Skip to main content
. 2021 Jul 22;11:709137. doi: 10.3389/fonc.2021.709137

Table 2.

Predictive performance of different models in the training data set.

AUC (95% CI) Sensitivity (%) Specificity (%) Accuracy (%)
StackPET-CT 0.86 (0.80-0.91) 71.75 84.38 75.25
 SECT 0.74 (0.67-0.80) 82.35 53.12 67.17
 SEPET 0.75 (0.69-0.81) 86.25 56.25 72.22
Clinical model 0.64 (0.57-0.71) 65.69 62.50 60.10

The bold values represented the highest one of the evaluation indices.