Stroke is the second leading cause of mortality worldwide, and it continues to be a huge health burden for both individuals and national healthcare systems. Hypertension, cardiac disease, diabetes, dysregulation of glucose metabolism, atrial fibrillation, and lifestyle factors are all potentially modifiable risk factors for stroke. Stroke is a life-threatening medical condition. When blood flow to a portion of your brain is halted or diminished, brain tissue is deprived of oxygen and nutrients, resulting in a stroke. Within minutes, brain cells begin to die. The authors aimed to derive a model equation for developing a stroke pre-diagnosis algorithm with the potentially modifiable risk factors. Ischemic embolic and haemorrhagic strokes account for the bulk of strokes. When a blood clot forms far away from the patient's brain, usually in the heart, it travels through the circulation and lodges in the patient's smaller brain arteries. Haemorrhagic stroke is another type of brain stroke that happens when a blood vessel in the brain ruptures or spills blood. Stroke is the world's second leading cause of death and one of the leading causes of death in persons over the age of 65[1]. By the method proposed, it would be able to mitigate the stroke by 99 percent, which is almost most of the time.

Keywords : Stroke prediction system, Artificial neural network, deep learning, prediction system, accuracy.