Incident and recurrent myocardial infarction (MI) in relation to comorbidities: Prediction of outcomes using...

To date, incident and recurrent MI remains a major health issue worldwide, and efforts to improve risk prediction in population health studies are needed. This may help the scalability of prevention strategies and management in terms of healthcare cost savings and improved quality of care.

We studied a large-scale population of 4.3 million US patients from different socio-economic and geographical areas from three health plans (Commercial, Medicare, Medicaid). Individuals had medical/pharmacy benefits for at least 30 months (2 years for comorbid history and followed up for 6 months or more for clinical outcomes). Machine-learning (ML) algorithms included supervised (logistic regression, neural network) and unsupervised (decision tree, gradient boosting) methodologies. Model discriminant validity, calibration and clinical utility were performed separately on allocated test sample (1/3 of original data).

In the absence of MI in comorbid history, the overall incidence rates were 0.442 cases/100 person-years and in the presence of MI history, 0.652. ML algorithms showed that supervised formulations had incrementally higher discriminant validity than unsupervised techniques (e.g., for incident MI outcome in the absence of MI in comorbid history: logistic regression "LR" - c index 0.921, 95%CI 0.920-0.922; neural network "NN" - c index 0.914, 95%CI 0.913-0.915; gradient boosting "GB" - c index 0.902, 95%CI 0.900-0.904; decision tree "DT" - c index 0.500, 95%CI 0.495-0.505). Calibration and clinical utility showed good to excellent results.

ML algorithms can substantially improve the prediction of incident and recurrent MI particularly in terms of the non-linear formulation. This approach may help with improved risk prediction, allowing implementation of cardiovascular prevention strategies across diversified sub-populations with different clusters of complexity.