Machine Learning -Based Stroke Prediction

This study emphasizes the importance of early stroke detection and prevention, highlighting challenges like missing and unbalanced data. It evaluates various machine learning models, including Random Forest and Logistic Regression, using k-fold cross-validation on balanced and imbalanced datasets. Key predictors identified are age, BMI, average blood sugar, and marital status. The Random Forest model achieved the highest accuracy (95.5%), demonstrating the potential of machine learning to enhance stroke prediction and improve patient outcomes.