Classification and Diagnosis of Cardiac Arrhythmia using an ECG-based Ensemble Approach

Abstract

Cardiovascular Disease (CVD) remains the leading cause of death, worldwide and in the United States. Approximately 30% of global deaths can be attributed to one form of CVD, including conditions such as heart disease, stroke, heart attack, and arrhythmia. In diagnosing CVD, electrocardiograms (ECG) are commonly used to measure and record the electrical activity of the heart. Their non-invasive, informative, and relatively simple nature allows for rapid deployment. However, because analysis of ECGs depends solely on a physician, ECG analysis becomes subjective, adding a potential layer of error to patient healthcare. Studies indicate that physicians often misread ECGs and disagree with each other’s interpretations. In order to develop an accurate and objective method for ECG analysis, this study evaluates various ensemble algorithms to design and create a supervised classification model. Several ensemble models were evaluated to derive one which correctly classifies CVD with sufficiently high accuracy. A boosted decision tree ensemble created to evaluate cardiac condition performs best, with an overall accuracy of 84.6% and an AUC of 0.828.