Deep Learning for Brain Stroke Disease Management: A Mapping Study

The origin of the word “stroke” is based on the concept of receiving a sudden blow or impact, which reflects how quickly the symptoms of this illness can appear - people can be suddenly struck by it. A stroke occurs when the supply of blood to the brain is interrupted, leading to damage in brain cells due to a lack of oxygen. The resulting set of symptoms is referred to as a stroke. Every year more than 15 million people worldwide are affected by stroke. Of these, 7 million die, and the other five million are left disabled. Since the brain governs the entire body, the symptoms of a stroke can vary extensively, contingent on the specific areas of the brain that are impacted. Recently, deep learning has emerged as a powerful tool in the healthcare field, allowing stroke patients to receive tailored and efficient clinical care. This paper aims to assess the role of various deep learning approaches utilized for brain stroke disease management using a systematic mapping methodology. Over the period from 2010 to 2022, a total of 1652 studies were unearthed by querying six widely used digital libraries. To the best of our knowledge, no formal mapping study has been conducted on the application of deep learning on brain stroke management.