Retinal AI Predicts Neonatal Lung Disease
Retinal scans already performed in the NICU could flag infants at risk for serious lung disease before standard diagnosis
-
By
-
Conexiant News Staff
-
February 17, 2026
-
Clinical Scorecard: Retinal AI Predicts Neonatal Lung Disease
At a Glance
| Category | Detail |
|---|
| Condition | Bronchopulmonary Dysplasia and Pulmonary Hypertension in Premature Infants |
| Key Mechanisms | Deep learning models analyzing retinal images to predict cardiopulmonary disease. |
| Target Population | Premature infants, particularly those screened for retinopathy of prematurity. |
| Care Setting | Neonatal Intensive Care Units (NICUs) |
Key Highlights
- Deep learning models can predict bronchopulmonary dysplasia and pulmonary hypertension from retinal images.
- Multimodal models combining imaging and demographic data outperformed single-modality models.
- The study utilized data from the i-ROP study, focusing on infants at 34 weeks' postmenstrual age or less.
Guideline-Based Recommendations
Diagnosis
- Use retinal imaging as a predictive tool for bronchopulmonary dysplasia and pulmonary hypertension.
Management
- Consider integrating retinal imaging into routine screening protocols for at-risk infants.
Monitoring & Follow-up
- Monitor infants with abnormal retinal findings for potential cardiopulmonary complications.
Risks
- Be aware of limitations in model performance across different imaging devices and settings.
Patient & Prescribing Data
Infants enrolled in the i-ROP study, particularly those with gestational age and birth weight data.
Retinal imaging may provide a non-invasive method to identify infants at risk for severe lung disease.
Clinical Best Practices
- Incorporate retinal imaging into standard care for premature infants.
- Utilize multimodal predictive models for better diagnostic accuracy.
References
