Improving classification of myocardial infarction with machine learning in a diverse population

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.