Mohammad Asghari Jafarabadi - Tabriz University of Medical Sciences, Tabriz, Iran۱
Nasrin Someeh - Tabriz University of Medical Sciences, Tabriz, Iran۱
Seyed Morteza Shamshirgarant - NeyshaburUniversity of Medical Sciences
Farshid Farzipoor - Tabriz University of Medical Sciences, Tabriz, Iran

Background:For enhancing the accuracy of diagnosis and the quality of patient care, Neural Networks (NN) method was approached in patients with Brain Stroke (BS) to predict the outcome by the risk factors.Methods:In this prospective study, total of 332 brain stroke patients (mean age 77.4 (SD 10.4) years, 50.6% male) from Imam Khomeini hospital, Ardabil, Iran, from 2004 to 2018, participated. The NN was applied to predict the effects of risk factors on mortality. The fitness and quality of models were measured by diagnostic indices.Results:The most important predictors for BS mortality based on optimal model results were time interval after ten years, smoking, history of myocardial infarction, and age category. The other independent variables sex, employment, residence, education level, former smoking, waterpipe smoking, history of heart disease, diabetes, oral contraceptive pill use, physical activates, history of cerebrovascular accident type, history of blood pressure history, history of hyperlipoproteinemia, were at moderate importance. The finding of this study demonstrated that the accuracy rang of models is 81%-85%Conclusion:The NN strategy showed a satisfying presentation in the prediction of BS mortality based on the main risk factors with higher diagnostic accuracy.

Data mining, Neural Networks, Predicting, Brain Stroke, Risk factors