Coronary Heart Disease Prediction Using Machine Learning Algorithms

—Cardiopathy is one of the most serious diseases worldwide with its high morbidity and mortality rates posing a latent risk over time. The objective of this research focuses on evaluating Machine Learning (ML) models such as Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Logistic Regression (LR) for the prediction of coronary heart disease (CHD), with the aim of identifying the most efficient model for this prediction. The model construction followed the Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology, which comprises five stages: business understanding, data understanding, data preparation, modeling, and evaluation. The modeling results revealed the superior predictive capability of the XGBoost algorithm for detecting coronary heart disease, compared to Random Forest and Logistic Regression. The assessment of performance metrics (Accuracy, Precision, Sensitivity, and F1 Score) established XGBoost as the reference model, highlighting an F1 Score of approximately 90.8%. This superiority is attributed to its robustness in capturing nonlinear interactions among clinical variables. Consequently, the XGBoost model is selected as the optimal tool for integration into future medical decision support systems. In summary, this ML-based approach provides a highly predictive tool capable of identifying subtle risk patterns from real clinical data. The XGBoost model is a promising candidate for integration into decision support systems and for the optimization of primary prevention protocols for coronary heart disease.