Table 4 Metrics of the 3 random forest classification models, each trained on the same subset of animals with the features shown in Table 3. The metrics are calculated from the test subset.
From: Radiomics approach for identifying radiation-induced normal tissue toxicity in the lung
Classifier | Radiation status | EV status | Treatment |
|---|---|---|---|
Accuracy (%) | 94.29 | 85.71 | 57.14 |
AUC/mean AUC | 0.909 | 0.859 | 0.796 |
Sensitivity (%)/mean sensitivity | 0.818 | 0.941 | 0.529 |
Specificity (%)/mean specificity | 1.00 | 0.778 | 0.842 |
No information rate (%) (p-value) | 68.57 (2.6 × 10−4) | 51.43 (2.3 × 10−5) | 34.29 (4.7 × 10−2) |
