The Aravind Eye Hospital in Madurai, India, is working with Google artificial intelligence (AI) scientists to automate the identification of diabetic retinopathy.
The hospital is using the new AI system to screen patients, with plans to deploy the technology in surrounding villages where eye doctors are scarce.
The system is based on a neural network that has analyzed millions of retinal scans indicating diabetic blindness to learn to identify the disease on its own.
The Aravind installation employs wall-mounted computer screens in waiting rooms to translate information into the various languages spoken by patients; the system's performance reportedly equals that of trained ophthalmologists.
However, Luke Oakden-Rayner, director of medical imaging research at the Royal Adelaide Hospital in Australia, warned, “On paper, the Google system performs very well, but when you roll it out to a huge population, there can be problems that do not show up for years.”
From The New York Times
View Full Article - May Require Paid Subscription
Abstracts Copyright © 2019 SmithBucklin, Washington, DC, USA
No entries found