Table 3.
Predictive performance for the proposed models.
| Different models | Training dataset N= 210 | Validation dataset N= 89 | ||||||
|---|---|---|---|---|---|---|---|---|
| AUC (95%CI) | ACC | SENS | SPEC | AUC (95%CI) | ACC | SENS | SPEC | |
| Clinical model | 0.756 (0.694–0.817) | 75.2% | 82.0% | 58.3% | 0.705 (0.586–0.823) | 77.5% | 84.7% | 47.1% |
| Radiomics signature | 0.886 (0.840–0.931) | 85.2% | 99.2% | 67.0% | 0.874 (0.802–0.945) | 84.3% | 100% | 57.6% |
| Combined model | 0.954 (0.930–0.978) | 88.6% | 99.2% | 72.6% | 0.906 (0.844–0.9680) | 87.6% | 98.4% | 64.3% |
AUC, area under the curve; CI, confidence interval; ACC, accuracy; SENS, sensitivity; SPEC, specificity.