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

Table 1 Results of baseline models with all risk factors

	Models	AUC	BS	\({\mathbf{HL}}_{{{\hat{\varvec{c}}}}}\)	P-value
Training mode 1 (10-fold cross validation)	NL-SRC	0.899	0.062	7.398	0.494
	logit	0.884	0.065	14.196	0.077
	CART	0.842	0.071	24.850	0.002
	SVM	0.866	0.065	27.490	<0.001
Training mode 1 (6-fold cross validation)	NL-SRC	0.897	0.062	8.798	0.360
	logit	0.883	0.065	13.879	0.085
	CART	0.826	0.070	16.848	0.031
	SVM	0.865	0.064	26.793	<0.001
Training mode 2	NL-SRC	0.902	0.058	8.391	0.396
	logit	0.890	0.059	12.427	0.133
	CART	0.853	0.065	11.321	0.184
	SVM	0.873	0.059	10.363	0.240
Training mode 3	NL-SRC	0.872	0.047	15.232	0.055
	logit	0.875	0.066	90.989	<0.001
	CART	0.781	0.077	12.146	0.145
	SVM	0.851	0.068	95.817	<0.001

ISSN: 1472-6947