The healthcare sector has traditionally been an early adopter of technological progress, gaining significant advantages, particularly in machine learning applications such as disease prediction. One of the most important diseases is stroke. Early detection of a brain stroke is exceptionally critical to saving human lives. A brain stroke is a condition that happens when the blood flow to the brain is disturbed or reduced, leading brain cells to die and resulting in impairment or death. Furthermore, the World Health Organization (WHO) classifies brain stroke as the world's second-deadliest disease. Brain stroke is still an essential factor in the healthcare sector. Controlling the risk of a brain stroke is important for the survival of patients. In this context, machine learning is used in various health-related fields, especially "brain stroke." To that end, an automated model for recognizing and providing helpful information for brain stroke prediction was created. It can predict brain strokes with high accuracy in the early stages. The proposed model aims to examine the patient for effective decision-making. This research study employed a freely accessible dataset and a mix of machine learning methods such as random forest, logistic regression, and decision trees. Furthermore, the Synthetic Minority Over Sampling Technique (SMOTE) was implemented to handle unbalanced data. The result shows a high accuracy of 99% in predicting a brain stroke.
