|Detection of Functional Limitation in Diabetic Patients Based on the Optimal Combination of Care Indicators Using Ramp AUC and Comparing its Performance With the Existing Methods|
|Parvin Sarbakhsh1,2, Leili Faraji Gavgani1, Mohamad Asghari Jafarabadi1,3, Seyed Morteza Shamshirgaran3|
|1Department of Statistics and Epidemiology, Faculty of Health, Tabriz University of Medical Sciences, Tabriz, Iran
2Road Traffic Injury Research Center, Tabriz University of Medical Sciences, Tabriz, Iran
3Medical Education Research Center, Tabriz University of Medical Sciences, Tabriz, Iran
CJMB 2018; 5: 149-154
Viewed : 1097 times
Downloaded : 1124 times.
Keywords : Ramp AUC model, SVM, GAM, Diabetes, Functional limitation, Classification, Kernel function, RBF kernel
|Full Text(PDF) | Related Articles|
Objectives: The area under the ROC curve (AUC) is a common criterion to assess the overall classification performance of the markers. In practice, due to the limited classification ability of a single marker, we are interested in combining markers linearly or nonlinearly to improve classification performance. Ramp AUC (RAUC) is a new statistical AUC-based method which can find such optimal combinations of markers. In this study, RAUC was used to find the optimal combinations of care indicators related to functional limitation as a complication of diabetes and accurately discriminate this outcome based on its underlying markers.
Materials and Methods: This cross-sectional study was conducted on 378 diabetic patients referred to diabetic centers in Ardebil and Tabriz during 2014 and 2015. To have an accurate classification of diabetic patients according to their functional limitation status, RAUC method with RBF kernel was employed to look for an optimal combination of care indicators. Classification performance of the model was evaluated by AUC and compared with logistic regression, support vector machine (SVM) and generalized additive model (GAM) via training and test validation method.
Results: Out of 378 diabetics, 67.46% had functional limitation. RAUC had an AUC of 1 for the test dataset and outperformed logistic (AUC = 0.079), GAM (AUC = 0.082), SVM with linear kernel (AUC = 0.67) and was slightly better than SVM with RBF kernel (AUC = 0.98).
Conclusions: There was a strong nonlinearity in data and RAUC with RBF kernel which is a nonlinear combination of markers could detect this pattern
Cite By, Google Scholar