Clinical Guidelines

Retinal AI Predicts Neonatal Lung Disease

AI models trained on routine ROP images identify bronchopulmonary dysplasia and pulmonary hypertension in premature infants

  • March 16, 2026

  • 4 min

Share

Deep learning models utilizing retinal images from routine retinopathy of prematurity (ROP) screenings have shown promise in predicting bronchopulmonary dysplasia and pulmonary hypertension in premature infants, as highlighted in a JAMA Ophthalmology study. Researchers analyzed fundus photographs from infants in the i-ROP study, finding that multimodal models combining both imaging data and demographic factors outperformed individual approaches. Despite limitations, such as small cohort sizes and potential confounding variables, the findings suggest retinal imaging may be a valuable tool for early identification of cardiopulmonary risks in neonatology.

Original Source(s)

Retinal AI Predicts Neonatal Lung Disease

  • March 16, 2026

Related Content

Teen Conflict and the Body’s Clock

Parent and peer relationship patterns across adolescence are examined alongside biomarkers of aging.

FDA Approves Secukinumab for Adolescents With Moderate to Severe Hidradenitis Suppurativa

Secukinumab becomes the only interleukin-17A inhibitor approved for pediatric patients aged 12 years and older with moderate to severe hidradenitis suppurativa.

Older RSV Hospitalization Linked to Pneumonia

Large Swedish cohort study finds children hospitalized for respiratory syncytial virus at older ages have greater risk of subsequent bacterial pneumonia