The Early Prediction Acute Myocardial Infarction in Real-Time Data Using an Ensemble Machine Learning Model

Cardiovascular disease is one of the extremely dangerous diseases in the world. Thus, the early detection of acute myocardial infarction is a critical model for patients and doctors. If the cardiovascular disease can make early detection, patients can prevent acute myocardial infarction. In this paper, we propose a machine learning ensemble approach for early detection of cardiac events on electronic health records (EHRs). The proposed ensemble approach combines a set of different classifier algorithms that are Random Forest, Decision Tree, Artificial Neural Network, K-Nearest Neighbors, and Support Vector Machine. Data from the Korea Acute Myocardial Infarction Registry (KAMIR), real life an acute myocardial database.