A Survey on Machine Learning Algorithm for Coronory Artery Disease

Coronary Artery Disease (CAD) is the most common form of cardiovascular disease (CVD) and often results in heart attacks. It is responsible for tens of thousands of fatalities and billions of dollars in annual economic damages. Patients with CAD are diagnosed with invasive and possibly dangerous conventional angiography. Machine learning (ML) techniques are often suggested as fast, inexpensive, and non-invasive means of identifying CAD models. Several datasets, sample sizes, data collection techniques, performance assessments, and machine learning algorithms are used in the published works on ML-based CAD diagnostics. Because of these differences, it is hard to generalize about literary accomplishments. In this article, every significant study on ML-based CAD diagnosis published in the last several years is examined. A comprehensive analysis of the effects of numerous factors, including dataset features (such as geographic location and sample size) and machine learning techniques (such as feature set selection, performance measures, and process) are conducted. Finally, the fundamental difficulties and limits of ML-based CAD diagnosis are investigated in depth.