AI-Based Stroke Prediction Using Machine Learning: A Comparative Model Evaluation with SHAP Explainability Article Swipe
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.36948/ijfmr.2025.v07i04.51727
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.
Related Topics To Compare & Contrast
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.36948/ijfmr.2025.v07i04.51727
- https://www.ijfmr.com/papers/2025/4/51727.pdf
- OA Status
- hybrid
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4412596512