• Chippala Naveen
• Sarang Khajuria
• Harsh Kumar

The majority of strokes happen as a result of an unanticipated blockage in the heart and brain's pathways. Stroke can be minimized by being aware of the various warning symptoms of the disease in advance. Using various machine learning techniques in conjunction with the presence of hypertension, body mass index, heart disease, average glucose level, smoking status, history of stroke, and age, this research work suggests an early prediction of stroke disorders. Six distinct classifiers—Logistics Regression, Decision Tree Classifier, KNeighbors Classifier, Naïve Bayes classifier, Support Vector Machine and Random Forest . The majority of research has been done on heart stroke prediction, but relatively little has been done on brain stroke risk. In light of this, numerous machine learning models are developed to forecast the likelihood of a brain stroke. This study uses machine learning methods such as Naïve Bayes, Support Vector Machine, K-Nearest Neighbors, Decision Tree Classification, Random Forest Classification, and Logistic Regression to analyze a variety of physiological parameters.

Machine learning Approaches, Hypertension, Decision tree Classifier, Kneighbors Classifier, Support Vector Machine.

"Well watch: Nurturing health with explainable stroke insights.", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.k131-k143, April-2024, Available :http://www.jetir.org/papers/JETIR2404A20.pdf

"Well watch: Nurturing health with explainable stroke insights.", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppk131-k143, April-2024, Available at : http://www.jetir.org/papers/JETIR2404A20.pdf