Related Experiment Video
Updated: Jul 25, 2025
Assessment and Evaluation of the High Risk Neonate: The NICU Network Neurobehavioral Scale
Published on: August 25, 2014
Two-stage learning-based prediction of bronchopulmonary dysplasia in very low birth weight infants: a nationwide
Jae Kyoon Hwang1, Dae Hyun Kim2, Jae Yoon Na1
1Department of Pediatrics, Hanyang University College of Medicine, Seoul, Republic of Korea.
Insights
This study developed advanced machine learning models to predict bronchopulmonary dysplasia (BPD) and its severity in very low birth weight (VLBW) infants. The models achieved high accuracy, offering valuable tools for neonatal intensive care units.
Area of Science:
- Neonatal Medicine
- Machine Learning in Healthcare
- Predictive Analytics
Background:
- Bronchopulmonary dysplasia (BPD) is a significant complication in very low birth weight (VLBW) infants.
- Accurate prediction of BPD and its severity is crucial for timely intervention and improved outcomes.
- Existing prediction models may not fully leverage the complexity of prenatal and early postnatal data.
Purpose of the Study:
- To develop and validate enhanced machine learning models for predicting BPD and its severity in VLBW infants.
- To integrate the duration of respiratory support (RSd) into a two-stage prediction framework.
- To identify key clinical variables influencing BPD development and severity.
Main Methods:
- Utilized a nationwide cohort of 16,384 VLBW infants from the Korean Neonatal Network (2013-2020).
- Employed multilayer perceptron (MLP)-based network analysis for model development, incorporating 45 prenatal and early perinatal variables.
- Compared prediction performance using Area Under the Receiver Operating Characteristic Curve (AUROC) and identified significant variables using the Shapley method.
Main Results:
- The developed PMbpd and two-stage TS-PMbpd models demonstrated superior predictive performance compared to conventional machine learning models across various BPD classifications (AUROC up to 0.897).
- Gestational age, birth weight, and patent ductus arteriosus treatment were key predictors for BPD occurrence.
- Birth weight, low blood pressure, intraventricular hemorrhage, and PDA ligation were significant for predicting severe BPD (BPD ≥2 or ≥3).
Conclusions:
- A novel two-stage machine learning model incorporating RSd was successfully developed for predicting BPD and its severity in VLBW infants.
- The model achieved high predictive accuracy, identifying significant clinical variables.
- This model can serve as an effective adjunctive tool in clinical neonatal intensive care unit settings.
Introduction:
The aim of this study is to develop an enhanced machine learning-based prediction models for bronchopulmonary dysplasia (BPD) and its severity through a two-stage approach integrated with the duration of respiratory support (RSd) using prenatal and early postnatal variables from a nationwide very low birth weight (VLBW) infant cohort.
Methods:
We included 16,384 VLBW infants admitted to the neonatal intensive care unit (NICU) of the Korean Neonatal Network (KNN), a nationwide VLBW infant registry (2013-2020). Overall, 45 prenatal and early perinatal clinical variables were selected. A multilayer perceptron (MLP)-based network analysis, which was recently introduced to predict diseases in preterm infants, was used for modeling and a stepwise approach. Additionally, we applied a complementary MLP network and established new BPD prediction models (PMbpd). The performances of the models were compared using the area under the receiver operating characteristic curve (AUROC) values. The Shapley method was used to determine the contribution of each variable.
Results:
We included 11,177 VLBW infants (3,724 without BPD (BPD 0), 3,383 with mild BPD (BPD 1), 1,375 with moderate BPD (BPD 2), and 2,695 with severe BPD (BPD 3) cases). Compared to conventional machine learning (ML) models, our PMbpd and two-stage PMbpd with RSd (TS-PMbpd) model outperformed both binary (0 vs. 1,2,3; 0,1 vs. 2,3; 0,1,2 vs. 3) and each severity (0 vs. 1 vs. 2 vs. 3) prediction (AUROC = 0.895 and 0.897, 0.824 and 0.825, 0.828 and 0.823, 0.783, and 0.786, respectively). GA, birth weight, and patent ductus arteriosus (PDA) treatment were significant variables for the occurrence of BPD. Birth weight, low blood pressure, and intraventricular hemorrhage were significant for BPD ≥2, birth weight, low blood pressure, and PDA ligation for BPD ≥3. GA, birth weight, and pulmonary hypertension were the principal variables that predicted BPD severity in VLBW infants.
Conclusions:
We developed a new two-stage ML model reflecting crucial BPD indicators (RSd) and found significant clinical variables for the early prediction of BPD and its severity with high predictive accuracy. Our model can be used as an adjunctive predictive model in the practical NICU field.
More Related Videos
05:50International Expert Consensus and Recommendations for Neonatal Pneumothorax Ultrasound Diagnosis and Ultrasound-guided Thoracentesis Procedure
Published on: March 12, 2020
06:15Protocol and Guidelines for Point-of-Care Lung Ultrasound in Diagnosing Neonatal Pulmonary Diseases Based on International Expert Consensus
Published on: March 6, 2019