Intelligent Method for Detection of Coronary Artery Disease with Ensemble Approach

Abstract

Coronary artery is a major reason of health ailments all over the world. Its detection and management incurred huge amount of deaths across the nation. Heart disease can be diagnosed using various invasive and non-invasive methods. One of the effective methods for detection of coronary artery disease is coronary angiography, which is expensive and also has side effects. This further requires high level of technical expertise. Due to improvement in technology and low-cost storage devices, storage of huge amount of data becomes easy. Even health sector has been untouched. Machine learning methods are being used to analyze the collected data due to its capability to predict the diseases. In this work, machine learning methods are implemented in order to achieve low-cost, reproducible, non-invasive, rapid, and precise identification of heart disease. This paper adopted ensemble method with multiple classifiers to construct and validate the model. For experiment purpose, Z-Alizadesh Sani coronary artery disease dataset is used. The ensemble method of prediction outperforms the other disease prediction methods.