Prediction of clinical pregnancy after frozen embryo transfer based on ultrasound radiomics: an analysis based on the optimal periendometrial zone

Table 3 Performance of the six ML Models in the training and external validation set

	Model	AUC (95% CI)	Accuracy	Sensitivity	Specificity
Training set	LR	0.628 (0.570–0.684)	0.657	0.853	0.391
	SVM	0.641 (0.580–0.694)	0.629	0.616	0.647
	RF	0.772 (0.723–0.818)	0.689	0.607	0.801
	DT	0.716 (0.669–0.766)	0.673	0.81	0.487
	KNN	0.744 (0.692–0.792)	0.689	0.664	0.724
	BPNN	0.744 (0.691–0.794)	0.703	0.716	0.686
External validation set	LR	0.633 (0.479–0.783)	0.618	0.892	0.29
	SVM	0.616 (0.472–0.753)	0.574	0.73	0.387
	RF	0.683 (0.527–0.821)	0.676	0.649	0.71
	DT	0.685 (0.561–0.802)	0.676	0.973	0.323
	KNN	0.548 (0.415–0.677)	0.515	0.568	0.452
	BPNN	0.715 (0.581–0.833)	0.647	0.595	0.71

AUC Area under the curve, ML machine learning, CI confidence interval, LR logistic regression, SVM support vector machine, RF random forest classifier, DT decision tree classifier, KNN k-nearest neighbor classifier, BPNN Back Propagation Neural Network

ISSN: 1471-2393