A hybrid stacked ensemble and Kernel SHAP-based model for intelligent cardiotocography classification and interpretability

Table 5 The experimental results in the private dataset

Classifiers	Accuracy	Precision	Recall	Average F1
LR	0.8936	0.8737	0.8403	0.8548
NB	0.8481	0.8257	0.7546	0.7792
SVM	0.9125	0.8903	0.8781	0.8839
BP	0.9137	0.8920	0.8797	0.8856
RF	0.9054	0.9063	0.8402	0.8663
XGB	0.9130	0.8947	0.8737	0.8834
Proposed strategy	0.9201	0.9056	0.8816	0.8926

ISSN: 1472-6947