Related Experiment Video
Updated: Jul 16, 2026
Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
Published on: October 13, 2023
Clinical and Imaging Data-based Machine Learning for Early Diagnosis of Bronchopulmonary Dysplasia: A Meta-analysis
Yilin Chen1, Huixu Ma2, Xi Liu3
1Department of Thoracic Surgery, Chongqing General Hospital, Chongqing University, Chongqing 401147, China.
Insights
Machine learning models accurately predict bronchopulmonary dysplasia (BPD) in preterm infants ultra-early. This approach enables timely risk stratification, preceding traditional diagnosis by weeks.
Area of Science:
- Neonatal Medicine
- Artificial Intelligence in Healthcare
- Biostatistics
Background:
- Bronchopulmonary dysplasia (BPD) poses a significant challenge in preterm infant care.
- Early prediction of BPD is crucial for timely intervention and improved outcomes.
- Current diagnostic methods for BPD lack the speed required for immediate risk stratification.
Purpose of the Study:
- To evaluate the diagnostic performance of Machine Learning (ML) models for the early prediction of BPD in preterm infants.
- To assess the accuracy and potential of ML in identifying infants at high risk for BPD.
- To provide evidence for the clinical utility of ML in neonatal intensive care units.
Main Methods:
- A systematic meta-analysis of 9 studies involving 12,755 preterm infants.
- Data extraction and pooling using bivariate generalized linear mixed models.
- Assessment of study quality using the QUADAS-2 tool.
Main Results:
- ML models achieved high diagnostic accuracy (pooled sensitivity: 0.81, specificity: 0.85, AUC: 0.90).
- Multimodal and ensemble ML algorithms (e.g., Random Forest) showed superior performance.
- Models utilizing early postnatal data (first 7 days) outperformed those using later data (day 28).
Conclusions:
- Machine learning enables ultra-early prediction of BPD, weeks ahead of conventional diagnosis.
- ML-based prediction holds promise for clinical application in preterm infant care.
- Further prospective validation and cost-effectiveness analyses are necessary for widespread adoption.
Introduction:
This meta-analysis aimed to evaluate the diagnostic performance of Machine Learning (ML) models for early prediction of bronchopulmonary dysplasia (BPD) in preterm infants, addressing the need for timely risk stratification.
Methods:
Systematic searches of PubMed, Embase, and other databases identified 9 eligible studies (12,755 infants). Data were extracted and pooled using bivariate generalized linear mixed models. Study quality was assessed via QUADAS-2.
Results:
ML models demonstrated high accuracy (pooled sensitivity: 0.81, specificity: 0.85, AUC: 0.90). Multimodal models and ensemble algorithms (e.g., Random Forest) outperformed single-modality approaches. Models using data from the first 7 postnatal days achieved superior performance compared to those using data from day 28.
Discussion:
ML enables ultra-early BPD prediction, preceding conventional diagnosis by weeks. Heterogeneity in data modalities and validation strategies highlights the need for standardized reporting.
Conclusion:
ML-based BPD prediction shows promise for clinical translation but requires prospective validation and cost-effectiveness analysis.
More Related Videos
02:09Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
Published on: April 12, 2024
03:38Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models
Published on: June 20, 2025
