Researchers at King’s College London used anonymous NHS eye data from more than 100,000 diabetic patients to build an AI model that can accurately predict who is likely to develop the vision-threatening diabetic retinopathy (DR) three years in advance.
The study was published in the journal Communication Medicine.
DR is an eye disease that affects approximately one-third of people with diabetes and is the leading cause of vision loss in working-age adults.
Anyone aged 12 or over diagnosed with diabetes under the NHS is required to participate in the annual eye examination to learn about DR by the NHS Diabetes Eye Screening Scheme (DESP), which screens about 3.2 million people a year at a cost of more than £ 85 million in the UK alone.
AI models can be used as a tool to enable personalized DESP screening by using images of the back of the eye to predict whether a person is at low or high risk of vision threatening DR within one, two, or three years. The NHS currently does not have it.
When developing the AI model, the researchers used more than 1.2 million retinal images from diabetic patients from DESP in southeast London. To ensure that the model was powerful enough to work accurately on different individuals, it was verified on a dataset of approximately 70,000 images at the INSIGHT Health Data Research Center.
Professor Timothy Jackson said: “This project demonstrates the great value of organizing, organizing and sharing routinely collected clinical data. It also shows the future path of how artificial intelligence can transform from hype to tangible patient benefits (pending further clinical research).” Doctor.
“It’s a pleasure to be involved in this clinically driven project that leverages the cross-disciplinary capabilities of King’s University School of Life Sciences and Medicine. Using artificial intelligence to predict the incidence of diabetic retinal disease has huge social and economic prospects.
Professor Christos Bergeles said: “Artificial intelligence can modernize diabetes screening programs without sacrificing its current ability to prevent vision loss.”
If implemented, personalized screening will reduce the screening burden on people at low risk of vision loss, while ensuring that people at high risk of vision loss receive urgent medical treatment. This approach could save the NHS millions of pounds and thousands of appointments every year.
There are links in the video below this video. If you are interested, you can open it and have a look.
Thank you for watching this video. If you like it, please subscribe and like it. thank
Original text:https://medicalxpress.com/news/2024-09-ai-tool-eye-imaging-datasets.html
More information: Paul Nderitu et al., Using deep learning to predict emergency referrals for diabetic retinopathy and maculopathy at 1, 2, and 3 years, e
Journal Information: Communication Medicine
Oil tubing: