Machine Learning-Based Web Platform for Early Stroke Risk Prediction
Keywords:
Machine Learning, Brain Stroke Prediction, Web-Based Interface, Healthcare System, Risk Assessment, Random Forest, Medical Data Analysis, Early DetectionAbstract
This research proposes the development of a web-based application that employs machine learning to determine the likelihood of a person experiencing a brain stroke. The system collects critical medical data, including age, blood pressure, glucose levels, cardiac history, BMI, smoking status, and lifestyle factors, to determine the likelihood of a stroke. Various machine learning methods, such as Logistic Regression, Decision Tree, Support Vector Machine, and Random Forest, can be employed to analyze medical data and generate more precise predictions. The web application is user-friendly and enables users to promptly obtain their stroke risk assessment results by inputting their health information. The proposed method could be implemented by both individuals and physicians to identify high-risk diseases in their early stages, prior to their development into severe conditions. This is in favor of preventative healthcare and early detection. Experiments have demonstrated that the system consistently generates predictions that are more precise and efficient, rendering it suitable for real-time healthcare surveillance and decision-support applications.
