Publication: Ordered Logistic Regression With Artificial Neural Network Models For Variable Selection For\r\nPrediction Of Hypertension Patient Outcomes
Loading...
Date
2020
Journal Title
Journal ISSN
Volume Title
Publisher
Cancer Research Institute, Sapporo Medical Univers
Abstract
The purpose of this study is to demonstrate the best strategy for the variable selection, using the developed Ordered Logistic Regression (OLR) and Multilayer Perceptron Neural Network (MLP). At the first stage, all the selected variables will be a screen for their important relationship point of view through ordered logistics regression and bootstrap methodology. After considering for 1500 of the bootstrapping methods, it was found that smoking factor, total cholesterol factor, and triglycerides come to a significant relationship to the level of hypertension. By considering the level of significance of 0.25 for ordered logistic regression, these three variables are being selected and used for the input of the MLP model. The performance of MLP was evaluated through the Predicted Mean Square Error (PMSE) of the neural network for the (MSE-forecasts the Network). PMSE is used as a measurement of how far away from our predictions are from the real data. The smallest MSE from MLP, indicate the best combination of variables selection in the model. In this research paper, we also provide the R syntax for OLR and MLP better illustration.
Description
Sapporo Medical Journal
Volume 54, Issue 10, October 2020
Keywords
Multilayer Perceptron Neural Network (MLP), Mean Square Error (MSE), hypertension
Citation
Mohamad Ghazali, Farah Muna and Wan Ahmad, Wan Muhamad Amir and Awang Nawi, Mohamad Arif and Mohd Noor, Nor Farid and Ghazalli, Nur Fatiha and Aleng, NorAzlida and Mohd Ibrahim, Mohamad Shafiq and Abdul Halim, Nurfadhlina (2020) Ordered logistic regression with artificial neural network models for variable selection for prediction of hypertension patient outcomes. Sapporo Medical Journal, 54 (10). pp. 1-9. ISSN 0036-472X