Skip to main content

Table 2 The performance of the predictive models in independent validation datasets

From: Construct of qualitative diagnostic biomarkers specific for glioma by pairing serum microRNAs

Dataset

#Non-cancer

#Glioma

SEN%

SPE%

ACC%

PPV%

NPV%

5-miRPairs

 GSE139031

151

164

100%

100%

100%

100%

100%

 GSE112264

39

48

100%

100%

100%

100%

100%

 GSE113740

10

24

100%

100%

100%

100%

100%

 GSE106817

2611

–

–

–

95.90%

–

–

Dataset

#Non-glioma

#Glioma

SEN%

SPE%

ACC%

PPV%

NPV%

32-miRPairs

 GSE112264

1204

48

97.92%

99.58%

98.74%

90.38%

99.91%

 GSE113740

282

24

100%

100%

100%

100%

100%

 GSE106817

1123

–

–

–

98.31%

–

–

 GSE139031

–

164

–

–

95.73%

–

–

 GSE122497

542

–

–

–

99.45%

–

–

  1. Abbreviation: SEN sensitivity, SPE specificity, ACC accuracy, PPV positive predictive value, NPV negative predictive value