Table 3 Diagnostic Performance of the Deep Learning Model in Training, Internal Test and External Test Sets
Sets | Accuracy (%) | Sensitivity (%) | Specificity (%) | PPV (%) | NPV (%) | AUC (95% CI) | F1 score | MCC |
|---|---|---|---|---|---|---|---|---|
Training set | 81.94 ± 0.01 | 82.24 ± 0.01 | 81.47 ± 0.01 | 82.81 ± 0.01 | 83.55 ± 0.01 | 0.87 ± 0.01 | 0.75 ± 0.01 | 0.63 ± 0.01 |
Internal test set | 81.43 | 82.83 | 74.00 | 83.33 | 80.77 | 0.86(0.83–0.90) | 0.70 | 0.59 |
External test set | 80.19 | 85.81 | 76.36 | 79.49 | 80.60 | 0.86(0.84–0.89) | 0.75 | 0.59 |