Table 3.
Diagnostic performance of models in the training and validation cohorts.
| Models | Training Cohort (n = 120) | Validation Cohort (n = 50) | ||||||
|---|---|---|---|---|---|---|---|---|
| Sensitivity | Specifity | Accuracy (95%CI) | AUC (95%CI) | Sensitivity | Specifity | Accuracy (95%CI) | AUC (95%CI) | |
| Clinical model | 0.67 | 0.69 | 0.68 (0.59, 0.76) |
0.69 (0.59, 0.79) |
0.50 | 0.79 | 0.70 (0.55, 0.82) |
0.72 (0.57, 0.87) |
| MP-Radscore | 0.91 | 0.80 | 0.84 (0.76, 0.90) |
0.89 (0.82, 0.95) |
0.81 | 0.88 | 0.82 (0.73, 0.89) |
0.88 (0.77, 0.98) |
|
Combined
nomogram |
0.92 | 0.81 | 0.85 (0.77, 0.91) |
0.91 (0.84, 0.97) |
0.71 | 0.90 | 0.78 (0.64, 0.88) |
0.90 (0.81, 1.00) |