Prediction of Coronary Artery Disease using an Ensemble Model

Abstract

The field of medical analysis follows an exponential curve in the area of scientific knowledge, yet things are not very optimistic and assured from the perspective of patients as many diseases are discovered quite late by doctors. The lack of comprehensive data on relevant risk factors for coronary artery disease (CAD) has limited the ability to predict the risk of developing CAD in large populations. The challenge lies in the data complexity and correlations in terms of prediction using conventional techniques. Coronary artery disease is predicted by uploading the electrocardiogram (ECG) reports of patients into the machine learning model. Multiple classifiers like k-nearest neighbors, Logistic Regression, Support Vector Machine, and Voting Based Ensemble Classifier are implemented, and based on the acceptable criteria on the accuracy, the model will be finalized. This model will help medical professionals in diagnosis of cardiac diseases, to detect whether a patient has/had Myocardial Infarction, Abnormal Heartbeat, or the patient is hale and healthy by inferring the ECG reports.