Comparison of artificial neural network with logistic regression in prediction of tendency to surgical intervention in nurses

Introduction: Logistic regression is one of the modeling methods for bipartite dependent variables. On the other hand, artificial neural network is a flexible method with the least limitation. The importance of growing unnecessary beauty surgeries and the importance of prediction and classification made us consider the present study, with the aim of comparing logistic regression and artificial neural network, to predict the tendency for nurses to crack down Method: The sample consisted of 360 nurses working in hospitals affiliated to Kermanshah University of Medical Sciences. The response variable was a tendency or unwillingness to cure. An artificial network evaluation was performed based on the least squares prediction error. Using the rock curve index and prediction accuracy, two models were compared. SPSS22, statistica12 and chi-square test were used to analyze the data Results: In the training group, predictive accuracy, sensitivity, specificity, and surface area under the rock curves for the logistic regression method were 0.777, 0.760, 0.779, 0.779, respectively, and artificial neural network method was 0.847, 0.859, 0.833, 0.846. Also, in the test group, the criteria for logistic regression were 0.813, 0.738, 0.926, 0.832 and 0.735, 0.737, 0.731, 0.735, respectively. Chi-square test did not show any significant difference between the two levels under the rock curve in any of the groups. Conclusion: In the training group, the performance of the ANN was better than the logistic regression method, but in the experimental group, the prediction accuracy and logistic regression characteristics were more than the artificial neural network. Therefore, logistic regression can be used to predict the tendency for surgical intervention in nurses.