Skip to main content

Table 3 Evaluating the performance of the prediction models

From: CT-based peritumoral radiomics signatures to predict early recurrence in hepatocellular carcinoma after curative tumor resection or ablation

Models

AUC

cfNRI

IDI

PPV

NPV

AUC [95%CI]

P

cfNRI+

cfNRI-

P

IDI

P

PPV

P

NPV

P

PT-RO

0.79 [0.66, 0.92]

–

–

–

–

–

–

0.93

–

0.64

–

T-RO

0.62 [0.46, 0.79]

< 0.01

−0.47

−0.32

< 0.01

0.22

< 0.01

0.63

< 0.01

0.65

0.92

PT-E

0.61 [0.47, 0.74]

< 0.01

−0.24

− 0.41

0.02

0.20

0.01

0.69

< 0.01

0.55

0.38

  1. AUC area under the curve, CI Confidence Interval, cfNRI+: movement in predicted risks introduced by changes of models in ER cases. cfNRI-: movement in predicted risks introduced by changes of models in non-ER cases. IDI Integrated Discrimination Improvement, PPV positive predictive value, NPV negative predictive value; P values of less than 0.05 (two-sided) were considered statistically significant; PT-RO peritumoral radiomics, T-RO tumoral radiomics, PT-E peritumoral enhancement