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

© 2019 The Authors. Increasingly large electronic health records (EHRs) provide an opportunity to algorithmi-cally 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 refi...

Full description

Bibliographic Details
Main Authors: Chen, Irene Y, Agrawal, Monica, Horng, Steven, Sontag, David
Other Authors: Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Format: Article
Language:English
Published: World Scientific Pub Co Pte Lt 2021
Online Access:https://hdl.handle.net/1721.1/137717
_version_ 1826203198627512320
author Chen, Irene Y
Agrawal, Monica
Horng, Steven
Sontag, David
author2 Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
author_facet Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Chen, Irene Y
Agrawal, Monica
Horng, Steven
Sontag, David
author_sort Chen, Irene Y
collection MIT
description © 2019 The Authors. Increasingly large electronic health records (EHRs) provide an opportunity to algorithmi-cally 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 knowl-edge from EHRs. Supplementary material: http://clinicalml.org/papers/ChenEtAl PSB20 suppl.pdf.
first_indexed 2024-09-23T12:32:52Z
format Article
id mit-1721.1/137717
institution Massachusetts Institute of Technology
language English
last_indexed 2024-09-23T12:32:52Z
publishDate 2021
publisher World Scientific Pub Co Pte Lt
record_format dspace
spelling mit-1721.1/1377172023-04-10T13:29:08Z Robustly Extracting Medical Knowledge from EHRs: A Case Study of Learning a Health Knowledge Graph Chen, Irene Y Agrawal, Monica Horng, Steven Sontag, David Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science © 2019 The Authors. Increasingly large electronic health records (EHRs) provide an opportunity to algorithmi-cally 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 knowl-edge from EHRs. Supplementary material: http://clinicalml.org/papers/ChenEtAl PSB20 suppl.pdf. 2021-11-08T17:13:57Z 2021-11-08T17:13:57Z 2020-01 2021-01-26T18:44:37Z Article http://purl.org/eprint/type/ConferencePaper https://hdl.handle.net/1721.1/137717 Chen, Irene Y, Agrawal, Monica, Horng, Steven and Sontag, David. 2020. "Robustly Extracting Medical Knowledge from EHRs: A Case Study of Learning a Health Knowledge Graph." Pacific Symposium on Biocomputing, 25 (2020). en 10.1142/9789811215636_0003 Pacific Symposium on Biocomputing Creative Commons Attribution NonCommercial License 4.0 https://creativecommons.org/licenses/by-nc/4.0/ application/pdf World Scientific Pub Co Pte Lt World Scientific
spellingShingle Chen, Irene Y
Agrawal, Monica
Horng, Steven
Sontag, David
Robustly Extracting Medical Knowledge from EHRs: A Case Study of Learning a Health Knowledge Graph
title Robustly Extracting Medical Knowledge from EHRs: A Case Study of Learning a Health Knowledge Graph
title_full Robustly Extracting Medical Knowledge from EHRs: A Case Study of Learning a Health Knowledge Graph
title_fullStr Robustly Extracting Medical Knowledge from EHRs: A Case Study of Learning a Health Knowledge Graph
title_full_unstemmed Robustly Extracting Medical Knowledge from EHRs: A Case Study of Learning a Health Knowledge Graph
title_short Robustly Extracting Medical Knowledge from EHRs: A Case Study of Learning a Health Knowledge Graph
title_sort robustly extracting medical knowledge from ehrs a case study of learning a health knowledge graph
url https://hdl.handle.net/1721.1/137717
work_keys_str_mv AT chenireney robustlyextractingmedicalknowledgefromehrsacasestudyoflearningahealthknowledgegraph
AT agrawalmonica robustlyextractingmedicalknowledgefromehrsacasestudyoflearningahealthknowledgegraph
AT horngsteven robustlyextractingmedicalknowledgefromehrsacasestudyoflearningahealthknowledgegraph
AT sontagdavid robustlyextractingmedicalknowledgefromehrsacasestudyoflearningahealthknowledgegraph