A non-linear ensemble model-based surgical risk calculator for mixed data from multiple surgical fields

Table 3 Results of baseline models with top-15 risk factors

	Models	AUC	BS	\({\mathbf{HL}}_{{\hat{varvec{c}}}}\)	P-value
Training mode 1 (10-fold cross validation)	NL-SRC	0.892	0.063	8.082	0.426
	logit	0.864	0.068	13.561	0.094
	CART	0.841	0.069	25.614	0.001
	SVM	0.818	0.069	64.247	<0.001
Training mode 1 (6-fold cross validation)	NL-SRC	0.890	0.064	9.753	0.283
	logit	0.867	0.068	14.603	0.067
	CART	0.825	0.071	20.643	0.008
	SVM	0.820	0.071	55.271	<0.001
Training mode 2	NL-SRC	0.894	0.060	7.638	0.470
	logit	0.861	0.065	31.460	<0.001
	CART	0.856	0.064	16.088	0.041
	SVM	0.827	0.072	97.202	<0.001
Training mode 3	NL-SRC	0.869	0.066	17.062	0.030
	logit	0.863	0.067	75.033	<0.001
	CART	0.745	0.079	14.266	0.075
	SVM	0.856	0.071	72.822	<0.001

ISSN: 1472-6947