Presentation a Model for Prediction of Cerebrovascular Accident using Data Mining Algorithm

Cerebrovascular Accident (CVA) is a major health problem and the most common neurological disease affecting 5.5 million individuals around the world annually. The present study aimed to assess the effective factors in CVA and determine the performance of data mining algorithm in predicting the disease.
This retrospective, cross-sectional, descriptive-analytical study used Crisp as one of the most powerful data mining techniques. The data were analyzed using SPSS Modeler 14.2 and neural network algorithm.
According to the findings, the overall accuracy of the neural network model was 89.7%, which reflects the strength of this model in predicting the risk of CVA. Indeed, this model predicted the risk factors of diabetes as the most important factor in the risk of CVA. Age, trauma, and atherosclerosis were also determined as other risk factors.
According to this study, diabetic patients were more prone to CVA. Additionally, the risk of this disease increased with age. Therefore, effective measures are recommended to be taken for diagnosis and treatment of diabetes surveillance by establishing clinics and performing periodic screening.