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

  • 1

    Deep learning can predict bronchopulmonary dysplasia and pulmonary hypertension from retinal images.

  • 2

    Study published in JAMA Ophthalmology.

  • 3

    Utilized images from premature infants in the i-ROP study.

  • 4

    Multimodal models outperformed single-factor models.

  • 5

    AUC for pulmonary hypertension was 0.91 with imaging-only model.

  • 6

    Findings generate hypotheses about retinal changes in disease.

  • 7

    Limited by small cohort sizes and lack of external validation.

  • 8

    Retinal imaging could support early identification of cardiopulmonary risks.

Original Source(s)

Retinal AI Predicts Neonatal Lung Disease

  • March 16, 2026

Related Content

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

More Pediatric ER Visits for Tooth Pain

Dentists link rising pediatric ER visits to workforce shortages, worsening oral hygiene, and policy shifts that could further limit preventive care.