Researchers at Moorfields Eye Hospital and UCL Institute of Ophthalmology have developed an artificial intelligence (AI) system with the potential to identify eye diseases, heart attacks, stroke and Parkinson’s disease, and made it freely available on GitHub for any institution to use. 

The system, RETFound, was developed using 1.6 million NHS retinal scans. Writing about the system in Nature, authors described it as a foundation model with a large dataset which can be fine-tuned for a diverse range of tasks. RETFound addresses the significant shortcoming of many current AI systems by working well in diverse populations and in patients with rare disease, they said.  

"By training RETFound with datasets representing the ethnical diversity of London, we have developed a valuable base for researchers worldwide to build their systems in healthcare applications, such as ocular disease diagnosis and systemic disease prediction," wrote lead author and Moorfields PhD student Yukun Zhou. 

“This is another big step towards using AI to reinvent the eye examination for the 21st century… We show several exemplar conditions where RETFound can be used, but it has the potential to be developed further for hundreds of other sight-threatening eye diseases that we haven’t yet explored,” said senior author Professor Pearse Keane.