Brain Strokes are one of the most serious and most common diseases in the world due to their sudden occurrence. It can be considered the death of brain cells as a result of the failure to provide these cells with the right amount of blood, which leads to the interruption of the brain's action and therefore leads to death within minutes. Therefore, predicting the incidence of strokes based on the risk factors of the patient is one of the most important reasons for preventing the occurrence of these strokes and providing early treatment for them. Machine learning techniques are widely used in building predictive models for strokes according to the patient's electronic health record, which contains the factors that lead to the occurrence of stroke. Ensemble methods are one of the most important concepts in machine learning as it works to collect more than one machine learning algorithm and combine them to produce a reliable predictive model with higher accuracy. The purpose of this paper is to present a survey on predictive models for Brain Strokes using a machine learning ensemble classifier.