Table 3 Amebiasis prediction results ± their standard deviation along the five runs of the fivefold cross-validation
From: Decision tree-based learning and laboratory data mining: an efficient approach to amebiasis testing
| Â | Accuracy | Precision | Recall | F1 score |
|---|---|---|---|---|
LR | 0.8911 (± 0.0159) | 0.8760 (± 0.0189) | 0.8555 (± 0.0198) | 0.8642 (± 0.0179) |
SGD | 0.7626 (± 0.1132) | 0.7851 (± 0.0492) | 0.7691 (± 0.0710) | 0.7298 (± 0.0992) |
SVM | 0.7067 (± 0.0283) | 0.3537 (± 0.0148) | 0.4994 (± 0.0012) | 0.4139 (± 0.0097) |
LSVM | 0.8641 (± 0.0452) | 0.8413 (± 0.0438) | 0.8658 (± 0.0256) | 0.8454 (± 0.0411) |
KNN | 0.7905 (± 0.0337) | 0.7465 (± 0.0578) | 0.7319 (± 0.0471) | 0.7378 (± 0.0514) |
HKNN | 0.8920 (± 0.0191) | 0.8682 (± 0.0311) | 0.8671 (± 0.0297) | 0.8674 (± 0.0299) |
DT | 0.936 (± 0.0179) | 0.937 (± 0.0250) | 0.936 (± 0.0271) | 0.936 (± 0.0257) |
RF | 0.9460 (± 0.0135) | 0.9330 (± 0.0171) | 0.9349 (± 0.0215) | 0.9337 (± 0.0189) |
AdaBoost | 0.9255 (± 0.0143) | 0.9120 (± 0.0128) | 0.9055 (± 0.0251) | 0.9082 (± 0.0194) |
GB | 0.9450 (± 0.0127) | 0.9323 (± 0.0174) | 0.9334 (± 0.0199) | 0.9326 (± 0.0178) |
NB | 0.7374 (± 0.0300) | 0.7040 (± 0.0200) | 0.5882 (± 0.0214) | 0.5833 (± 0.0375) |
MLP | 0.8938 (± 0.0188) | 0.8860 (± 0.0211) | 0.8478 (± 0.0436) | 0.8623 (± 0.0338) |
LDA | 0.8715 (± 0.0139) | 0.8476 (± 0.0149) | 0.8375 (± 0.0098) | 0.8420 (± 0.0112) |
XGBoost | 0.9385 (± 0.0116) | 0.9289 (± 0.0130) | 0.9196 (± 0.0227) | 0.9237 (± 0.0173) |