Robustly Extracting Medical Knowledge from EHRs: A Case Study of Learning a Health Knowledge Graph

Abstract

Increasingly large electronic health records (EHRs) provide an opportunity to algorithmically learn medical knowledge. In one prominent example, a causal health knowledge graph could learn relationships between diseases and symptoms and then serve as a diagnostic tool to be refined with additional clinical input. Prior research has demonstrated the ability to construct such a graph from over 270,000 emergency department patient visits. In this work, we describe methods to evaluate a health knowledge graph for robustness. Moving beyond precision and recall, we analyze for which diseases and for which patients the graph is most accurate. We identify sample size and unmeasured confounders as major sources of error in the health knowledge graph. We introduce a method to leverage non-linear functions in building the causal graph to better understand existing model assumptions. Finally, to assess model generalizability, we extend to a larger set of complete patient visits within a hospital system. We conclude with a discussion on how to robustly extract medical knowledge from EHRs.

Publication
Proceedings of the Pacific Symposium on Biocomputing (PSB)
Irene Chen
Irene Chen
PhD Student

Irene works on machine learning methods to improve understanding of human health and reduce inequality.

Monica Agrawal
Monica Agrawal
PhD Student

Monica’s research interests include reasoning over longitudinal clinical notes, building more intelligent electronic health records, studying user-ML interactions in clinical settings, and developing algorithms that can incorporate domain knowledge.

David Sontag
David Sontag
Associate Professor of EECS

My research focuses on advancing machine learning and artificial intelligence, and using these to transform health care.

Related