Assigning Medical Codes at the Encounter Level by Paying Attention to Documents
Published in Machine Learning for Health Workshop (ML4H) at NeurIPS, 2019
Abstract
The vast majority of research in computer assisted medical coding focuses on coding at the document level, but a substantial proportion of medical coding in the real world involves coding at the level of clinical encounters, each of which is typically represented by a potentially large set of documents. We introduce encounter-level document attention networks, which use hierarchical attention to explicitly take the hierarchical structure of encounter documentation into account. Experimental evaluation demonstrates improvements in coding accuracy as well as facilitation of human reviewers in their ability to identify which documents within an encounter play a role in determining the encounter level codes.
Recommended citation:
@inproceedings{shing2019assigning,
title={Assigning Medical Codes at the Encounter Level by Paying Attention to Documents},
author={Shing, Han-Chin and Wang, Guoli and Resnik, Philip},
booktitle={ML4H, Machine Learning for Health Workshop at NeurIPS},
url = {https://arxiv.org/abs/1911.06848},
year={2019}
}