Researchers have found that artificial intelligence (AI) can help identify serious lung and heart complications in premature infants by analysing images already collected during routine eye screenings for retinopathy of prematurity (ROP).
The study, published in JAMA Ophthalmology,1 demonstrated that AI could detect signs of bronchopulmonary dysplasia (BPD) and pulmonary hypertension (PH) from retinal images.
BPD and PH are complications that are major causes of illness and death in premature babies and often require invasive diagnostic testing.
The study evaluated 493 premature infants across seven neonatal intensive care units (NICUs).
AI predicted risk of BPD with 82% accuracy and PH with 91% accuracy.
Eye imaging is already standard care for screening ROP, meaning this approach may not require additional procedures.
Identifying Vulnerable Babies Earlier
“Artificial intelligence allows us to detect subtle patterns in retinal images that are not visible to the human eye,” said Dr Praveer Singh, assistant professor of ophthalmology at the University of Colorado Anschutz and study lead author.2
“This opens the possibility of using a simple photograph to gain insights into a premature infant’s overall health.”
Importantly, results remained consistent even when researchers excluded images showing clinical signs of ROP, suggesting the AI model identified information beyond traditional eye disease markers.
“Premature and low birthweight babies undergo frequent eye imaging to screen for ROP,” said Professor Jayashree Kalpathy-Cramer, also from CU Anschutz.2 “Our findings suggest that information about a baby’s lung and heart health may already be present in these images routinely collected in neonatal care. Earlier detection could make a meaningful difference in outcomes and treatment planning.”
The researchers said AI-assisted screening could eventually help clinicians identify vulnerable infants earlier and guide decisions about monitoring and treatment. While the findings are promising, investigators emphasised that further validation studies are needed before the technology could be integrated into routine clinical care.
References
- Singh P, Kumar S, Kalpathy-Cramer J et al. Deep learning-based prediction of cardiopulmonary disease in retinal images of premature infants. JAMA Ophthalmol. 2026 Jan 22:e255814. doi: 10.1001/jamaophthalmol.2025.5814. Epub ahead of print.
- Pieters K, AI analysis of eye photos may help detect serious lung and heart conditions in premature infants, University of Colorado Anschutz News, available at: news.cuanschutz.edu/news-stories/ai-analysis-of-eye-photos-may-help-detect-serious-lung-and-heart-conditions-in-premature-infants [accessed March 2026].
