Google diabetic retinopathy AI crosses one million patients

Over one million patients have been screened using Google's diabetic retinopathy detection model across three health systems in India, Thailand and Australia, according to a Comment in Nature Medicine published on 23 September 2026.

The anchor deployments are Aravind Eye Care System in Madurai, Rajavithi Hospital in Bangkok, and Lions Outback Vision at the Lions Eye Institute in Western Australia. Lead authors include Richa Tiwari, Rajroshan Sawhney and Kasumi Widner from Google, alongside Paisan Ruamviboonsuk at Rajavithi and Angus Turner at Lions Eye.

The authors frame the work as "scaling a successful deep learning tool across three highly distinct settings – in India, Thailand and Australia," and argue it "offers cross-cutting insights that may inform the expansion of healthcare artificial intelligence globally."

Google reached the number through licensed partners Forus Health, AuroLab and Perceptra, and is targeting six million screenings across India and Thailand within ten years. Two researchers we track posted the paper the day it went live.

Only the abstract is public. Per-country accuracy figures, workflow-integration notes and any regulatory friction sit behind the journal's paywall.