Researchers to build first medical AI model with globally representative data
A research consortium of over 100 study groups in more than 65 countries has launched a collaborative effort to develop the first globally representative AI foundation model in medicine, using 100 million eye images.
The Global RETFound initiative is one of the largest medical AI collaborations ever undertaken, producing one of the most geographically and ethnically diverse medical datasets assembled for AI training purposes.
The data will span Africa, the Middle East, North and South America, the breadth of Asia, Oceania, Europe and the Caucasus region.
The consortium will develop an AI model using an unprecedented dataset of over 100 million colour fundus photographs of the retina at the back of the eye, sourced from more than 65 countries.
Dr Yih Chung Tham is assistant professor at the National University of Singapore (NUS) Medicine and one of the project leads
Tham said: “Current foundational models are trained on data that is geographically and demographically ‘narrow’, which limits their effectiveness and can perpetuate existing health inequalities.
“The Global RETFound Consortium addresses this challenge through innovative approaches that enable broad international participation while maintaining strict privacy protections.”
The initiative builds on the success of RETFound, the first foundation model for retinal and systemic disease detection.
Published in Nature in 2023, RETFound was developed by researchers at Moorfields Eye Hospital and UCL Institute of Ophthalmology in London, using 1.6 million retinal images curated by the INSIGHT Health Data Research Hub at Moorfields.
While RETFound has already demonstrated significant potential for medical AI applications, the global model will expand the training data to encompass every continent except Antarctica.
A key innovation of the project is its flexible, two-pronged data sharing framework, designed to accommodate varying technical capacities and regulatory requirements across participating institutions.
The first approach involves local fine-tuning of generative AI models at individual institutions, with only model weights shared centrally — ensuring no patient data leaves the originating site.
The second pathway enables direct sharing of de-identified data through secure infrastructure for institutions that do not have local GPU resources or technical expertise.
Pearse Keane is professor of artificial medical intelligence at UCL and consultant ophthalmologist at Moorfields eye hospital.
Keane said: “This dual approach allows participation from research groups regardless of their resource levels.
By combining real and synthetic data generation techniques, we can build a diverse, globally representative dataset without compromising security.
The Global RETFound model will undergo comprehensive evaluation across multiple ophthalmic and systemic diseases, including diabetic retinopathy, glaucoma, age-related macular degeneration and cardiovascular disease.
The model will be released under a Creative Commons license, making it freely available for non-commercial research worldwide.
