AI-Powered Heart Disease Prediction with Appropriate Feature Selection

Abstract: Heart disease remains one of the major causes of death worldwide, making early prediction and prevention extremely important. This study presents an ai-powered heart disease prediction system that uses machine learning techniques to estimate a patient's risk of developing heart disease based on clinical parameters such as age, blood pressure, cholesterol level, heart rate, and other medical factors. multiple machine learning models were trained and evaluated using the cleveland heart disease dataset, and the best performing model was integrated into a flask based web application for real time prediction. To improve transparency and user trust, shap (shapley additive explanations) is used to explain how different features influence the prediction results, The proposed system demonstrates how explainable artificial intelligence can assist healthcare professionals and patients in understanding prediction outcomes, promoting preventive healthcare, and supporting informed clinical decision making.

Keyword—Heart Disease Prediction, Machine Learning, Explainable Artificial Intelligence, SHAP, Risk Assessment, Flask Web Application.