Detection of CAD using optimization approach with machine learning classification techniques

CAD Detection using AI

Abstract

One of most serious ailments among cardiovascular disorders is Coronary Artery Disease (CAD). One of the key concerns is the high expense of CAD detection conventional tools like angiography. In terms of high accuracy and cost-effective solutions, supervised learning models for the automatic classification of the CAD are an economical way. Using machine learning techniques to build a model for CAD detection provides the optimal approach so far. In health-care organizations, a large volume of data is generated. It assists researchers in making the most of large amounts of data in order to quickly and accurately diagnose the problem. The research's key objective is to use feature extraction and optimization approaches to create a machine learning model. The performance is assessed in this study employing four strong machine learning classification algorithms and two feature extraction algorithms, namely Independent Component Analysis (ICA) and Principal Component Analysis (PCA), as well as a hybridization of Particle Swarm Optimization (PSO) and Firefly Algorithm (FA) for feature optimization.