AI-Based Stroke Prediction Using Machine Learning: A Comparative Model Evaluation with SHAP Explainability

Author(s)	Ms. Chitra Devi Thangavelu, Mr. Gnanaguru PP, Mr. Arunkumar VL, Mr. Abhilash Joshua M
Country	India
Abstract	Stroke is a major global health concern and a leading cause of mortality and long-term disability. Early detection through predictive modeling can significantly improve clinical outcomes and reduce the burden on healthcare systems. This study presents a comprehensive machine learning approach to stroke prediction using clinical data. Three classifiers Random Forest, XGBoost, and Logistic Regression were implemented and evaluated based on accuracy, AUC, and confusion matrices. SHAP (Shapley Additive explanations) was employed to interpret the model decisions. Among the models, XGBoost demonstrated the highest AUC. SHAP analysis revealed that age, average glucose level, and BMI were key contributing features. This research underlines the potential of explainable AI in enhancing medical decision-making.
Keywords	Stroke, Machine Learning, SHAP, XGBoost, Random Forest, Logistic Regression, Predictive Modeling, Explainable AI
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 7, Issue 4, July-August 2025
Published On	2025-07-22
DOI	https://doi.org/10.36948/ijfmr.2025.v07i04.51727
Short DOI	https://doi.org/g9t2dj

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research