Fig. 5From: Development of a simplified model and nomogram in preoperative diagnosis of pediatric chronic cholangitis with pancreaticobiliary maljunction using clinical variables and MRI radiomicsCalibration curves of the combined model in the training (a) cohort and validation (b) cohort. The combined model predicted the incidence of cholangitis and actual rate are, respectively, plotted on the x- and y-axis. The diagonal line represents a faultless calculation of an ideal model. Pink lines represent outcomes of the combined model in training and test cohort. A closer lining to the diagonal line indicates a more accurate calculation. The decision curve analysis (DCA) of the clinical model (red line) and the combined model (blue line) in the training (c) cohort and validation (d) cohort. The y-axis indicates the net benefit; x-axis indicates threshold probability. The gray line represents the decision curve of the assumption that all PBM cases with cholangitis, and the black line shows the decision curve of the assumption that no PBM case with cholangitis. The DCA revealed that the combined model was more advantageous than the clinical modelBack to article page