Google eye AI passes one million patients across three countries

Google's diabetic retinopathy screening model has now been used on more than one million patients across three countries, according to a Comment published in Nature Medicine on 23 September 2026.

The piece is co-authored by a Google-plus-clinician roster: Richa Tiwari, Rajroshan Sawhney and Kasumi Widner from Google in Mountain View, alongside Kim Ramasamy and Ravindran Padmanabhan at the Aravind Medical Research Foundation in India, Paisan Ruamviboonsuk at Rajavithi Hospital in Bangkok, and Angus Turner at Lions Outback Vision at the Lions Eye Institute in Western Australia. Those three sites are the anchor deployments behind the million-patient tally. Two researchers we follow in our Who's Who directory shared the link.

The framing is scaling, not fresh accuracy numbers. "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.

Nature Medicine ran the article as a Comment rather than primary research, and the abstract publishes no per-site sensitivity or specificity numbers. The one-million figure is a cumulative screening tally across the three programs.