ABSTRACT
Coronary artery disease (CAD) is the leading cause of death in the world, accounting for more than half of all deaths. It's a difficult condition to diagnose because of the variety of risk factors and symptoms. CAD arises when the inner layer of the coronary arteries becomes clogged with cholesterol plaque, preventing oxygen-rich blood from reaching the heart. Computer-aided design has undergone major changes in the recent decade. Prototyping and testing of various machine learning (ML) models will be done in this study in order to find the best model for the given problem at hand. Seven of the most often used ML models discussed here include support vector machine, K-nearest neighbors, decision tree, random forest, logistic regression, naive Bayes, and XG-Boost. The Z-Alizadeh Sani dataset is used in this study to detect CAD. The statistical performance is analyzed on the basis of sensitivity, accuracy, specificity, and ROC curves. Among these models, random forest has achieved the best performance and obtained accuracy of 93.44%, sensitivity of 76.47%, and specificity of 100%.
