Table 3.

Model performance in the training, internal and external validation sets for in-hospital mortality.

Test Sets	Statistics	Lasso LR	Elastic net LR	XGBoost
Training	Sensitivity (95% CI)	0.12 (0.06,0.22)	0.12 (0.06,0.22)	0.99 (0.93,1.0)
	Specificity (95% CI)	0.99 (0.98,1.0)	0.99 (0.98,1.0)	1.0 (0.99,1.0)
	AUC (95% CI)	0.76 (0.71,0.81)	0.78 (0.73,0.83)	1.0 (1.0,1.0)
Internal validation	Sensitivity (95% CI)	0.05 (0.01,0.17)	0.10 (0.03,0.23)	0.37 (0.22,0.53)
	Specificity (95% CI)	0.98 (0.95,0.99)	0.98 (0.95,0.99)	0.89 (0.84,0.93)
	AUC (95% CI)	0.68 (0.59,0.77)	0.72 (0.64,0.81)	0.67 (0.59,0.76)
External validation	Sensitivity (95% CI)	0.11 (0.06,0.16)	0.22 (0.16,0.28)	0.50 (0.42,0.57)
	Specificity (95% CI)	0.99 (0.97,1.0)	0.97 (0.94,0.99)	0.93 (0.89,0.97)
	AUC (95% CI)	0.83 (0.78,0.87)	0.85 (0.81,0.89)	0.77 (0.72,0.82)

The cutoff threshold to determine sensitivity and specificity was 0.5