An Explainable Machine Learning approach for Heart Disease Prediction using Data Analytics and Streamlit Dashboard

– Heart disease is a cause of death in many parts of the world and therefore early disease diagnosis and risk evaluation is the key factor in efficient prevention and treatment of the disease. Conventional diagnostic tools usually involve some clinical knowledge and might not be readily available to the masses. This paper introduces a Heart Disease Prediction System, which uses machine learning methods to deliver precise as well as real-time risk evaluation on the basis of health parameters inputted by users. The system is deployed as a web application that is interactive and is based on Streamlit, allowing users to enter medical and lifestyle information and make immediate predictions in a user-friendly format. Several classification models such as the Logistic Regression, the Decision Tree and the XGBoost are used and the model that performs best is chosen by considering the evaluation measures like accuracy and precision. To increase transparency and user trust, the system incorporates Explainable Artificial Intelligence (XAI) with SHAP that offers information on the contribution of features to the prediction. The system also creates individual health recommendations and facilitates the automatic creation of PDF-based reports to document and analyze. The experimental findings prove that the suggested system can reach high levels of prediction accuracy, and it is also interpretable and usable. Combining machine learning, explainable AI, and web technologies, the system can be used as an effective tool in early detection and preventive healthcare support.