Using AI to prevent blindness

We’re using artificial intelligence to help healthcare workers detect diabetic retinopathy, with future possibilities of AI algorithms to assist clinicians in identifying other diseases.

A daunting challenge

Diabetic retinopathy creates lesions in the back of the retina that can lead to total blindness. It’s important to screen people diagnosed with diabetes early, but with over 420 million people with diabetes globally, checking on every patient is an impossible task. Both the lack of awareness of the disease and the resources to screen it are huge issues.

Teaching AI to detect disease

In research published in JAMA, Google’s artificial intelligence accurately interpreted retinal scans to detect diabetic retinopathy. The tricky part was creating a data set for the AI model to learn from – a task which required a large team of ophthalmologists scoring and labeling scans one by one for different grades of severity.

Person looking at eye scan on screen

Developing a diabetic retinopathy screening solution

Google worked with a large team of ophthalmologists who helped us train the AI model by manually reviewing more than 100,000 de-identified retinal scans. This led to a development of an AI-based application called Automated Retinal Disease Assessment. This application can help doctors expand high-quality diabetic retinopathy screening programs in countries without enough eye specialists, such as India and Thailand.

Image of Dr. Lily Peng

Dr. Lily Peng, leading the charge

Lily, who leads the team behind the AI technology, was named one of the “40 Under 40” emerging leaders in healthcare, by Fortune.

The bigger promise of AI in healthcare is to make good care accessible to more people

Man getting his eyes checked at the doctor

Deployed across the globe

Our solution is being used to detect diabetic retinopathy in India and Thailand, and we intend to expand in Europe as well. We are working with multiple partners to make this solution available around the world, especially in the areas which have lower access to specialist care.

A future of diagnostic tools

We are optimistic that many more patients with diabetes could keep their vision in part to Automated Retinal Disease Assessment assisting doctors in spotting diabetic retinopathy. Our early research on the continuing possibilities of AI algorithms diagnosing serious diseases is encouraging and we anticipate a world in which simple screening tools might be used to identify conditions. Read more

Healed through A.I. | The Age of A.I.

The human body is not infallible, but through the wonders of A.I. research scientists are finding ways to address those imperfections. One of those areas of research is through the human eye to detect diabetic retinopathy.

The Age of A.I. Series, YouTube. Copyrights by Network Entertainment