Google diabetic retinopathy AI passes one million patients

Google's diabetic retinopathy screening model has now been used on over a million patients across three health systems in India, Thailand and Australia, according to a Comment published in Nature Medicine on 23 September 2026.

The anchor sites are the Aravind Eye Care System in Madurai, Rajavithi Hospital in Bangkok, and Lions Outback Vision at the Lions Eye Institute in Western Australia. Authors from Google (Richa Tiwari, Rajroshan Sawhney and Kasumi Widner), writing with Paisan Ruamviboonsuk of Rajavithi Hospital and Angus Turner of the Lions Eye Institute, describe the deployment as one that "offers cross-cutting insights that may inform the expansion of healthcare artificial intelligence globally."

The operational lessons are the less flattering half of the story. According to the reporting, the biggest challenges were not the model itself but the cameras and related infrastructure at each site: imaging acquisition, extraction logic, and the harmonisation work that had to be done before the model could touch a patient.

Google reached the million through licensed commercial partners Forus Health, AuroLab and Perceptra, who run the deployments in-country. The stated target is six million screenings across India and Thailand within ten years.

Read as a field guide rather than a paper, the Comment sets out what a decade of pushing one research model into three health systems actually took.