AI Project Could Prevent Needless Blindness

Posted on January 11, 2018 I Written By

Anne Zieger is veteran healthcare consultant and analyst with 20 years of industry experience. Zieger formerly served as editor-in-chief of FierceHealthcare.com and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also contributed content to hundreds of healthcare and health IT organizations, including several Fortune 500 companies. Contact her at @ziegerhealth on Twitter or visit her site at Zieger Healthcare.

At this point, you’re probably sick of hearing about artificial intelligence and the benefits it may offer as a diagnostic tool. Even so, there are still some AI stories worth telling, and the following is one of them.

Yes, IBM Watson Health recently had a well-publicized stumble when it attempted to use “cognitive computing” to detect cancer, but that may have more to do with the fact that Watson was under so much pressure to produce results quickly with something that could’ve taken a decade to complete. Other AI-based diagnostic projects seem to be making far more progress.

Consider the following, for example. According to a story in WIRED magazine, Google is embarking on a project which could help eye doctors detect diabetic retinopathy and prevent blindness, basing its efforts on technologies it already has in-house.

The tech giant reported last year that it had trained image recognition algorithms to detect tiny aneurysms suggesting that the patient is in the early stages of retinopathy. This system uses the same technology that allows Google’s image search photo and photo storage services to discriminate between various objects and people.

To take things to the next step, Google partnered with the Aravind Eye Care System, a network of eye hospitals based in India. Aravind apparently helped Google develop the retinal screening system by contributing some of the images it already had on hand to help Google develop its image parsing algorithms.

Aravind and Google have just finished a clinical study of the technology in India with Aravind. Now the two are working to bring the technology into routine use with patients, according to a Google executive who spoke at a recent conference.

The Google exec, Lily Peng, who serves as a product manager with the Google Brain AI research group, said that these tools could help doctors to do the more specialized work and leave the screening to tools like Google’s. “There is not enough expertise to go around,” she said. “We need to have a specialist working on treating people who are sick.”

Obviously, we’ll learn far more about the potential of Google’s retinal scanning tech once Aravind begins using it on patients every day. In the meantime, however, one can only hope that it emerges as a viable and safe tool for overstressed eye doctors worldwide. The AI revolution may be overhyped, but projects like this can have an enormous impact on a large group of patients, and that can’t be bad.