Open AccessAn explainable artificial intelligence approach for predicting cardiovascular outcomes using electronic health records
Author(s) -
Sergiusz Wesołowski,
Gordon Lemmon,
Edgar Javier Hernández,
A. Michael Henrie,
Thomas A. Miller,
Derek Weyhrauch,
Michael D. Puchalski,
Bruce E. Bray,
Rashmee U. Shah,
Vikrant Deshmukh,
Rebecca K. Delaney,
H. Joseph Yost,
Karen Eilbeck,
Martin Tristani-Firouzi,
Mark Yandell
Publication year - 2022
Publication title -
plos digital health
Language(s) - English
Resource type - Journals
ISSN - 2767-3170
DOI - 10.1371/journal.pdig.0000004
Subject(s) - comorbidity , health records , diagnosis code , scalability , data science , medical diagnosis , computer science , electronic health record , medicine , artificial intelligence , psychiatry , health care , database , pathology , population , environmental health , economics , economic growth
Understanding the conditionally-dependent clinical variables that drive cardiovascular health outcomes is a major challenge for precision medicine. Here, we deploy a recently developed massively scalable comorbidity discovery method called Poisson Binomial based Comorbidity discovery (PBC), to analyze Electronic Health Records (EHRs) from the University of Utah and Primary Children’s Hospital (over 1.6 million patients and 77 million visits) for comorbid diagnoses, procedures, and medications. Using explainable Artificial Intelligence (AI) methodologies, we then tease apart the intertwined, conditionally-dependent impacts of comorbid conditions and demography upon cardiovascular health, focusing on the key areas of heart transplant, sinoatrial node dysfunction and various forms of congenital heart disease. The resulting multimorbidity networks make possible wide-ranging explorations of the comorbid and demographic landscapes surrounding these cardiovascular outcomes, and can be distributed as web-based tools for further community-based outcomes research. The ability to transform enormous collections of EHRs into compact, portable tools devoid of Protected Health Information solves many of the legal, technological, and data-scientific challenges associated with large-scale EHR analyses.