RESUMO
OBJECTIVES@#To construct risk prediction models for bronchopulmonary dysplasia (BPD) in preterm infants on postnatal days 3, 7, and 14.@*METHODS@#A retrospective analysis was performed on the medical data of 414 preterm infants, with a gestational age of <32 weeks and a birth weight (BW) of <1 500 g, who were admitted to the neonatal intensive care unit from July 2019 to April 2021. According to the diagnostic criteria for BPD revised in 2018, they were divided into a BPD group with 98 infants and a non-BPD group with 316 infants. The two groups were compared in terms of general status, laboratory examination results, treatment, and complications. The logistic regression model was used to identify the variables associated with BPD. The receiver operating characteristic (ROC) curve was used to evaluate the predictive value of models.@*RESULTS@#The logistic regression analysis showed that BW, asphyxia, grade III-IV respiratory distress syndrome (RDS), acute chorioamnionitis, interstitial pneumonia, fraction of inspired oxygen (FiO@*CONCLUSIONS@#BW, asphyxia, grade III-IV RDS, acute chorioamnionitis, interstitial pneumonia, FiO