Table 1.

The performance evaluation of a SVM classifier in training and validation dataset

	ROC
Datasets	AUROC	Sensitivity	Specificity	PPV	NPV
Training set (TCGA, N = 176)	0.969	0.915	0.884	0.741	0.966
Validation set (GSE21257, N = 53)	0.907	0.857	0.778	0.882	0.737

SVM Support vector machine, ROC Receiver operating characteristic, AUROC Area under the receiver operating characteristic curve, PPV Positive predictive value, NPV Negative predictive value