Google's ARDA retinal AI crosses one million patients
TL;DR
- Google's ARDA retinal-screening AI has crossed one million patients across sites in India, Thailand and Australia.
- The Nature Medicine Comment anchors on Aravind Eye Care in Madurai, Rajavithi Hospital in Bangkok, and Lions Outback Vision at the Lions Eye Institute.
- Google licenses ARDA to Forus Health, AuroLab and Perceptra, with a stated target of six million screenings across India and Thailand in ten years.
Google's Automated Retinal Disease Assessment, the diabetic retinopathy screening model known as ARDA, has now been used on more than a million patients, according to a Comment in Nature Medicine dated 23 September 2026.
The paper anchors on three deployments: Aravind Eye Care System in Madurai, Rajavithi Hospital in Bangkok, and Lions Outback Vision at the Lions Eye Institute in Western Australia. The authors, led by Google's Richa Tiwari with Paisan Ruamviboonsuk of Rajavithi Hospital and Angus Turner of the Lions Eye Institute among the co-signers, pitch the write-up as portable operational lessons. Scaling the tool across three highly distinct settings, they argue, "offers cross-cutting insights that may inform the expansion of healthcare artificial intelligence globally."
It is a lessons narrative rather than a fresh accuracy study. Google licenses ARDA to three commercial partners, Forus Health, AuroLab and Perceptra, which run the service at no cost to patients, with a stated target of six million AI-assisted screenings across India and Thailand within ten years. Two of the researchers we track in our Who's Who tracker passed the paper along the day it ran.
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