Heart Stroke Prediction Using Machine Learning

Stroke remains one of the leading causes of mortality and long-term disability worldwide, posing a significant burden on healthcare systems and society. Early identification of individuals at high risk of stroke is crucial for implementing preventive strategies and reducing fatal outcomes. This research proposes an intelligent stroke prediction system based on advanced machine learning techniques that analyse clinical and demographic data to assess stroke risk with high accuracy. The proposed framework utilizes a structured healthcare dataset comprising key attributes such as age, hypertension, heart disease status, body mass index (BMI), average glucose level, smoking habits, and lifestyle factors. A comprehensive data preprocessing pipeline is implemented, including missing value imputation, categorical encoding, feature scaling, and class imbalance handling using resampling techniques. Multiple supervised learning algorithms, including Logistic Regression, Decision Tree, and Random Forest, are employed and comparatively evaluated to identify the most effective predictive model. Experimental results demonstrate that ensemble-based models, particularly Random Forest, outperform other classifiers in terms of accuracy, precision, recall, and F1-score, achieving robust and reliable predictions. The model also incorporates feature importance analysis to interpret the contribution of critical risk factors, thereby enhancing transparency and clinical relevance. The proposed system offers a scalable, cost-effective, and efficient solution for early stroke risk detection and can be integrated into modern healthcare infrastructures, including electronic health record systems and mobile health applications. Furthermore, this study highlights the potential of machine learning-driven predictive analytics in transforming preventive healthcare by enabling data-driven decision-making and personalized risk assessment.