Related Experiment Video
Updated: Jan 8, 2026
08:58
Development of a Neonatal Piglet Acute Lung Injury Model Recreating the Early Environment of Preterm Infant Lungs
Published on: October 31, 2025
506
Enhancing bronchopulmonary dysplasia prediction in preterm infants using artificial intelligence and multimodal data
Xinkai Zhang1,2, Anping Wang3, Rongwei Xu1,2
1Qingdao Medical College, Qingdao University, Qingdao, China.
Frontiers in Pediatrics
|December 22, 2025
Summary
Artificial intelligence (AI) and machine learning (ML) offer promising tools for predicting bronchopulmonary dysplasia (BPD) in preterm infants using multimodal data. Addressing challenges in clinical translation is key to moving AI from risk prediction to precise intervention for improved infant outcomes.
Area of Science:
- Medical Informatics
- Neonatology
- Artificial Intelligence
Background:
- Bronchopulmonary dysplasia (BPD) is a common respiratory condition in preterm infants, influenced by various perinatal and postnatal factors.
- Multimodal data, including clinical, physiological, imaging, biomarker, and omics data, are crucial for understanding and predicting BPD.
- Artificial intelligence (AI) and machine learning (ML) are emerging as powerful tools for developing sophisticated BPD prediction models.
Purpose of the Study:
- To systematically review the research progress of AI in predicting bronchopulmonary dysplasia (BPD).
- To analyze representative AI models and tools for BPD prediction, evaluating their clinical performance and limitations.
- To identify challenges hindering the clinical translation of AI models in BPD management.
Main Methods:
- Systematic literature review of AI and ML applications in BPD prediction.
- Analysis of multimodal data sources used in AI-driven BPD prediction models.
- Evaluation of existing BPD prediction tools, such as the RTI BPD Outcome Estimator.
- Discussion of the PALM (Predict-Act-Learn-Monitor) framework for AI translation in clinical practice.
Main Results:
- AI and ML models show potential for BPD prediction using diverse datasets.
- Current AI models face challenges in clinical translation, including data standardization, interpretability, and integration.
- The PALM framework offers a structured approach to bridge the gap between AI prediction and clinical intervention.
Conclusions:
- AI holds significant promise for improving BPD risk prediction and guiding clinical interventions.
- Overcoming challenges in data sharing, privacy (e.g., federated learning), and regulatory frameworks is essential for clinical adoption.
- Developing a closed-loop management system for AI models is crucial for transitioning from prediction to precise, outcome-improving interventions for infants with BPD.
