A Machine Learning-Driven Framework for Stroke Risk Prediction Using Clinical Data and Web-Based Decision Support

Stroke is one of the top causes of mortality and disability on a worldwide scale in the modern era. It is possible that early prediction has the ability to significantly improve patient outcomes by allowing fast action to be taken during the identification process. The purpose of this article is to explain how the risk of having a stroke may be predicted by using a machine learning technique that takes into consideration demographic, clinical, and lifestyle factors. Five distinct algorithms, including Decision Tree, Logistic Regression, Random Forest, and Support Vector Machine (SVM), were trained on the dataset, which comprised of 5,110 patient records. The dataset was used to train the algorithms. The most accurate approach was Support Vector Machine (SVM), which had a score of 93.9%, while Logistic Regression came in second with a score of 93.8 %. The deployment of the model and the facilitation of real-time risk assessment were both accomplished via the use of a web application that in turn was constructed using Flask. The purpose of this study is to illustrate how machine learning has the potential to enhance preventive procedures in the healthcare industry. the strategies.