Published Paper Details:

Heart disease remains one of the leading causes of mortality worldwide, posing a significant challenge to healthcare systems due to its complex etiology and the need for early and accurate diagnosis. With the rapid growth of medical data and advances in computational intelligence, machine learning and deep learning models have been widely adopted for heart disease classification. However, most high-performance models operate as black boxes, providing predictions without offering insights into how decisions are made. This lack of transparency limits clinical trust, interpretability, and ethical adoption in real-world healthcare environments. Explainable Artificial Intelligence (XAI) addresses this critical gap by enabling models to provide human-understandable explanations alongside predictions. This research proposes an XAI-driven methodology for heart disease classification that balances predictive accuracy with interpretability. The methodology integrates structured clinical data such as age, cholesterol levels, blood pressure, electrocardiogram results, and lifestyle indicators with interpretable machine learning techniques. By embedding explanation mechanisms such as feature attribution, rule-based reasoning, and local explanation models, the system allows clinicians to understand why a patient is classified as high-risk or low-risk. The proposed approach aims to improve diagnostic confidence, support clinical decision-making, and enhance patient trust by offering transparent and accountable AI outcomes. Ultimately, this study contributes to the development of ethical, reliable, and clinically applicable AI systems in cardiovascular healthcare.