Smartphone AI

A novel pairing of two technologies may offer a solution for better screening for diabetic retinopathy, a condition that can lead to permanent vision loss if not caught early. At the 2019 annual meeting of the Association for Research in Vision and Ophthalmology, researchers at the University of Michigan Kellogg Eye Center reveal that combining a smartphone-mounted device that takes high-quality retinal pictures with artificial intelligence software that reads them.
The key to preventing DR-relate vision loss is early detection through regular screening,” says Yannis Paulus, M.D., a Kellogg vitreoretinal surgeon and the study’s lead author. They think the key to that is bringing portable, easy-to-administer; so reliable retinal screening to primary care doctors’ offices and health clinics. Michigan Medicine is one of a handful of institutions leading an effort to adapt smartphone technology to ophthalmic screening.

Smartphone to functioning retinal camera

Paulus was part of a Kellogg team that develop a device that turns a smartphone into a functioning retinal camera. In 2016 the project, CellScope Retina, was one of 12 fund by U-M’s Translational Research and Commercialization for Life Sciences Hub; which accelerates ideas with a high potential for positively impacting human health.

The new study utilizes the latest generation of the device, now called RetinaScope. Traditional retinal cameras are expensive, large, immovable and require special training to operate; so whereas RetinaScope is a smartphone base platform that is cheap; so hand-held, and easy to use with no require training” says Paulus; hence an assistant professor of ophthalmology and visual sciences and an assistant professor of biomedical engineering.

While smartphone platforms like RetinaScope can be use to deliver high definition retinal images virtually anywhere; so that’s only part of the challenge. It can take two to seven days for an ophthalmologist to interpret the images,” Paulus explains. “To make screening truly accessible; they need to provide on-the-spot feedback; so taking the photo and interpreting it while the patient is there to schedule an eye appointment if necessary.”

Check of AI based grading

Data was collect from 69 adult patients with diabetes see in the Kellogg Eye Center Retina Clinic; hence including previously record results of dilate slit lamp fundus examinations by their treating clinicians. After pupillary dilation, RetinaScope was use to image patient retinas and the images were analyze with Eye Art software; which grade them as referral warrant diabetic retinopathy (RWDR) or non-referral-warrant DR.
When human grading is use as the only check of AI base grading; so there’s a risk that photos that fail to accurately capture the pathology of DR could be interpret incorrectly by both,” Aaberg says. The study compare two measurements; so if the screening was sensitive enough to find disease; so if it is specific enough to confirm when an individual does not have diabetic retinopathy.
One of the human graders achieved a level of sensitivity that was higher by a statistically-significant factor (96.2 percent) and both had lower specificity (40 percent and 46.7 percent). This is the first time AI used on a smartphone-based platform has been shown to be effective when compared to the gold standard of clinical evaluation,” says Paulus.
Encourage by both these finding and the soon-to-be-published results of a usability study in a primary care clinic, Paulus’ lab continues to pursue hardware and software improvements (notably a version that does not require pupillary dilation), as well as FDA clearance.