Table 5.
Mean 3-Fold CV | Ensemble 3-Fold CV | |||
---|---|---|---|---|
Train | Validation | Test | Test (95% CI) | |
LGG vs. HGG | ||||
Loss | 0.451 | 0.474 | 0.459 | |
Accuracy | 0.793 | 0.797 | 0.797 | 0.805 (0.759–0.851) |
AUC-ROC | 0.874 | 0.864 | 0.866 | 0.878 (0.840–0.916) |
Precision | ||||
LGG | 0.600 | 0.611 | 0.606 | 0.624 (0.567–0.680) |
HGG | 0.917 | 0.911 | 0.913 | 0.906 (0.872–0.940) |
Recall | ||||
LGG | 0.822 | 0.804 | 0.809 | 0.788 (0.740–0.835) |
HGG | 0.781 | 0.794 | 0.792 | 0.812 (0.766–0.857) |
F1 | ||||
LGG | 0.693 | 0.694 | 0.701 | 0.696 (0.642–0.750) |
HGG | 0.843 | 0.848 | 0.856 | 0.856 (0.815–0.897) |
Grade (2/3/4) | ||||
Loss | 0.867 | 0.837 | 0.802 | |
Accuracy | 0.729 | 0.751 | 0.742 | 0.752 (0.701–0.803) |
G.2 | 0.801 | 0.793 | 0.794 | 0.802 (0.755–0.849) |
G.3 | 0.865 | 0.889 | 0.892 | 0.892 (0.856–0.929) |
G.4 | 0.793 | 0.819 | 0.798 | 0.809 (0.763–0.856) |
AUC-ROC | 0.776 | 0.788 | 0.803 | 0.816 (0.770–0.861) |
G.2 | 0.838 | 0.849 | 0.862 | 0.872 (0.833–0.911) |
G.3 | 0.865 | 0.670 | 0.697 | 0.713 (0.660–0.766) |
G.4 | 0.793 | 0.844 | 0.850 | 0.861 (0.821–0.902) |
Precision | ||||
G.2 | 0.427 | 0.422 | 0.434 | 0.448 (0.390–0.507) |
G.3 | 0.246 | 0.000 | 0.000 | 0.000 (0.000–0.000) |
G.4 | 0.869 | 0.880 | 0.881 | 0.890 (0.853–0.927) |
Recall | ||||
G.2 | 0.655 | 0.726 | 0.812 | 0.848 (0.806–0.890) |
G.3 | 0.099 | 0.000 | 0.000 | 0.000 (0.000–0.000) |
G.4 | 0.842 | 0.871 | 0.836 | 0.842 (0.799–0.885) |
Specificity | ||||
G.2 | 0.829 | 0.806 | 0.790 | 0.793 (0.745–0.841) |
G.3 | 0.960 | 1.000 | 1.000 | 1.000 (1.000–1.000) |
G.4 | 0.662 | 0.683 | 0.697 | 0.724 (0.671–0.776) |
F1 | ||||
G.2 | 0.517 | 0.532 | 0.520 | 0.586 (0.529–0.644) |
G.3 | 0.139 | 0.000 | 0.000 | 0.000 (0.000–0.000) |
G.4 | 0.662 | 0.875 | 0.872 | 0.865 (0.825–0.905) |