Machine Learning Models for Cardiovascular Disease Events Prediction

Tsarapatsani K, Sakellarios AI, Pezoulas VC, Tsakanikas VD, Kleber ME, Marz W, Michalis LK, Fotiadis DI

Six machine learning models — Logistic Regression, Support Vector Machine, Random Forest, Naive Bayes, XGBoost, and AdaBoost — were trained on clinical and biochemical data from 2,943 LURIC participants to predict 10-year cardiovascular mortality (484 CVD deaths). Logistic Regression achieved the highest accuracy at 72.20%. These models are intended to support risk scoring and mortality estimation in the TIMELY study.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference, Juli 2022 | PMID 36085658