Table 2 Comparison of the performance of the three models in predicting MSI status
Models | AUC | Sensitivity | Specificity | Accuracy | PPV | NPV |
|---|---|---|---|---|---|---|
Radiomics | ||||||
 Training(n = 194) | 0.81 (0.74–0.87) | 0.67 | 0.81 | 0.77 | 0.57 | 0.86 |
 Validation (n = 82) | 0.82 (0.72–0.92) | 0.65 | 0.80 | 0.76 | 0.54 | 0.86 |
Clinics | ||||||
 Training(n = 194) | 0.85 (0.79–0.92) | 0.77 | 0.88 | 0.84 | 0.70 | 0.89 |
 Validation (n = 82) | 0.87 (0.79–0.95) | 0.79 | 0.80 | 0.79 | 0.59 | 0.90 |
Nomogram | ||||||
 Training(n = 194) | 0.87 (0.81–0.93) | 0.82 | 0.83 | 0.82 | 0.65 | 0.91 |
 Validation (n = 82) | 0.90 (0.83–0.96) | 0.80 | 1.00 | 0.80 | 1.00 | 0.73 |