A stroke is a medical disorder in which the blood flow to the brain is interrupted, resulting in cell death. In many parts of the world, it is now the leading cause of death. Several risk factors believed to be linked to the aetiology of stroke have been established by investigating the affected persons. These risk factors have been used in a number of studies to predict and diagnose stroke problems. Machine learning and data mining technologies are used in the bulk of the models. Two machine learning algorithms, the XG Boost algorithm and the Decision tree, are employed in this study to determine the type of stroke that could occur or has occurred based on a person's physical state and medical report data. A large number of entries from the hospitals are used in order to address our challenge. The suggested machine learning algorithms can help with enhanced disease knowledge and can be a helpful healthcare companion. © 2022 Elsevier B.V., All rights reserved.