Deep Learning-Based Prediction of Cardiopulmonary Disease in Retinal Images of Premature Infants.

Praveer Singh; Sourav Kumar; Riya Tyagi; B. Kay Young; Brian K. Jordan; Brian Scottoline; Patrick D. Evers; Susan Ostmo; Aaron S Coyner; Wei-Chun Lin; Aarushi Gupta; Deniz Edogmus; R V Paul Chan; Emily A. McCourt; James Barry; Cindy T. McEvoy; Susan Ostmo; J Peter Campbell; Jayashree Kalpathy-Cramer

doi:10.1001/jamaophthalmol.2025.5814

Key Points

This research aims to explore the potential of using retinal images for predicting cardiopulmonary disease in preterm infants.
Analyzed retinal images from premature infants during ROP screening
Applied deep learning algorithms to interpret the images
Examined correlations between retinal features and diagnoses of BPD and PH
Retinal images were effective in predicting the diagnosis of BPD
Retinal images successfully predicted PH
Utilizing these images may reduce the need for invasive diagnostic tests

Implication

Researchers find retinal images can predict cardiopulmonary disease in premature infants, suggesting earlier interventions.

Abstract

Results suggest that retinal images obtained during ROP screening may be used to predict the diagnosis of BPD and PH in preterm infants, which may lead to earlier diagnosis and avoid the need for invasive diagnostic testing in the future.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Singh et al. (2026) studied this question.

synapsesocial.com/papers/697460acbb9d90c67120a93d https://doi.org/10.1001/jamaophthalmol.2025.5814

View at Publisher

Ask AI

Bookmark

Share

Deep Learning-Based Prediction of Cardiopulmonary Disease in Retinal Images of Premature Infants.

Key Points

Implication

Abstract

Discussion

Cite This Study

Deep Learning-Based Prediction of Cardiopulmonary Disease in Retinal Images of Premature Infants.

Key Points

Implication

Abstract

Discussion

Cite This Study

Keep reading

More related papers

Keep reading

More related papers