Personalized lung care: “Bronchopulmonary Dysplasia Risk Prediction Tool Tailored for Neonates Born in the Resource-limited Settings.”

Purpose: Predicting Bronchopulmonary dysplasia (BPD) to assess the risk-benefit of the therapy is necessary due to the side effects of medications. We developed and validated an instrument for predicting BDP and compared it with an instrument currently used in neonates born in a Brazilian hospital. Methods: Retrospective cohort of patients born between 2016 and 2020, with gestational ages (GA) between 23 and 30 weeks. Predictive equations were elaborated using methods of selection of component variables: stepwise, conditional inference tree, Fisher’s exact test and all the collected variables; 70% of the sample was randomly selected for the construction of risk prediction equations, and the remaining 30% were used for their validation, application and comparison with the National Institute of Child Health and Human Development (NICHD) instrument published in 2011, currently used in that institution. Sensitivity, specificity, and predictive values of the equations were calculated. Results: The equation that used variables whose p-value was lower than 5% in Fisher’s exact test (clinical chorioamnionitis, GA, birth weight, sex, need for surfactant, patent ductus arteriosus, late-onset sepsis, inspired fraction of oxygen, and respiratory support) presented the best results: specificity of 98% and positive predictive value of 93%. Our instrument allowed applying the prediction to small-for-gestational-age (SGA). The currently used calculator applied to our population had a specificity of 93% and a positive predictive value of 75% and could not be applied to SGA patients. Conclusion: Our tool has a higher specificity and positive predictive value than the foreign instrument and is suited for SGA.