Risk Prediction and Stratification of Patients with Stroke Using Data Mining Techniques

Abstract

Background: Stroke is one of the most common causes of death and neurological disabilities in all societies. The use of data mining techniques to create predictive models is very helpful in identifying people at risk to reduce the complications of the disease. Objectives: The purpose of this study was to investigate the performance of data mining algorithms and predict the risk of stroke in suspected stroke patients using decision tree based on the risk factors that affect it. Methods: This research is analytical and its database contains 1184 records. Data were obtained from the patients referring to Imam Reza Educational Center of Tabriz in year 2017. The data collection tool was a check list. The analysis was performed using Orange software version 2.7. In modeling phase, the Classification Tree, Naïve Bayes, Neural Network, SVM and kNN algorithms have been used. Results: having physical inactivity, high cholesterol, cardiovascular disease, history of transient ischemic attack, history of previous stroke, and high blood pressure were the most effective variables. With the decision tree, rules have been developed that can be used as a model for predicting the risk of stroke in patients. The model's accuracy was 95.52%. Conclusion: The findings showed that by applying the rules, for a new sample with specific characteristics, it is possible to determine what the risk of stroke is.