Heart Disease Prediction Using Ensemble Techniques and Explainable AI Validation

Cardiovascular diseases (CVD) pose a global threat, with mortality projected to reach 23.3 million by 2030. This paper presents a comprehensive approach to designing a system aimed at leveraging machine learning and Explainable AI (XAI) techniques for the development of a reliable and interpretable predictive model for coronary artery disease (CAD). The primary objective encompasses both the construction of predictive models and the utilization of SHAP (SHapley Additive exPlanations) Analysis to enhance model interpretability. Through meticulous system design, we evaluate various machine learning algorithms to identify the most effective model for CAD prediction. Following model selection, SHAP Analysis is employed to elucidate the impact of different features on model predictions, thereby facilitating a deeper understanding of the underlying mechanisms driving CAD classification. This study underscores the importance of not only predictive accuracy but also interpretability in medical decision-making processes.