Google's ARDA retinal AI tops one million patients screened
TL;DR
- Google's ARDA diabetic retinopathy screening model has crossed one million patients across sites in India, Thailand and Australia.
- Google does not run the service itself; three licensees, Forus Health, AuroLab and Perceptra, deliver screenings at no cost to patients.
- A 23 September 2026 Comment in Nature Medicine, corresponding author Richa Tiwari of Google, distills lessons from scaling the tool globally.
Google's diabetic retinopathy screening model has crossed one million patients across three countries, according to a Comment that Google researchers and partner clinicians published on 23 September 2026 in Nature Medicine. The tool is Google's Automated Retinal Disease Assessment, or ARDA, and the piece positions it as a scaling case study rather than a fresh trial report.
The three anchor deployments named are the Aravind Eye Care System in Madurai, Rajavithi Hospital in Bangkok, and Lions Outback Vision at the Lions Eye Institute in Western Australia. Rather than operate screenings itself, Google licenses ARDA to three commercial partners, Forus Health, AuroLab and Perceptra, which run the service at no cost to patients.
"Scaling a successful deep learning tool across three highly distinct settings—in India, Thailand and Australia—offers cross-cutting insights that may inform the expansion of healthcare artificial intelligence globally," the authors write. The corresponding author is Richa Tiwari of Google; Paisan Ruamviboonsuk of Rajavithi Hospital and Angus Turner of the Lions Eye Institute are among the clinical co-authors, and the Comment is funded by Alphabet. Google has previously set a target of six million AI-supported screenings across India and Thailand within ten years.
The piece reads as the program's own retrospective, told through named clinical partners rather than fresh accuracy numbers.
Shared on Bluesky by 2 AI experts
-
Over a million patients were screened for diabetic eye disease as Google scaled its clinical tool across India, Thailand, and Australia. One of the biggest challenges wasn't the model itself; it was sorting out camera o…
View on Bluesky →
Originally reported by nature.com
Read the original article →Original headline: Practical lessons in the global scaling of clinical AI: from one hospital to over a million patients screened - Nature Medicine