Google retinal AI hits 1M patients across three countries
TL;DR
- A Nature Medicine comment reports a deep learning eye-screening tool has scaled from one hospital to over a million patients screened across India, Thailand and Australia.
- The paper draws lessons from deployments at Aravind Eye Care System in India, Rajavithi Hospital in Bangkok and Lions Outback Vision in Western Australia.
- Lead authors sit at Google, with clinician co-authors named at each partner site including Kim Ramasamy, Paisan Ruamviboonsuk and Angus Turner.
A Nature Medicine comment from Google and three eye-care partners describes scaling a deep learning tool from a single hospital to more than a million patients screened across India, Thailand and Australia.
The abstract says the deployments span "three highly distinct settings" and produce "cross-cutting insights that may inform the expansion of healthcare artificial intelligence globally." Local co-authors are named at each partner site: Kim Ramasamy at Aravind Eye Care System in Madurai, Paisan Ruamviboonsuk at Rajavithi Hospital in Bangkok, and Angus Turner at Lions Outback Vision in Western Australia. Lead authors Richa Tiwari, Rajroshan Sawhney and Kasumi Widner are at Google.
The comment format keeps the piece short on numbers. The abstract does not break down accuracy per site or say how the million-plus screenings distribute across the three countries. Two researchers on our tracker's list circulated the paper within its first day.
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