Coronary artery disease remains a leading cause of morbidity and mortality worldwide. With the rapid advancement of machine learning and artificial intelligence techniques, there has been an increasing interest in using these methods for CAD risk prediction. This study aims to provide a comprehensive comparative analysis of various ML and AI models for predicting CAD risk, considering both their performance and interpretability. A diverse dataset containing clinical, demographic, and diagnostic features was used to train and evaluate the models. The models' performance was assessed using standard evaluation metrics, including accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve. Additionally, model interpretability was evaluated using techniques such as feature importance analysis and SHAP (SHapley Additive exPlanations). Our findings indicate that while some complex models achieve higher predictive performance, simpler models also demonstrate competitive accuracy while maintaining higher interpretability. The trade-off between performance and interpretability is crucial, as interpretable models can offer valuable insights into the factors driving CAD risk. The study underscores the need to strike a balance between model complexity and clinical interpretability in CAD risk prediction applications.
HTML PDFShare this article
Journal of Coronary Heart Diseases received 15 citations as per Google Scholar report
