One-year mortality prediction for patients with sepsis: a nomogram integrating lactic dehydrogenase and clinical characteristics

Table 3 Comparison of models in predicting the one-year mortality of sepsis patients

Models	Sets	Cut off	Sensitivity (95%CI)	Specificity (95%CI)	PPV (95%CI)	NPV (95%CI)	AUC (95%CI)	Accuracy (95%CI)
LDH-model	Training set	0.530	0.761 (0.732–0.791)	0.662 (0.624–0.700)	0.747 (0.717–0.777)	0.679 (0.641–0.716)	0.773 (0.748–0.798)	0.718 (0.695–0.742)
LDH-model	Testing set	0.530	0.751 (0.704–0.798)	0.619 (0.561–0.676)	0.703 (0.655–0.751)	0.673 (0.615–0.732)	0.750 (0.711–0.789)	0.691 (0.654–0.728)
SOFA	Training set	0.629	0.283 (0.252–0.314)	0.827 (0.796–0.857)	0.682 (0.631–0.732)	0.467 (0.437–0.498)	0.578 (0.548–0.608)	0.518 (0.492–0.544)
SOFA	Testing set	0.629	0.178 (0.137–0.220)	0.833 (0.789–0.878)	0.563 (0.467–0.659)	0.457 (0.413–0.501)	0.542 (0.495–0.588)	0.476 (0.436–0.516)
SAPS II	Training set	0.570	0.624 (0.591–0.658)	0.662 (0.624–0.700)	0.708 (0.674–0.742)	0.573 (0.536–0.610)	0.679 (0.651–0.707)	0.640 (0.615–0.666)
SAPS II	Testing set	0.570	0.594 (0.540–0.647)	0.630 (0.572–0.687)	0.659 (0.604–0.713)	0.563 (0.507–0.619)	0.653 (0.609–0.697)	0.610 (0.571–0.649)
LDH alone	Training set	0.556	0.525 (0.491–0.560)	0.603 (0.564–0.642)	0.635 (0.598–0.672)	0.492 (0.456–0.528)	0.576 (0.546–0.606)	0.559 (0.533–0.585)
LDH alone	Testing set	0.556	0.542 (0.487–0.596)	0.530 (0.470–0.589)	0.581 (0.525–0.636)	0.490 (0.432–0.547)	0.565 (0.519–0.611)	0.536 (0.496–0.576)

LDH-model: a predicting model integrating LDH and clinical features (including age, gender, ethnicity, potassium, calcium, albumin, hemoglobin, alkaline phosphatase, vasopressor, Elixhauser score, and respiratory failure)
LDH Lactic dehydrogenase, SOFA Sequential organ failure assessment, SAPS Simplified acute physiology score, PPV Positive predictive value, NPV Negative predictive value, AUC Area under the curve, CI Confidence interval

ISSN: 1471-2334