Development and Validation of a Nomogram for Predicting Bronchopulmonary Dysplasia in Very Preterm Infants ≤32 Weeks

Read the full article See related articles

Discuss this preprint

Start a discussion What are Sciety discussions?

Listed in

This article is not in any list yet, why not save it to one of your lists.
Log in to save this article

Abstract

Background Bronchopulmonary dysplasia (BPD) remains the most common chronic lung disease in very preterm infants. This study aimed to develop and validate a nomogram for predicting BPD risk using data available by postnatal day 14. Methods This retrospective study analyzed data from 476 very preterm infants admitted to the neonatal intensive care unit (NICU) of the First Affiliated Hospital of Army Medical University in China between January 2015 and June 2025. The participants were randomly divided into a training cohort (n = 333) and a validation cohort (n = 143) at a ratio of 7:3. Based on the 2019 Jensen criteria, infants in the training cohort were categorized as non-BPD (n = 184) or BPD (n = 149), with the BPD group encompassing mild, moderate, and severe cases, as well as those with fatal severe respiratory disease. Least absolute shrinkage and selection operator (LASSO) regression was employed for predictor selection. Model performance was assessed for discrimination using the receiver operating characteristic (ROC) curve, calibration with calibration plots, and clinical utility via decision curve analysis. Results Six predictors were identified in the training cohort: birth weight, number of red blood cell transfusions, number of surfactant doses, fraction of inspired oxygen at postnatal day 14, neonatal respiratory distress syndrome, and duration of invasive ventilation. The nomogram demonstrated adequate discriminatory ability, with an area under the ROC curve of 0.810 (95% CI: 0.764–0.856) in the training cohort and 0.753 (95% CI: 0.671–0.835) in the validation cohort. Calibration curves and decision curve analysis supported the model's accuracy and clinical utility. An online tool was developed to facilitate clinical application (https://neo-care-predict.shinyapps.io/dynnomapp/ ). Conclusion This nomogram provides an accurate and individualized method for predicting BPD risk in very preterm infants by postnatal day 14, which may facilitate timely clinical interventions.

Article activity feed