Stroke Detection Using Machine Learning: Gradient Boosting Optimized with Whale Optimization Algorithm

A stroke, often known as a brain attack, results from a cut off blood supply to the brain or from anything blocking the blood vessels. In any of these conditions, damage to or death in the brain occurs. Every ability in our body - including memory, breathing, hormone production and release, and everything - is under the control of our brain. Lack of oxygen causes cells in the brain to die in a second should the blood supply to the brain get blocked. This causes strokes at last. Stroke is one of the most frequent reasons for death globally. According to the World Health Organization (WHO), stroke is responsible for 11% of worldwide mortality. Therefore, based on medical data inputs, including health risks that may contribute to strokes, such as smoking, cardiovascular disease, obesity, high blood cholesterol, insulin levels, and elevated blood pressure, we propose a machine learning (ML) model with supervised learning methodologies that can predict whether or not a person is likely to have a stroke. This study compares many ML approaches, including the Random Forest (RF), Logistic Regression (LR), Decision Tree (DT), as well as Gradient Boosting (GB). The model we developed results show that the suggested approach significantly increases system efficiency (97.62%) and accuracy.