Fig. 6From: Assessment of axial spondyloarthritis activity using a magnetic resonance imaging-based multi-region-of-interest fusion modelAUC-ROC (left), calibration (center), and decision (right) curves of different Rad_Sig in training (up) and testing (down) cohorts. The model based on fusion-set derived Rad_Sig and constructed with Random Forest outperforms the other two models. AUC, area under the curve; DCA, decision curve analysis; ROC, receiver operating characteristic; ROI, region of interestBack to article page