Table 3.
Detailed metrics for the receiver operating characteristic analysis of the best model MS/G trained with all available data on both test sets with report and image-based labels. The area under the receiver operating characteristic curve (AUC) in % is given per class. Also, sensitivity and specificity in % are given per class for binary classifications. Thresholds were calculated by the Youden-Index on the training set and applied to the test set
| Test-set labeled by report content | Test-set labeled by image content | |||||
|---|---|---|---|---|---|---|
| Classes | AUC | Sensitivity | Specificity | AUC | Sensitivity | Specificity |
| Misplaced CVC | 77.6 | 64.4 | 74.1 | 83.4 | 70.5 | 76.9 |
| Pleural Effusion | 86.4 | 71.9 | 83.3 | 87.5 | 73.5 | 83.8 |
| Pulmonary Congestion | 74.5 | 57.8 | 75.9 | 83.9 | 60.2 | 88.1 |
| Pulmonary Infiltrates | 81.9 | 78.3 | 70.7 | 77.3 | 77.8 | 66.9 |
| Pneumothorax | 84.0 | 87.8 | 60.6 | 91.8 | 97.1 | 60.1 |
| Overall | 80.9 | 72.0 | 72.9 | 84.8 | 75.8 | 75.2 |