Machine learning modelling and explainability of coronary heart disease based on Mediterranean diet.

This article focuses on using machine learning (ML) models to predict coronary heart disease (CHD) by integrating adherence to the Mediterranean diet (MD) with clinical characteristics. Employing seven ML algorithms on a nutrition and cardiovascular disease dataset, the study found that the Random Forest (RF) model achieved the highest predictive performance, with accuracy, precision, recall, and F1-score values of 0.90, 0.95, 0.95, and 0.90, respectively. Explainable AI techniques, including Shapley additive explanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME), identified glucose levels, high-density lipoprotein cholesterol (HDL-C), bread, and chocolate consumption as significant factors influencing CHD risk. The findings support the cardioprotective role of the MD and suggest that incorporating dietary patterns into ML models enhances CHD risk prediction and may inform personalized prevention strategies.