Heart Disease Risk Assessment with Explainable AI

Heart disease remains a leading cause of morbidity and mortality worldwide, often coexisting with conditions such as diabetes mellitus, hypertension, and atherosclerosis. Recent studies emphasize the importance of early diagnosis and transparent risk prediction to improve clinical outcomes. However, many existing predictive models lack interpretability, limiting their acceptance in clinical practice. This paper presents the development of a web-based Heart Disease Prediction system integrated with Explainable Artificial Intelligence (XAI) techniques. The system employs multiple machine learning algorithms, including Random Forest, Gradient Boosting, Support Vector Machine, and Logistic Regression, trained on preprocessed medical datasets. To enhance trust and usability, XAI methods are incorporated to provide users with clear explanations for each prediction, identifying key contributing factors such as age, cholesterol, and blood pressure. A user-friendly web interface facilitates input and displays both predictions and interpretative insights, aiming to make advanced predictive tools accessible to a broader audience, including elderly users and those with limited medical knowledge. The system’s performance is evaluated using standard metrics, demonstrating reliable accuracy and transparency. This project bridges the gap between accurate machine learning models and user understanding, ultimately contributing to more informed healthcare decision-making.