Risk calculator for advanced neonatal resuscitation.

Area of Science:

• Neonatal medicine
• Perinatal research
• Clinical prediction models

Background:

• Predicting the need for advanced respiratory support (ANR) in newborns is crucial for timely intervention.
• Existing prediction methods may not fully capture all risk factors, especially those emerging during the perinatal period.

Purpose of the Study:

• To develop and validate a predictive model for identifying newborns requiring advanced respiratory support (ANR).
• To assess the utility of incorporating perinatal variables into ANR risk prediction.

Main Methods:

• A case-control study utilizing a bootstrap sample of 52,973 newborns (≥34 weeks gestation).
• Multivariable logistic regression was employed to identify significant risk factors and interaction terms.
• Model performance was evaluated using the area under the receiver-operating characteristic curve (AUC).

Main Results:

• The developed ANR risk calculator demonstrated high predictive accuracy with an AUC of 0.9243.
• The model identified 10 original risk factors and two interaction terms as significant predictors.
• Incorporating perinatal variables significantly improved ANR prediction compared to prenatal factors alone.

Conclusions:

• The ANR risk calculator offers a robust tool for predicting the need for advanced respiratory support in newborns.
• Accounting for perinatal variables enhances predictive accuracy, offering a more comprehensive risk assessment.
• Prospective clinical validation of this model is recommended to confirm its utility in practice.