• SHAIKH FURKHAN AHMED
• Suvarna D. Pingle

Stroke remains a major global cause of mortality and long-term disability, creating a strong need for early and accurate risk prediction. The reviewed study presents an explainable machine learning framework for stroke prediction that incorporates data preprocessing, class-imbalance handling, feature selection, and comparative evaluation of multiple algorithms. A key strength of the model is the integration of XAI techniques such as SHAP and LIME, which offer transparent and clinically interpretable insights into feature contributions. The study also includes an end-to-end deployment pipeline through both web and Android applications, enabling real-time risk assessment for users. This review outlines the study’s methodology, tools, challenges, and outcomes while identifying opportunities for future enhancement through multimodal datasets, improved balance strategies, and advanced interpretability methods.

Stroke Prediction, Machine Learning, Prediction Models, Healthcare Analytics, Medical Data Mining

"PREDICTIVE ANALYTICS IN HEALTHCARE USING MACHINE LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 11, page no.h1-h4, November-2025, Available :http://www.jetir.org/papers/JETIR2511711.pdf

"PREDICTIVE ANALYTICS IN HEALTHCARE USING MACHINE LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 11, page no. pph1-h4, November-2025, Available at : http://www.jetir.org/papers/JETIR2511711.pdf