AI-Driven Explainable Stroke Risk Evaluation with Intelligent Decision Support for Early Prevention

Abstract

Stroke is one of the leading causes of death and long-term disability worldwide, making early risk identification essential for timely medical intervention and improved patient outcomes. This study presents an AIDriven Explainable Stroke Risk Evaluation with Intelligent Decision Support for Early Prevention, which combines machine learning with explainable artificial intelligence to support reliable clinical decision-making. The proposed system uses patient health information, including demographic details and medical risk factors, to predict the likelihood of stroke. Before model development, the dataset undergoes preprocessing steps such as data cleaning, feature selection, class balancing using SMOTE, and normalization to improve data quality and model performance. Multiple machine learning algorithms are trained and evaluated using standard performance metrics to identify the most effective prediction model. Explainable AI techniques are incorporated to highlight the factors influencing each prediction, enabling healthcare professionals to understand and trust the model's decisions. A user-friendly web application is also developed to provide real-time stroke risk assessment and decision support. The proposed framework offers an accurate, interpretable, and practical solution for early stroke prevention, assisting clinicians in identifying high-risk individuals and supporting timely healthcare interventions.