Table 2 The predictive performance of the clinical model, the radiomics model, and the combined model
Model | Accuracy | Sensitivity | Specificity | positive predictive value | negative predictive value | AUC (95% CI) |
|---|---|---|---|---|---|---|
Radiomics training | 0.782 | 0.944 | 0.643 | 0.694 | 0.931 | 0.84 (0.76–0.93) |
Radiomics validation | 0.824 | 0.938 | 0.722 | 0.750 | 0.929 | 0.84 (0.70–0.98) |
Clinical training | 0.603 | 0.568 | 0.634 | 0.583 | 0.619 | 0.65 (0.55–0.75) |
Clinical validation | 0.500 | 0.474 | 0.533 | 0.563 | 0.444 | 0.58 (0.40–0.76) |
Combined training | 0.782 | 0.702 | 0.903 | 0.917 | 0.667 | 0.85 (0.77–0.94) |
Combined validation | 0.853 | 0.789 | 0.933 | 0.938 | 0.778 | 0.85 (0.71–0.99) |