DATA-DRIVEN NEUROLOGY: MACHINE LEARNING APPLICATIONS IN STROKE FORECASTING

Abstract

Brain stroke is a leading cause of mortality and long-term disability worldwide, making early prediction a crucial step in reducing the associated healthcare burden. With the growth of digital health records and advanced computational methods, machine learning (ML) has emerged as a promising approach to identifying high-risk patients before critical events occur. This study explores the potential of machine learning models for stroke prediction by analyzing patient datasets comprising demographic, clinical, and lifestyle factors. Various supervised learning algorithms were implemented, including Logistic Regression, Random Forest, Support Vector Machines (SVM), and Gradient Boosting, with performance evaluated through accuracy, precision, recall, and F1-score. The results highlight the superiority of ensemble-based methods in balancing sensitivity and specificity, suggesting that machine learning can serve as an effective decision-support tool for clinicians. This work underscores the importance of integrating predictive analytics into neurology to move toward proactive and preventive healthcare.