RESUMO

PURPOSE: Predicting bronchopulmonary dysplasia (BPD) to assess the risk-benefit of therapy is necessary considering the side effects of medications. We developed and validated an instrument for predicting BPD and compared it with an instrument currently used for neonates born in a Brazilian hospital. METHODS: This was a retrospective cohort study of patients born between 2016 and 2020 with a gestational age (GA) between 23 and 30 weeks. Predictive equations were elaborated using methods of component variable selection collected on the 14th day of life; 70% of the sample was randomly selected for the construction of risk prediction equations and the remaining 30% for their validation, application, and comparison with the National Institute of Child Health and Human Development (NICHD) instrument. The sensitivity, specificity, and predictive values of the equations were calculated. RESULTS: The equation that used variables with p < 5% in Fisher's exact test presented the best results: specificity of 98% and positive predictive value of 93% and could be used for BPD prediction of all small-for-gestational-age (SGA) infants. The NICHD calculator applied to our population had a specificity of 93% and a positive predictive value of 75% and could not be applied to extremely SGA infants. CONCLUSION: Our tool can predict the risk of BPD on the 14th day of life, has higher specificity and positive predictive value to our population than the NICHD instrument, and can be suitable for SGA infants. The results must be confirmed by applying it to other populations to validate our tool.