Volume 26, Issue 5 (8-2019)
RJMS 2019, 26(5): 104-113 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
andayeshgar B, KHatony A, Rezaei M. Prediction of tendency to surgical intervention in nurses using logistic regression model and its comparison with artificial neural network. RJMS 2019; 26 (5) :104-113
URL: http://rjms.iums.ac.ir/article-1-5623-en.html
URL: http://rjms.iums.ac.ir/article-1-5623-en.html
Kermanshah University of Medical Sciences, Kermanshah, Iran , akhatony@kums.ac.ir
Abstract: (2835 Views)
Background: 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.
Methods: 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.
Methods: 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.
Type of Study: Research |
Subject:
Biostatistics
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
