Table 3 Performance of XGB_AP2D classifier with different SkFoldCV split values on train set with standard deviation across folds and the same metrics evaluated with an external validation set
Internal validation | A | SE | SP | P | F1 |
|---|---|---|---|---|---|
S5FoldCV | 0.91 ± 0.01 | 0.90 ± 0.02 | 0.91 ± 0.01 | 0.90 ± 0.01 | 0.90 ± 0.01 |
S10FoldCV | 0.91 ± 0.01 | 0.90 ± 0.02 | 0.92 ± 0.02 | 0.93 ± 0.02 | 0.91 ± 0.02 |
S15FoldCV | 0.91 ± 0.02 | 0.90 ± 0.03 | 0.92 ± 0.02 | 0.91 ± 0.03 | 0.91 ± 0.03 |
External validation | 0.91 | 0.88 | 0.93 | 0.91 | 0.90 |