Model | AUC (95% CI) | Sensitivity | Specificity | Accuracy | F1 score |
---|---|---|---|---|---|
Training cohort | Â | Â | Â | Â | Â |
Clinical model | 0.81 (0.72–0.90) | 0.79 | 0.72 | 0.76 | 0.81 |
Radiomics model | 0.83 (0.75–0.91) | 0.75 | 0.77 | 0.75 | 0.79 |
Combined model | 0.95 (0.91–0.99) | 0.84 | 0.99 | 0.90 | 0.91 |
Internal validation cohort | Â | Â | Â | Â | Â |
Clinical model | 0.68 (0.51–0.85) | 0.59 | 0.76 | 0.65 | 0.68 |
Radiomics model | 0.80 (0.67–0.93) | 0.76 | 0.65 | 0.72 | 0.77 |
Combined model | 0.83 (0.71–0.96) | 0.90 | 0.71 | 0.83 | 0.87 |
External validation cohort | Â | Â | Â | Â | Â |
Clinical model | 0.73 (0.57–0.88) | 0.71 | 0.67 | 0.69 | 0.73 |
Radiomics model | 0.68 (0.52–0.84) | 0.68 | 0.76 | 0.71 | 0.73 |
Combined model | 0.79 (0.66–0.92) | 0.82 | 0.71 | 0.78 | 0.81 |