Table 5.
The validation of classify model between LR and SVM in healthy, mild, and severe patient (n = 101).
| Validation | LR | SVM | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| SK | KUR | FAV | FAD | FADV | SK | KUR | FAV | FAD | FADV | |
| Sensitivity | 0.667 | 0.737 | 0.747 | 0.768 | 0.818 | 0.657 | 0.747 | 0.747 | 0.788 | 0.828 |
| Specificity | 0.500 | 0.500 | 1.000 | 0.500 | 1.000 | 0.500 | 0.500 | 1.000 | 0.500 | 1.000 |
| PPV | 0.660 | 0.730 | 0.747 | 0.760 | 0.827 | 0.650 | 0.755 | 0.747 | 0.780 | 0.837 |
| NPV | 1.000 | 1.000 | 1.000 | 1.000 | 0.667 | 1.000 | 0.333 | 1.000 | 1.000 | 0.667 |
| Accuracy | 0.663 | 0.733 | 0.752 | 0.762 | 0.822 | 0.653 | 0.753 | 0.752 | 0.782 | 0.832 |
| AUC | 0.738 | 0.840 | 0.845 | 0.866 | 0.905 | 0.739 | 0.790 | 0.768 | 0.865 | 0.845 |
| Kappa | 0.344 | 0.482 | 0.527 | 0.539 | 0.661 | 0.326 | 0.509 | 0.523 | 0.578 | 0.680 |