The text of clinical notes can be a valuable source of patient information and clinical assessments. Historically, the primary approach for exploiting clinical notes has been information extraction: linking spans of text to concepts in a detailed domain ontology. However, recent work has demonstrated the potential of supervised machine learning to extract document-level codes directly from the raw text of clinical notes. We propose to bridge the gap between the two approaches with two novel syntheses: (1) treating extracted concepts as features, which are used to supplement or replace the text of the note; (2) treating extracted concepts as labels, which are used to learn a better representation of the text. Unfortunately, the resulting concepts do not yield performance gains on the document-level clinical coding task. We explore possible explanations and future research directions.
@article{arxiv.1906.03380,
title = {Clinical Concept Extraction for Document-Level Coding},
author = {Sarah Wiegreffe and Edward Choi and Sherry Yan and Jimeng Sun and Jacob Eisenstein},
journal= {arXiv preprint arXiv:1906.03380},
year = {2019}
}