Leveraging Selected Lifestyle Factors from NHANES Data for Chronic Heart Disease Risk Prediction

Chronic Heart Disease (CHD) remains a major global health concern, necessitating early detection strategies for effective intervention. This study employs machine learning (ML) techniques to predict CHD risk using selected lifestyle factors from NHANES data. A comprehensive feature selection process was conducted to enhance predictive accuracy and interpretability. Among various ML models evaluated, XGBoost demonstrated the best performance, achieving an accuracy of 85.94 %, an F1-score of 85.89, and an AUC-ROC of 0.92, underscoring the relevance of lifestyle factors in CHD assessment. These findings highlight the potential of ML-driven methodologies for improving early diagnosis and preventive healthcare strategies.