Related Experiment Video
Updated: Jan 8, 2026
Development of a Neonatal Piglet Acute Lung Injury Model Recreating the Early Environment of Preterm Infant Lungs
Published on: October 31, 2025
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.
Insights
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.
Abstract:
Bronchopulmonary dysplasia (BPD) remains a prevalent respiratory condition among preterm infants, with its development influenced by a combination of perinatal and postnatal factors. The development of artificial intelligence (AI) and machine learning (ML) technologies has provided new ideas for building BPD prediction models based on multimodal data (such as clinical information, physiological signals, imaging data, biomarkers, and omics data). This article systematically reviewed the research progress of AI in BPD prediction, analyzed representative models and key tools (such as RTI BPD Outcome Estimator), and assessed their performance and limitations in actual clinical settings. It also sorted out the challenges faced by AI models in clinical translation, including data standardization, model interpretability, system integration capabilities, model update mechanisms, and ethical and legal issues. To address the clinical need of "moving from prediction to intervention", this article discussed the PALM translation framework (Predict-Act-Learn-Monitor) organized around key clinical nodes. In the future, it is necessary to strengthen multi-center data sharing, develop privacy protection technologies such as federated learning, and build a design, validation, integration, regulation, and feedback closed-loop management system to help AI models move from risk prediction to precise intervention, ultimately improving the clinical outcomes of children with BPD.
