This reviewer provided examples of research that had been done in the past to detect brain strokes. Brain strokes are one of the leading causes of death among humans around the world. There are two main types of strokes: ischemic strokes and hemorrhagic strokes. In this study, we focused on ischemic stroke ways to prevent death. With this type of stroke, it is possible to save a person's life and help them recover from the effects of the condition. However, haemorrhage. In this review, an effort is made to recall a large number of studies that have been conducted in that area in the past to demonstrate a large number of ways that can be used to identify strokes and then can deliver therapy to preserve the life of the patient. In my research, I used two distinct methods to investigate and diagnose strokes: first, I used an electroencephalogram (EEG) (time series) approach; with the EEG, I chose the acute ischemic stroke way (AIS), and I got the signals from four positions only (c3,c4o1,o2); this gave me more of an indication that a stroke was occurring. Secondly, I used an image processing path that involved a magnetic resonance imaging (MRI) scan; this gave me a clearer. In my research, the electroencephalogram (EEG) is combined with the machine learning methodology implemented in the Python programming language to construct a variety of algorithm types. These algorithm types include multi-layered perceptron (MLP), random forest, decision tree, and additional tree. The application of machine learning and deep learning is developed and now it's a desired way to the health path, so can get good results, the aim of this study is to fix the stroke case exactly and to classify any case in the stroke or outside of it. Machine learning has become a powerful tool in the health path exactly to get good results and can be used in multiple algorithms techniques.