. 2019 Dec 27;9:19847. doi: 10.1038/s41598-019-56367-1

Table 2.

Effectiveness evaluation of the classifier of ten miRNAs on training set and validation set.

Datasets	C index	Brier score	Log rank P	ROC
Datasets	C index	Brier score	Log rank P	AUROC	Sensitivity	Specificity	PPV	NPV
Training set (GSE43732, N = 119)	0.867	0.054	1.05 × 10⁻³	0.948	0.755	0.879	0.833	0.817
Validation set (TCGA, N = 93)	0.819	0.096	1.47 × 10⁻³	0.902	0.806	0.710	0.847	0.747

ROC, receiver operating characteristic curve; AUROC, area under the receiver operating characteristic curve; PPV, positive predictive value; NPV, negative predictive value.