Table 2.

Comparison of the performance of two models for predicting SAE.

Predict model		AUROC	P-value	NRI (categorical)	P-value	NRI (continuous)	P-value	IDI	P-value
Training set	Nomogram	0.751
	SOFA + Delirium	0.725	<0.001	0.0493[0.0177–0.0808]	0.002	0.3484[0.278–0.4189]	<0.001	0.0279[0.0194–0.0364]	<0.001
Validation set	Nomogram	0.766
	SOFA + Delirium	0.742	0.008	0.0504[0.0042–0.0965]	0.03	0.3814[0.2731–0.4897]	<0.001	0.0268[0.0139–0.0397]	<0.001

The P-value was calculated by comparing the results of nomogram with SOFA plus Delirium. SOFA, Sequential Organ Failure Assessment; AUROC, Area Under the ROC Curve; NRI, Net Reclassification Improvement; IDI, Integrated Discrimination Improvement.