Stroke Prediction Using XGB Classifier, Logistic Regression, GaussianNB and BernaulliNB Classifier

Stroke is one of major reason for human mortality as well as morbidity worldwide, making early prediction and intervention significant for effective treatment. In latest years, machine learning algorithms have emerged as important tools for stroke prediction. This abstract presents an investigation on Predicting stroke using machine learning algorithms. The study aims to evolve a model that can accurately identify human at risk of stroke based upon their demographic, clinical, and lifestyle factors. The dataset which is used for this study consists of a large cohort of patients, including both stroke and non-stroke cases, with detailed information on various risk factors. ML algorithms, including logistic regression, XGBoost, BernoulliNB, and GaussianNB, are trained and evaluated on the dataset. Feature selection techniques are employed to identify the most significant risk factors contributing to stroke prediction. The investigation's findings show how effective different machine learning algorithms are at forecasting strokes. . The XGBoost models achieve high accuracy, sensitivity, and specificity in identifying individuals at risk of stroke as compared to LR Classifier, GaussianNB and BernoulliNB Classifier Model.