Identification of the Optimal Model for the Prediction of Diabetic Retinopathy in Chinese Rural Population: Handan Eye Study

Table 5

The details of pairwise comparisons of the values.

Model	GBM	RF	MLR	SVM	C&RT	AUROC
GBM	—	0.624	0.408	<0.001	<0.001	0.952
RF	0.624	—	0.538	<0.001	<0.001	0.949
MLR	0.408	0.538	—	<0.001	<0.001	0.936
SVM	<0.001	<0.001	<0.001	—	0.052	0.765
C&RT	<0.001	<0.001	<0.001	0.052	—	0.682

Note: Gradient boosting machine (GBM); random forests (RF); multivariable logistic regression (MLR); support vector machine (SVM); classification and regression trees (C&RT).