The explosive increase of medical data on a worldwide basis is unsustainable since it can only be handled by BigData analytics. BigData Analytics can deal with rapidly exploding medical data by focusing on fundamental characteristics such as volume, velocity, variety, veracity, and value. Ischemic Stroke is a medical condition in which when the blood arteries supplying blood to the brain is clogged, causing brain damage. According to the World Health Organization (WHO), stroke is the leading cause of death and disability globally. Early recognition of the multiple strokes warning indicators can reduce the severity of the stroke.The primary goal of this research is to use Ensemble Boosting Algorithms to efficiently predict the likelihood of a brain stroke happening at an early stage.In order to evaluate the algorithm's effectiveness, an effective dataset for stroke prediction was obtained from the Kaggle website. Several Ensemble Boosting Algorithms including AdaBoost, Gradient Boosting Machine, Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine and CatBoost were successfully used in this study. Among the above algorithms Extreme Gradient Boosting (XGBoost) give a high accuracy rate of 98.2% and provides a fast-training speed, LightGBM second the XGBoost with an accuracy rate of 95.7% but fastest of all the algorithms. This work has the potential to substantially boost the medical system's ability to prevent and alleviate the damage caused by ischemic strokes.

Ensemble Boosting Algorithms, XGBoost, AdaBoost, Gradient Boost Machine, Light GBM, CatBoost