Prediction of Coronary Artery Disease using Artificial Intelligence – A Systematic Literature Review

Abstract

Purpose: Coronary heart disease and the risk of having a heart attack have both risen in recent years. Angioplasty, lifestyle changes, stent implantation, and medications are only some of the methods used to diagnose and treat various diseases. In this study, we will gather and analyze a variety of health indicators in order to identify heart-related illnesses via Machine Learning and Deep Learning prediction models. The best way to improve treatment and mortality prevention is to identify the relevant critical parameters and use Machine Learning or Deep Learning algorithms to achieve optimum accuracy. Design/Methodology/Approach: Secondary sources were used for this investigation. These included periodicals, papers presented at conferences, online sources, and scholarly books and articles. In order to analyze and present the data gathered from academic journals, websites, and other sources, the SWOT analysis is being used. Findings/Results: Predicting heart problems and their severity with a handful of crucial characteristics can save lives. Machine Learning algorithms such as Linear Regression, Deep Learning algorithms such as Neural Networks, and many others can all be applied to those medical parameters for this goal. Originality/Value: This literature study utilizes secondary data collected from diverse sources. Understanding the many types of coronary artery disease and evaluating the most recent advances in predicting the same using Machine Learning approaches will be facilitated by the learned knowledge. This knowledge will aid in the development of a new model or the enhancement of an existing model for predicting coronary artery disease in an individual. Included are tables detailing the forms of coronary artery disease, a variety of recently published research publications on the topic, and standard datasets. Paper Type: Literature Review