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{192230,
        author = {MULINTI GOLLA USHA RANI and UPPARA SHARANYA and MALLAM PALLI KONGATHI PAVITHRA and K RAMALAKSHMI and Mr T. Somasekhar M.tech Assistant professor and Dr. C.V. Madhusudan Reddy},
        title = {Brain Stroke Prediction Using Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {9},
        pages = {710-714},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=192230},
        abstract = {Stroke is a big deal when it comes to our health. This is one of the reasons why people die or become disabled for a long time. We need to determine who is at risk of having a stroke as early as possible. Thus, we can take steps to prevent it. Individuals will have a better chance of survival. This study is about a system that uses machine learning to predict whether a person will have a brain stroke. It examines the history of patients to determine whether they might have a stroke. This system is called a brain stroke prediction system. It uses machine learning algorithms to make predictions about stroke. The proposed system can assist doctors. It looks at things like where people are from and how old they are. It also examines how their bodies work and the kind of life they lead. All of these factors are related to the risk of stroke. The system helps doctors by looking at these things like factors, physiological factors and lifestyle factors that are related to the pos-sibility of a person having a stroke.
We used several different machine learning algorithms, such as Logistic Regression, Support Vector Machine, Decision Tree, Random Forest and Gradient Boosting. We compared these machine learning algorithms to determine which one works best.
Before training these machine learning algorithms, we performed a lot of work to prepare the data. We have to deal with missing data, ensure that the numbers are all on the scale, and fix problems where one group of data is much larger than the others.
The results of our tests show that Random Forest and Gradient Boosting, which are based models, work bet-ter than the other machine learning algorithms. Ran-dom Forest and Gradient Boosting are more accurate and work well even when the data are not perfect. The system can help doctors make decisions. It can help doctors determine whether a patient is at risk of hav-ing a stroke before it actually occurs. This system can be trusted by doctors to obtain information about stroke risks.},
        keywords = {Brain Stroke Prediction, Machine Learning, Healthcare Analytics, Medical Data Mining, Super-vised Learning},
        month = {February},
        }