Fig. 7

Constructing a predictive model based on diagnostic FRLs. A The predicting nomogram of 6 diagnostic FRLs for BPD incidence. B ROC curve for the training set (AUC = 0.932). C Calibration curve for the training set (mean absolute error = 0.053 mean squared error = 0.00393). D DCA curve for the training set. E ROC curve for internal validation (AUC = 0.923). F Calibration curve for internal validation (mean absolute error = 0.046 mean squared error = 0.00328). G DCA curve for internal validation. ROC, Receiver operating characteristic. AUC, area under the ROC curve. DCA, decision curve analysis