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{181604,
        author = {Pooja Laxman Dudhe and Shubhangi P Tidake and Prashant B Kulkarni},
        title = {An Advanced Hybrid Machine Learning Framework  for Stroke Risk Prediction},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {1},
        pages = {5093-5098},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=181604},
        abstract = {Stroke remains a major threat to global health, causing significant loss of life and often leading to lasting neurological challenges. To improve early stroke prediction, this study introduces a new hybrid machine learning model. This model combines the strengths of three powerful algorithms: Random Forest, XGBoost, and Artificial Neural Networks.
We trained and tested our approach using a substantial dataset of 5,110 patient records, each containing 12 important clinical features. Before building the models, we carefully prepared the data. This included effectively managing missing information and addressing the common challenge of having far fewer stroke cases than non-stroke cases using SMOTE (Synthetic Minority Over- sampling Technique), a data balancing method.
The results demonstrate that our combined model significantly outperforms any of the individual algorithms used alone. It achieved a high classification accuracy of 95.63},
        keywords = {Cerebrovascular Accident, Ensemble Learning, Predictive Analytics, Clinical Decision Support, Machine Learning},
        month = {June},
        }