Bronchopulmonary dysplasia prediction model for 7-day-old infants

Carlos A Bhering1, Christieny C Mochdece, Maria E L Moreira

  • 1Universidade Severino Sombra, Vassouras, RJ, Brazil.

Jornal De Pediatria
|March 24, 2007
PubMed

Insights

A new predictive model can identify premature infants at high risk for bronchopulmonary dysplasia (BPD) within the first week of life. This model uses key factors like gestational age and birth weight loss to accurately predict BPD development.

Area of Science:

  • Neonatal Medicine
  • Pediatric Pulmonology
  • Clinical Prediction Modeling

Background:

  • Bronchopulmonary dysplasia (BPD) is a significant complication in premature infants.
  • Early identification of infants at risk for BPD is crucial for timely intervention.

Purpose of the Study:

  • To develop and validate a predictive model for identifying premature infants at high risk of developing BPD.
  • The model assesses risk at the end of the infant's first week of life.

Main Methods:

  • Retrospective and prospective data collection from infants with gestational age < 34 weeks and birth weight < 1,500 g.
  • Univariate analysis and logistic regression identified key risk factors.
  • A predictive formula was constructed and validated on an independent cohort using ROC curves.

Main Results:

  • The final model included gestational age ≤ 30 weeks, persistent ductus arteriosus, mechanical ventilation > 2 days, and > 15% birth weight loss by day 7.
  • The model achieved 93.7% accuracy when all four variables were present.
  • Validation on a separate cohort confirmed similar predictive performance.

Conclusions:

  • The developed predictive model effectively identifies premature infants at increased risk for BPD.
  • High sensitivity in predicting BPD risk is achieved by the end of the first week of life.
Abstract