Clinical diagnosis guidelines aim at specifying the steps that may lead to a diagnosis. Inspired by guidelines, we aim to learn the optimal sequence of actions to perform in order to obtain a correct diagnosis from electronic health records. We apply various deep reinforcement learning algorithms to this task and experiment on a synthetic but realistic dataset to differentially diagnose anemia and its subtypes and particularly evaluate the robustness of various approaches to noise and missing data. Experimental results show that the deep reinforcement learning algorithms show competitive performance compared to the state-of-the-art methods with the added advantage that they enable the progressive generation of a pathway to the suggested diagnosis, which can both guide and explain the decision process.
@article{arxiv.2305.06295,
title = {Extracting Diagnosis Pathways from Electronic Health Records Using Deep Reinforcement Learning},
author = {Lillian Muyama and Antoine Neuraz and Adrien Coulet},
journal= {arXiv preprint arXiv:2305.06295},
year = {2023}
}
Comments
Extended Abstract presented at Machine Learning for Health (ML4H) symposium 2023, December 10th, 2023, New Orleans, United States, 17 pages