panych 4c302b9498 | 9 months ago | |
---|---|---|
bert_model | 2 years ago | |
data | 2 years ago | |
src | 2 years ago | |
.gitignore | 2 years ago | |
README.md | 9 months ago | |
predict.sh | 2 years ago | |
train.sh | 2 years ago |
This repository contains codes and models for the paper:
Pan Y, Wang C, Hu B, Xiang Y, Wang X, Chen Q, Chen J, Du J
A BERT-Based Generation Model to Transform Medical Texts to SQL Queries for Electronic Medical Records: Model Development and Validation
JMIR Med Inform 2021;9(12):e32698
URL: https://medinform.jmir.org/2021/12/e32698
DOI: 10.2196/32698
pytorch >= 1.4.0
transformers == 3.0.2
nltk, numpy, tqdm, matplotlib, idna, tushare, sqlalchemy, pandas,
boto3, requests, regex, more_itertools, interval, translate, num2words
We provide the processed dataset in ./data, including train, validation and test sets.
The original dataset can be found from TREQS.
python -u ./src/train.py \
--dataset $DATA_DIR \
--train_data $TRAIN_DATA_PATH \
--epoch $EPOCH_NUM \
--save $SAVED_MODEL_DIR \
--cuda \
--cuda_device_num $DEVICE_NUM\
python -u ./src/predict.py \
--dataset $DATA_DIR \
--eval_data $PREDICT_DATA_PATH \
--model_dir $SAVED_MODEL_DIR \
--model $SAVED_MODEL_NAME \
--output_dir $OUTPUT_DIR \
--cuda \
--cuda_device_num $DEVICE_NUM \
The details of evaluation can be found in TREQS_evaluation, which is based on the publicly available real-world de-identified Medical Information Mart for Intensive Care III (MIMIC III) dataset.
No Description
Python Text other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》