Improving classification of myocardial infarction with machine learning in a diverse population
American Journal of Epidemiology · 2026
DOI: 10.1093/aje/kwaf223 ↗Kurz gefasst
Fachartikel in der Zeitschrift American Journal of Epidemiology, 2026. Verfasst von Alicia W Chen und 27 weiteren Autor:innen. Beteiligte Einrichtung: Massachusetts Veterans Epidemiology Research and Information Center (MAVERIC), VA Boston Healthcare System, Boston, MA, United States. Hauptthemen laut MEDLINE: Myocardial Infarction, Machine Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: CSRD VA, NIAMS NIH HHS, HSRD VA.
Abstract (Originalsprache)
Phenotype classification with electronic health record (EHR) data is increasingly performed with machine learning (ML); however, their performance in diverse population remains understudied. We compared an international classification of diseases (ICD)–based algorithm with an ML phenotyping pipeline to classify myocardial infarction (MI) in a general and self-reported Black population. We determined the impact of differential performance by replicating a published MI risk factor study with MI defined by the ICD or ML algorithms. Individuals followed in the Veterans Health Administration (VHA) EHR with data from 2002 to 2019 were examined: 11 523 175 Veterans; mean age, 67.5 years; 93.8% male; 14.3% Black; 79.1% White. MI was classified using a published rule-based ICD algorithm and an ML pipeline, PheCAP, which incorporates natural language processing. Algorithms were trained and validated against n = 403 Veterans randomly selected and chart reviewed for MI (gold standard), oversampled for self-reported Black. Among chart-reviewed Veterans, the ICD algorithm had high positive predicted value (PPV) and low sensitivity (all race, PPV: 0.97, sensitivity: 0.17; Black Veterans, PPV: 0.94, sensitivity: 0.24). PheCAP MI had good PPV and higher sensitivity (all race, PPV: 0.90, sensitivity: 0.66; Black, PPV: 0.81, sensitivity: 0.79). Applying PheCAP MI to the entire VHA population to classify MI provided increased power to replicate findings from the published MI risk factor study compared to the ICD algorithm.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Massachusetts Veterans Epidemiology Research and Information Center (MAVERIC), VA Boston Healthcare System, Boston, MA, United States.
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, United States.
- Centralized Interactive Phenomics Resource (CIPHER), Office of Research and Development, Veterans Health Administration, Washington, DC, United States.
- Department of Biostatistics, Harvard School of Public Health, Boston, MA, United States.
- Department of Medicine, VA Atlanta Healthcare System, Decatur, GA, United States.
- New England Geriatric Research Education and Clinical Center (GRECC), VA Boston Healthcare System, Boston, MA, United States.
ORCID-Profile: Jacqueline P Honerlaw, Kelly Cho, Katherine P Liao
Förderung
- CSRD VA
- NIAMS NIH HHS
- HSRD VA
- US Department of Veterans Affairs
- NHLBI NIH HHS
- VA CSR&D CDA-2
Zitieren
APA
Chen, A. W., Hong, C., Ho, Y. L., Link, N., Honerlaw, J. P., Tanukonda, V., Orkaby, A. R., Qazi, S., Melley, C., Galloway, A., Costa, L., Maripuri, M., Wang, X., Zhang, Y., Schubert, P., Cai, T., He, Z., Panickan, V. A., Rosser, M., …, & Liao, K. P. (2026). Improving classification of myocardial infarction with machine learning in a diverse population. American Journal of Epidemiology. https://doi.org/10.1093/aje/kwaf223
Vancouver
Chen AW, Hong C, Ho YL, Link N, Honerlaw JP, Tanukonda V, et al. Improving classification of myocardial infarction with machine learning in a diverse population. American Journal of Epidemiology. 2026. doi:10.1093/aje/kwaf223
BibTeX
@article{Chen2026,
author = {Chen, Alicia W and Hong, Chuan and Ho, Yuk Lam and Link, Nicholas and Honerlaw, Jacqueline P and Tanukonda, Vidisha and Orkaby, Ariela R and Qazi, Saadia and Melley, Connor and Galloway, Ashley and Costa, Lauren and Maripuri, Monika and Wang, Xuan and Zhang, Yichi and Schubert, Petra and Cai, Tianrun and He, Zeling and Panickan, Vidul A and Rosser, Morgan and Tarko, Laura and Dowell, Sharon and Feldman, Candace and Kerr, Gail and Gaziano, J Michael and Wilson, Peter W F and Cho, Kelly and Cai, Tianxi and Liao, Katherine P},
title = {Improving classification of myocardial infarction with machine learning in a diverse population},
journal = {American Journal of Epidemiology},
year = {2026},
doi = {10.1093/aje/kwaf223}
}
EUVIMED