Fig. 6

Receiver operating characteristic (ROC) curves, calibration curve and decision curve analysis (DCA) of the complex predictive model including 4 signatures (miR-139-5p, STC1, miR-20a-5p and FGL2) to distinguish CRC samples from normal samples. A ROC curves of the complex predictive model in testing datasets GSE126095, GSE128449 and GSE35602, and external validation cohort. B Calibration curve of the complex predictive model in testing datasets and validation cohort. C The decision curve analysis of 15 models, of which a complex predictive model containing all 4 signatures (miR-139-5p, STC1, miR-20a-5p and FGL2), 4 models containing 3 signatures, 6 models containing 2 signatures and 4 models containing 1 signature