Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{183239,
        author = {S MITHILESH REDDY},
        title = {BRAIN STROKE PREDICTION USING GRADIENT BOOSTING WITH XAI},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {3},
        pages = {999-1009},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=183239},
        abstract = {Stroke is the largest cause of death and disability globally, making it a serious health concern. A disturbance in blood flow to the brain results in oxygen deprivation, damage to brain cells, and significant issues with speech, movement, and everyday tasks. Early detection plays a critical role in enabling timely medical intervention and improving patient outcomes. Conventional stroke prediction systems frequently use Explainable AI in conjunction with Machine Learning models to improve interpretability. However, many of these systems depend on conventional algorithms that may not fully exploit the capabilities of more advanced techniques. They also frequently face challenges related to class imbalance and may struggle to model the complex interdependencies among risk factors. This research presents an enhanced stroke prediction framework that integrates advanced gradient boosting methods with XAI to improve both accuracy and interpretability. A hybrid resampling method that blends Borderline, Tomek Links, and SMOTE. While optimized models involving CatBoost(Category Boosting), XGBoost (Extreme Gradient Boosting),  LightGBM(Light Gradient Boosting Machine), and Gradient Boosting Machine (GBM) are utilized to ensure robust performance, SMOTE is used to correct data imbalance. This comprehensive approach supports more accurate stroke risk assessment and contributes to early diagnosis and informed clinical decision-making.},
        keywords = {Brain Stroke Prediction, Class Imbalance, Explainable AI (XAI), Gradient Boosting, Machine Learning.},
        month = {August},
        }