Explainable Heart Disease Risk Prediction using Cat Boost, SHAP, and Stream lit

Heart disease has been identified as one of the major contributors to mortality around the world, and hence the need for the early detection of the risks associated with heart disease cannot be overstated. This research aims at developing an explainable machine learning system for the early detection of the risks associated with heart disease using patient data. The system will utilize the CatBoost algorithm as the main classifier for the system because of its ability to handle structured data sets that contain both categorical and numerical features. To make the system explainable, the system will utilize the SHapley Additive exPlanations (SHAP) technique for the interpretation of the results produced by the classifier in relation to the various features provided in the system. Additionally, the system will utilize the Streamlit tool for the development of an interactive web application that can be utilized for the generation of real-time results for the user.