Early Brain Stroke Prediction Using Machine Learning Technique

Abstract

Sometimes, a stroke called a "brain attack" occurs when blood supply to an area in the brain is cut off. Often due to doctor perception, deciding whether an observation diagnostic test is brain stroke or not which causes controversy. As a stroke can happen many problems in our brain which causes brain stroke. One of the most common reason of brain stroke is blood supply occurrences. But the examination of this kind of brain stroke, doctor observes the result of this test then decide a result of brain stroke. But human can’t show a result early and accurate result all the time. In this matter doctor make their decision on diagnostic test result. But human perception cannot be accurate all the time. Besides, it is not always possible to conclude the accurate judgement early. In that case, the benefit of early prediction, we can get accurate result. In this project, we define our classification task as the prediction of brain stroke. This system gives 97% accuracy of brain stroke. Our approach eliminates the time consuming of human perception.