Article’s

Brain stroke is one of the leading causes of death and long-term disability worldwide, making early detection and timely intervention essential for improving patient outcomes. This project presents a machine learning-based Brain Stroke Prediction system that estimates an individual’s risk of stroke using health and lifestyle parameters such as age, gender, hypertension, heart disease, average glucose level, body mass index (BMI), smoking status, work type, residence type, and marital status. The proposed system is developed using Python, Flask, and Scikit-learn, with a Random Forest Classifier trained on a publicly available healthcare dataset to provide accurate and reliable predictions. The application features a simple and interactive web interface that allows users to enter their health information and instantly receive a prediction indicating their stroke risk. To protect user privacy, the system operates without a database, ensuring that no personal information or prediction results are stored. Data preprocessing techniques, including handling missing values, encoding categorical features, and feature transformation, are applied to improve the performance of the prediction model. The trained model is integrated into a Flask-based web application to enable fast and efficient real-time predictions. The proposed system aims to assist healthcare professionals, students, and individuals by providing an accessible tool for preliminary stroke risk assessment. Although it is not intended to replace professional medical diagnosis, it can serve as a valuable decision-support system that promotes early awareness and preventive healthcare. The project demonstrates the practical application of machine learning in healthcare by combining predictive analytics with an easy-to-use web interface, offering a cost-effective, secure, and efficient solution for stroke risk prediction suitable for academic, research, and educational purposes.