Establishment and Validation of a Risk Prediction Model for Non-Invasive Ventilation Failure After Birth in Premature Infants with Gestational Age < 32 Weeks.

OBJECTIVES

This study was performed to construct and validate a risk prediction model for non-invasive ventilation (NIV) failure after birth in premature infants with gestational age < 32 weeks.

METHODS

The data were derived from the multicenter retrospective study program - Jiangsu Provincial Neonatal Respiratory Failure Collaboration Network from Jan 2019 to Dec 2021. The subjects finally included were preterm infants using NIV after birth with gestational age less than 32 weeks and admission age within 72 h. After screening by inclusion and exclusion criteria, 1436 babies were subsequently recruited in the study, including 1235 infants in the successful NIV group and 201 infants in the failed NIV group.

RESULTS

(1) Gestational age, 5 min Apgar, Max FiO during NIV, and FiO fluctuation value during NIV were selected by univariate and multivariate analysis. (2) The area under the curve of the prediction model was 0.807 (95% CI: 0.767-0.847) in the training set and 0.825 (95% CI: 0.766-0.883) in the test set. The calibration curve showed good agreement between the predicted probability and the actual observed probability (Mean absolute error = 0.008 for the training set; Mean absolute error = 0.012 for the test set). Decision curve analysis showed good clinical validity of the risk model in the training and test cohorts.

CONCLUSION

This model performed well on dimensions of discrimination, calibration, and clinical validity. This model can serve as a useful tool for neonatologists to predict whether premature infants will experience NIV failure after birth.