Skip to main content

Table 4 Predictive performance of the radiomic signature and radiomic Nomogram

From: Radiomic nomogram based on MRI to predict grade of branching type intraductal papillary mucinous neoplasms of the pancreas: a multicenter study

Model

Radiomic signature

Radiomic nomogram

Specificity

Sensitivity

AUC (95% CI)

Specificity

Sensitivity

AUC (95% CI)

Training set

0.740

0.769

0.836 (0.750 ~ 0.901)

0.948

0.734

0.903 (0.828 ~ 0.952)

Validation set 1

0.816

0.700

0.811 (0.671 ~ 0.909)

0.790

0.900

0.884 (0.759 ~ 0.958)

Validation set 2

0.812

0.714

0.822 (0.690 ~ 0.915)

0.838

0.857

0.876 (0.754 ~ 0.952)

  1. AUC Area under the receiver operating characteristic (ROC) curve, CI Confidence interval