Development of a novel tool: a nomogram for predicting in-hospital mortality of patients in intensive care unit after percutaneous coronary intervention

Table 3 Comparison of different models in predicting the in-hospital mortality of patients after PCI

	Predictive Model	AUROC	p value	IDI	p value	NRI	p value
Training set	nomogram	0.907 [0.880-0.933]
	SOFA	0.790 [0.746-0.835]	< 0.001	0.181 [0.139-0.224]	< 0.001	0.964 (0.645-1.227)	< 0.001
	SASP II	0.813 [0.772-0.855]	< 0.001	0.176 [0.126-0.226]	< 0.001	0.663 (0.435-1.029	< 0.001
Validation set	nomogram	0.901 [0.865-0.936]
	SOFA	0.822 [0.774-0.870]	< 0.001	0.191 [0.131-0.251]	< 0.001	0.848 (0.405-1.194)	< 0.001
	SASP II	0.822 [0.768-0.876]	< 0.001	0.152 [0.087-0.217]	< 0.001	0.601 (0.196-1.032)	< 0.001

The p value of IDI and NRI were calculated by comparing the nomogram with SOFA or SAPS II
PCI percutaneous coronary intervention, SOFA Sequential Organ Failure Assessment, AUROC area under the receiver operating characteristic curve, IDI integrated discrimination improvement, NRI net reclassification improvement

ISSN: 1471-2253