Retinal AI Predicts Neonatal Lung Disease - Takeaways - MDSpire

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 models using retinal images can predict bronchopulmonary dysplasia and pulmonary hypertension in premature infants.

  • 2

    The study utilized images from the i-ROP study, focusing on infants at 34 weeks' post-menstrual age or less.

  • 3

    The multimodal model combining retinal images and demographic factors outperformed models using either data type alone for bronchopulmonary dysplasia.

  • 4

    For pulmonary hypertension, the imaging-only model achieved a high AUC of 0.91, indicating strong diagnostic capability.

  • 5

    The findings suggest potential for retinal imaging in identifying high-risk infants for cardiopulmonary complications in clinical settings.

Original Source(s)

Retinal AI Predicts Neonatal Lung Disease

  • March 16, 2026

Related Content

Six Patient Journey Marketing Strategies That Drive Growth and Profitability

Thomas Nydegger of Refractive MD Growth explains that although different stages along the patient journey can each stand on their own, they must support each other for a practice to succeed.

  • April 11, 2026

  • 5 min
Early Insights Into Home OCT Monitoring Reveal Real-World Impact

In our conversation, which has been edited for length and clarity, Kapil Kapoor, MD, a vitreoretinal surgeon and president of research at the Wagner Kapoor Institute, discussed the reasons his practice was an early adopter of home OCT and described the experiences of implementing the program for both patients and team members.

DIMS Wear Linked to Slower Axial Growth

Nearly 10 years of observational follow-up suggested sustained axial-length slowing, although refractive findings were less consistent and comparisons relied on statistical modeling.