Table 4 Predictive performance of the three models in the training and validation sets
Model | Accuracy (%) | Sensitivity (%) | Specificity (%) | AUC (95% CI) |
|---|---|---|---|---|
Training set | ||||
 Clinicopathological model | 62.4 | 69.0 | 60.2 | 0.708 (0.642, 0.774) |
 Radiomics score | 67.2 | 77.4 | 64.0 | 0.783 (0.727, 0.839) |
 Nomogram | 74.7 | 81.0 | 72.7 | 0.850 (0.803, 0.898) |
Validation set | ||||
 Clinicopathological model | 53.7 | 69.4 | 48.7 | 0.659 (0.563, 0.755) |
 Radiomics score | 65.1 | 80.6 | 60.2 | 0.782 (0.702, 0.862) |
 Nomogram | 72.5 | 83.3 | 69.0 | 0.824 (0.755, 0.894) |