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

Table 4 The experimental results in the public dataset

Classifiers	Accuracy	Precision	Recall	Average F1
LR	0.8881	0.8053	0.7729	0.7847
NB	0.7198	0.6616	0.7439	0.7003
SVM	0.9315	0.8992	0.8621	0.8782
BP	0.9210	0.8680	0.8393	0.8514
RF	0.8949	0.8743	0.7170	0.7718
XGB	0.9314	0.9070	0.8610	0.8794
Proposed strategy	0.9539	0.9354	0.9167	0.9249

ISSN: 1472-6947