
 
 
11
  ---
12
 
13
  ## Model information:
14
+ This model is the [scibert_scivocab_uncased](https://huggingface.co/allenai/scibert_scivocab_uncased) model that has been finetuned using radiology report texts from the MIMIC-III database. The task performed was text classification in order to benchmark this model with a selection of other variants of BERT for the classifcation of MIMIC-III radiology report texts into two classes. Labels of [0,1] were assigned to radiology reports in MIMIC-III that were linked to an ICD9 diagnosis code for lung cancer = 1 and a random sample of reports which were not linked to any type of cancer diagnosis code at all = 0.
15
 
16
  ## Intended uses:
17
+ This model is intended to be used to classify texts to identify the presence of lung cancer. The model will predict lables of [0,1].
18
 
19
  ## Limitations:
20
+ Note that the dataset and model may not be fully represetative or suitable for all needs it is recommended that the paper for the dataset and the base model card should be reviewed before use -
21
  - [MIMIC-III](https://www.nature.com/articles/sdata201635.pdf)
22
  - [scibert_scivocab_uncased](https://huggingface.co/allenai/scibert_scivocab_uncased)
23