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

Table 2 Results of similar 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
	RF	0.885	0.064	10.426	0.236
	XGBoost	0.895	0.062	13.026	0.111
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
	RF	0.885	0.064	12.818	0.118
	XGBoost	0.896	0.063	10.968	0.204
Training mode 2	NL-SRC	0.902	0.058	8.391	0.396
	logit	0.890	0.059	12.427	0.133
	RF	0.892	0.058	14.226	0.058
	XGBoost	0.900	0.056	9.439	0.306
Training mode 3	NL-SRC	0.872	0.047	15.232	0.055
	logit	0.875	0.066	90.989	<0.001
	RF	0.879	0.067	11.522	0.174
	XGBoost	0.886	0.067	27.285	<0.001

ISSN: 1472-6947