Abstract
BACKGROUND: Despite the advances in neonatology, the incidence of bronchopulmonary dysplasia (BPD) is increasing. It is important to prevent the development of BPD in the first place. The online BPD outcome estimator from National Institute of Children Health and Human Development and Neonatal Research Network is available. However, it is not applicable for Asians. Moreover, limits are set for birth weight and gestational weeks excluding those who may still have BPD. The aim of this study was to develop a prediction model for BPD using first hour perinatal and neonatal factors in Korean very low birth weight infants (VLBWIs). METHODS: Data were collected for 8,022 VLBWIs with gestational age (GA) ≥ 22 weeks who were born between January 1, 2013 and December 31, 2016, and admitted to the neonatal intensive care units of the KNN. Multiple logistic regression models reanalyzed by stepwise selection with significant clinical indicators for BPD. PROC package was used to calculate the area under curve (AUC) and corresponding 95% confidence intervals. Moreover, it was used to search the best cut-off value. External validation was performed with the 2017 Korean neonatal network (KNN) data. RESULTS: After all missing data were excluded, 4,600 VLBWIs were included in the training dataset of the prediction model. Predictability of presence of BPD was 90.8% and prediction P value cut off was 0.550. Five-minute Apgar score, birth weight, GA, sex, surfactant use were significant indicators. Predictability of severe BPD was 81.5% and prediction P value cut off was 0.160. Five-minute Apgar score, birth weight, maternal PIH, chronic maternal hypertension, GA, sex, respiratory distress syndrome, need of resuscitation at birth were significant indicators. After external validation, sensitivity and specificity did not change significantly. CONCLUSION: From this study, high predictability was obtained using clinical parameters obtained within one hour of life. P value for prediction of each grade of BPD and equation for calculation was presented. It can be helpful for the early prediction of BPD in Korean VLBWI. This study will contribute to the prediction of BPD in Asians especially Korean VLBWIs, not currently included in the NICHD BPD online BPD predictor. In addition, the predictive power may be continuously increased with the cumulative data of KNN.