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{186225,
        author = {MONIKA ROKADE and Khatal S.S and Gholap. P.S and Vaishnavi Mane and Aarti Jadhav and Sanika Naykodi},
        title = {Automated Stroke Prediction Using Machine Learning: Exploratory Study With a Web Application for Early Intervention.},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {874-879},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=186225},
        abstract = {Stroke is a serious medical condition that happens when the blood supply to the brain is blocked or stopped. This causes damage to the brain and leads to problems with how the body and mind work. Stroke is a major health issue around the world and has serious effects on both people's health and the economy. To tackle this, scientists are creating computer programs that can predict stroke before it happens. These programs help doctors take action early, which can save lives. As people get older, more people are at risk of having a stroke, so having good prediction tools is more important than ever.
In this study, the performance of a new machine learning method was tested against six other common types of classifiers. The goal was to see how well the method could predict stroke and how well it worked in different situations. To understand how these complex computer models make decisions, the study also looked at two methods for explaining model behaviour: SMOTE. These are well-known and trusted ways to make sense of how machine learning models work, especially in healthcare performed better than simpler ones The best model achieved almost 91% accuracy, while the other models had accuracy between 83% and 91%. The new system, which includes both overall and detailed explanations, helps make complex models easier to understand and use. This can improve how stroke is diagnosed and treated.},
        keywords = {Stroke prediction, machine learning Algorithms, SMOTE, HTML, FLASK.},
        month = {November},
        }