Table. 1.

Table 1 Discriminatory performances of LR and XGBoost

Location	Data set	Model	Predictor variables	AUROC (95% CI)	APS (95% CI)
GW	Training/validation set	LR	FS1	0.809 (0.796–0.823)	0.010 (0.008–0.012)
			FS2	0.867 (0.855–0.878)	0.011 (0.010–0.013)
			FS3	0.899 (0.890–0.908)	0.013 (0.012–0.016)
		XGBoost	FS1	0.969 (0.966–0.973)	0.107 (0.090–0.126)
			FS2	0.992 (0.991–0.993)	0.226 (0.199–0.252)
			FS3	0.993 (0.992–0.993)	0.201 (0.180–0.224)
	Test set	LR	FS1	0.795 (0.774–0.819)	0.008 (0.006–0.012)
			FS2	0.862 (0.842–0.881)	0.011 (0.009–0.015)
			FS3	0.876 (0.859–0.894)	0.013 (0.010–0.017)
		XGBoost	FS1	0.839 (0.817–0.859)	0.007 (0.006–0.010)
			FS2	0.925 (0.912–0.937)	0.026 (0.018–0.040)
			FS3	0.934 (0.923–0.944)	0.034 (0.024–0.050)
ICU	Training/validation set	LR	FS1	0.719 (0.703–0.735)	0.026 (0.022–0.030)
			FS2	0.785 (0.769–0.798)	0.030 (0.027–0.034)
			FS3	0.818 (0.806–0.831)	0.036 (0.032–0.041)
		XGBoost	FS1	1.000 (0.999–1.000)	0.946 (0.933–0.957)
			FS2	0.994 (0.993–0.995)	0.726 (0.700–0.755)
			FS3	1.000 (1.000–1.000)	0.978 (0.968–0.985)
	Test set	LR	FS1	0.729 (0.700–0.759)	0.026 (0.021–0.037)
			FS2	0.792 (0.769–0.815)	0.031 (0.025–0.038)
			FS3	0.816 (0.798–0.837)	0.035 (0.030–0.044)
		XGBoost	FS1	0.828 (0.803–0.850)	0.097 (0.073–0.135)
			FS2	0.878 (0.859–0.896)	0.115 (0.083–0.151)
			FS3	0.896 (0.875–0.917)	0.179 (0.142–0.228)

Data are AUROC and APS for three feature sets derived from the three-stage expansion of variable groups in the GW and the ICU.

Abbreviations: LR, logistic regression; XGBoost, eXtreme Gradient Boosting; AUROC, area under the ROC curve; CI, confidence interval; APS, average precision score; GW, general ward; FS1, feature set 1; FS2, feature set 2; FS3, feature set 3; ICU, intensive care unit.

Ann Lab Med 2025;45:209~217 https://doi.org/10.3343/alm.2024.0315