Objectives: Illness severity scores for newborns are complex and restricted by birth weight and have dated validations and calibrations. We developed and validated simplified neonatal illness severity and mortality risk scores. The primary outcome was in-hospital mortality.
Study design: Thirty neonatal intensive care units in Canada, California, and New England collected data on all admissions during the mid 1990s; patients moribund at birth or discharged to normal newborn care in <24 hours were excluded. Starting with the 34 data elements of the Score for Neonatal Acute Physiology (SNAP), we derived the most parsimonious logistic model for in-hospital mortality using 10,819 randomly selected Canadian cases. SNAP-II includes 6 physiologic items; to this are added points for birth weight, low Apgar score, and small for gestational age to create a 9-item SNAP-Perinatal Extension-II (SNAPPE-II). We validated SNAPPE-II on the remaining 14,610 cases and optimized the calibration.
Results: In all birth weights, SNAPPE-II had excellent discrimination and goodness of fit. Area under the receiver operator characteristic curve was .91 +/- 0.01. Goodness of fit (Hosmer-Lemeshow) was 0.90.
Conclusions: SNAP-II and SNAPPE-II are empirically validated illness severity and mortality risk scores for newborn intensive care. They are simple, accurate, and robust across populations.