Nomogram predictive model for in-hospital mortality risk in elderly ICU patients with urosepsis

BMC Infectious Diseases

Table 3 Predictive performances and validation of the nomogram

Predictive model	AUC	P	NRI	P	IDI	P
Training set
Nomogram	0.748(0.708–0.785)
SAPS-II	0.693(0.649–0.741)	< 0.001	0.125(0.047–0.203)	< 0.001	0.043(0.012–0.073)	< 0.001
APACHE-II	0.667(0.621–0.716)	< 0.001	0.057(0.018–0.096)	0.004	0.059(0.030–0.087)	< 0.001
SOFA	0.708(0.678–0.761)	< 0.001	0.138(0.044–0.232)	0.004	0.051(0.023–0.079)	< 0.001
Validation set
Nomogram	0.789(0.720–0.832)
SAPS-II	0.686(0.615–0.759)	< 0.001	0.266(0.155–0.376)	< 0.001	0.078(0.028–0.129)	0.002
APACHE-II	0.656(0.588–0.732)	< 0.001	0.096(0.021–0.171)	0.012	0.107(0.057–0.158)	< 0.001
SOFA	0.735(0.680–0.794)	< 0.001	0.142(0.007–0.276)	0.038	0.088(0.039–0.138)	< 0.001

Abbreviations: AUC, area under the receiver operating characteristic curve; NRI, net reclassification improvement; IDI, integrated discrimination improvement; SAPS-II, Simplified Acute Physiologic Score-II; SOFA, Sequential Organ Failure Assessment; APACHE-II, Acute Physiology and Chronic Health Evaluation-II.

ISSN: 1471-2334