Table VI.

Prediction results of the support vector machine classifier using sample data from GSE17260, GSE44104 and GSE51088.

Datasets	Number of samples	Correct samples	Correct rate	Sensitivity	Specificity	PPV	NPV	AUROC
GSE17260	110	102	0.927	0.894	0.987	0.964	0.915	0.988
GSE44104	60	56	0.933	1.000	0.800	0.909	1.000	0.970
GSE51088	147	142	0.966	0.969	0.941	0.992	0.800	0.967
TCGA	395	357	0.9038	0.987	0.801	0.862	0.979	0.981

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