Table 4 Comparison of diagnostic performance between thoracic surgeons and our model
From: Intelligent detection and grading diagnosis of fresh rib fractures based on deep learning
Senior Surgeon | Middle grade surgeon | Junior surgeon | |||||||
|---|---|---|---|---|---|---|---|---|---|
Fracture type | Precision | Recall | F1 score | Precision | Recall | F1 score | Precision | Recall | F1 score |
Non-severe fracture | 0.802 | 0.932 | 0.862 | 0.669 | 0.736 | 0.701 | 0.651 | 0.670 | 0.660 |
Severe fracture | 0.922 | 0.842 | 0.880 | 0.793 | 0.774 | 0.783 | 0.606 | 0.695 | 0.645 |
All classes | 0.845 | 0.895 | 0.869 | 0.713 | 0.751 | 0.731 | 0.635 | 0.678 | 0.656 |