Table 4 Performance evaluation of Face2Bone model in overall and gender-stratified validation sets.
Validation sets | Accuracy | Precision | Recall | F1-score | AUC | Kappa |
|---|---|---|---|---|---|---|
Overall model | 0.9285 | 0.9294 | 0.9285 | 0.9283 | 0.9856 | 0.8887 |
Female subgroup | 0.8964 | 0.8958 | 0.8964 | 0.8960 | 0.9657 | 0.7926 |
Male subgroup | 0.8343 | 0.8349 | 0.8343 | 0.8341 | 0.9470 | 0.7400 |