Explainable Artificial Intelligence for Early Heart Disease Prediction Using Ensemble Machine Learning Models

Heart disease remains one of the leading causes of mortality worldwide, creating an urgent need for accurate and interpretable predictive systems that can support early diagnosis and clinical decision-making. Recent advances in machine learning have demonstrated significant potential for identifying cardiovascular risk patterns from patient health records; however, many high-performing models operate as black boxes, limiting their acceptance in healthcare environments where transparency and trust are essential. This study proposes an explainable artificial intelligence (XAI) framework for early heart disease prediction using ensemble machine learning models. The framework integrates multiple predictive algorithms through ensemble learning techniques to improve classification performance while maintaining model interpretability. Patient demographic information, clinical measurements, and lifestyle-related factors are utilized to develop a robust predictive system capable of distinguishing individuals at risk of heart disease from healthy subjects. To enhance transparency, explainability methods are incorporated to identify the most influential features contributing to predictions and to provide both global and local interpretations of model behavior. Experimental evaluation demonstrates that the ensemble approach achieves superior predictive performance compared with individual machine learning models, while the explainability component offers clinically meaningful insights into risk factors associated with cardiovascular conditions. The proposed framework supports reliable, transparent, and data-driven healthcare decision-making, facilitating earlier intervention and improved patient outcomes. The findings highlight the potential of combining ensemble learning and explainable artificial intelligence to advance trustworthy predictive analytics in cardiovascular medicine.