Related Experiment Video
Updated: Aug 11, 2026
Assessment and Evaluation of the High Risk Neonate: The NICU Network Neurobehavioral Scale
Published on: August 25, 2014
Development and Internal Validation of a Neonatal Outcomes Prediction Score and Model for Neonates at 22-29 Weeks'
Prakesh S Shah1, Soutrik Seth1, Seungwoo Lee1
1Department of Paediatrics, Mount Sinai Hospital and University of Toronto, Toronto, Ontario, Canada.
Objective:
To develop and internally validate models and severity scores at days 7, 14, and 28 to predict death, major morbidity, and bronchopulmonary dysplasia (BPD) in infants born at 22-29 weeks' gestation.
Study Design:
This retrospective cohort study included infants admitted to Canadian neonatal intensive care units (2010-2023) and used 16 predefined baseline, intervention, and morbidity variables to develop prediction models and the Neonatal Outcomes Prediction Score (NOPS) at days 7, 14, and 28. Infants transferred to level 2 units before model age were excluded.
Results:
We studied 26 719 infants born at 22-29 weeks' gestation (median gestational age, 27 weeks; median birth weight, 980 g). Eleven variables for outcome of death, 8 for death/major morbidity, 7 for death/BPD, and 8 for death/moderate-to-severe BPD were associated with respective outcomes in 3 time-based models. The models were internally valid. The area under the curve was ≥0.85 for death, ≥0.80 for death/major morbidity, ≥0.78 for death/BPD, and ≥0.76 for death/moderate-to-severe BPD at all time points. The NOPS derived from these models showed that a score >30 was significantly associated with all 3 outcomes, with ORs ≥8.3 at all time points.
Conclusions:
Internally valid and accurate models for neonatal outcome prediction in the first postnatal weeks were generated, including static variables, exposed interventions, and accumulated morbidities. A NOPS >30 was significantly associated with all 4 outcomes at all time points. The models require external validation.