A recent study, published in the Lancet Digital Health, details the development of a deep learning AI model that can identify which at-risk infants have retinopathy of prematurity.
The research team, which included scientists and clinicians from the UK, Brazil, Egypt, and the US, hopes their technique could improve access to screening in the many areas with limited neonatal services and few trained ophthalmologists.
The study was supported by the National Institute for Health and Care Research (NIHR) Biomedical Research Centre at Moorfields Eye Hospital NHS Foundation Trust and UCL Institute of Ophthalmology.
Lead author Dr. Konstantinos Balaskas (Director, Moorfields Ophthalmic Reading Centre & Clinical AI Lab, Moorfields Eye Hospital and Associate Professor, UCL Institute of Ophthalmology) said, "Retinopathy of prematurity is becoming increasingly common as survival rates of premature babies improve across the globe, and it is now the leading cause of childhood blindness in middle-income countries and in the US."
"As many as 30% of newborns in sub-Saharan Africa have some degree of ROP and, while treatments are now readily available, it can cause blindness if not detected and treated quickly. This is often due to a lack of eye care specialists—but, given it is detectable and treatable, no child should be going blind from ROP."
"As it becomes more common, many areas do not have enough trained ophthalmologists to screen all at-risk children; we hope that our technique to automate diagnostics of ROP will improve access to care in underserved areas and prevent blindness in thousands of newborns worldwide."
ROP is a condition that affects premature babies and causes abnormal blood vessels to grow in the retina, which can lead to retinal detachment and ultimately blindness. While mild cases can be monitored, more severe cases require prompt treatment. Approximately 50,000 children worldwide are blind due to this condition. Symptoms are not visible to the naked eye, and screening is necessary to identify it. Without proper infrastructure for antenatal and postnatal care, the narrow screening window could be missed, resulting in preventable blindness.
The UCL-Moorfields team developed a deep learning AI model for ROP screening. The model was trained on a sample of 7,414 images of newborns' eyes assessed for ROP by ophthalmologists at Homerton Hospital, London, which serves an ethnically and socioeconomically diverse community, ensuring the tool is safe to use across different ethnic groups. The tool's performance was assessed on 200 images and compared to senior ophthalmologists' assessments. The tool's validity was further confirmed by testing it on datasets from the US, Brazil, and Egypt.
On the left, a photograph of the left retina of a neonate (newborn infant) with retinopathy of prematurity. The image on the right has an overlaid saliency map generated by the AI algorithm, which shows the parts of the image most influencing the algorithm decision-making. Credit: Moorfields Eye Hospital
The researchers found that the AI tool is equally effective as senior pediatric ophthalmologists in distinguishing normal retinal images from those with ROP, which could cause blindness. Although it was optimized for a UK population, the researchers discovered that it is still effective on other continents, and they believe it could be further optimized for other environments. The tool is a code-free deep learning platform, which means it could be optimized in new settings by people without prior coding experience.
First author Dr. Siegfried Wagner (UCL Institute of Ophthalmology and Moorfields Eye Hospital) said, "Our findings justify the continued investigation of AI tools to screen for ROP. We are now further validating our tool in multiple hospitals in the UK and are seeking to learn how people interact with the AI's outputs, to understand how we could incorporate the tool into real world clinical settings."
"We hope that the tool will enable a trained nurse to take images that could be assessed by the AI tool, in order for a referral for treatment to be made without the need for an ophthalmologist to manually review the scans."
"AI tools are particularly useful in ophthalmology, a field which is heavily reliant on the manual interpretation and analysis of scans for detection and monitoring—here we have found further evidence that AI can be a game-changer for the field and open up access to sight-saving treatments."
Siegfried K Wagner et al, Development and international validation of custom-engineered and code-free deep-learning models for detection of plus disease in retinopathy of prematurity: a retrospective study, The Lancet Digital Health (2023). DOI: 10.1016/S2589-7500(23)00050-X