AI-CADS: An Artificial Intelligence based framework for automatic early detection and severity evaluation of coronary artery disease

Abstract

Coronary artery disease (CAD) is one of the leading causes of sudden cardiac arrest and accounts for a substantial proportion of global mortality. An early and accurate diagnosis is essential and can save lives. This study presents a methodological framework for the automated detection and severity evaluation of CAD, utilizing novel biomarkers. A comprehensive evaluation of the biomarker feature space was performed, resulting in the selection of an optimal feature set for further analysis. Subsequently, twelve machine learning classifiers were applied to this refined input, which included clinical, chemical, and molecular cardiac biomarkers obtained from the specially curated NUMS-NIHD dataset. Experimental validation was performed using K-fold cross-validation and leave-p-out cross-validation (LpOCV) to identify the most effective biomarker–classifier combinations for CAD detection and severity evaluation. The proposed combinations were then integrated into a framework aligned with clinical protocols. Benchmarking against state-of-the-art methodologies demonstrated the framework’s efficacy, achieving a detection accuracy of 97.18%, sensitivity of 96.67%, and specificity of 100.00%. For severity evaluation, the framework achieved an accuracy of 90.91%. These results indicate that the proposed framework is both effective and clinically viable.