Predictive Modeling for Brain Stroke Detection Using Machine Learning

Brain strokes often resulting in severe health complications and mortality are a significant global health concern. Early detection and brain stroke prediction involves assessing risk factors, medical history, diagnostic tests, and predictive models. Aims to identify individuals at risk before stroke occurrence, enabling timely interventions and lifestyle modifications to mitigate the risk. In this research, an in-depth exploration of predictive modeling for brain stroke detection utilizing machine learning algorithms specifically XG Boost, Decision Tree, and K-Nearest Neighbors (KNN) is presented. The proposed methodology encompasses data preprocessing, feature engineering, model selection, and accuracy evaluation. Through extensive experimentation, cross-validation, prediction of the performance of each algorithm focuses on metrics such as accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC-ROC).