Official code for "Deep Stable Representation Learning on Electronic Health Records" published and orally presented in IEEE International Conference on Data Mining (ICDM 2022). [paper] [arXiv]
Check the presentation material.
MIMIC III: https://physionet.org/content/mimiciii/1.4/
MIMIC IV: https://physionet.org/content/mimiciv/0.4/
Diagnoses and Procedures.
Run preprocessing.py for the main experiment and preprocess_insurance.py for the "OOD" experiment. Run under the Stable folder for CHE+BaseModels and Normal folder for BaseModels.
Some baselines are implemented following the PyHealth library.
If your paper benefits from this repo, please consider citing with:
Y. Luo, Z. Liu and Q. Liu, "Deep Stable Representation Learning on Electronic Health Records," 2022 IEEE International Conference on Data Mining (ICDM), Orlando, FL, USA, 2022, pp. 1077-1082, doi: 10.1109/ICDM54844.2022.00134.
@INPROCEEDINGS{10027709,
author={Luo, Yingtao and Liu, Zhaocheng and Liu, Qiang},
booktitle={2022 IEEE International Conference on Data Mining (ICDM)},
title={Deep Stable Representation Learning on Electronic Health Records},
year={2022},
pages={1077-1082},
doi={10.1109/ICDM54844.2022.00134}}