Heart Stroke Prediction Using Machine Learning and Explainable AI Insights

Heart stroke is a critical worldwide medical problem that requires early and accurate prediction in order to provide proper treatment. Recent advancements in machine learning, utilizing models such as XGBoost, Decision Tree, KNN, SVC, and Random Forest, have demonstrated promise in predicting patients at risks from medical data like Age, BMI, Glucose Levels, Hypertension, Heart disease etc., The aim is to evaluate the effectiveness of these machine learning models in predicting people at risk. Metrics like recall, precision, accuracy, and F1-score are examined to assess how well these models perform in predicting the risk of heart strokes. In addition, the research will look at the primary features of medical data that influence model predictions, using Explainable AI techniques such as SHAP. The overall objective is to provide effective and exact approaches for early detection of heart stroke risks, allowing patients to receive timely and important medical care when it is most needed.