Could Artificial Intelligence Replace Doctors? AI Is Now Diagnosing This Common Eye Disease

Artificial intelligence is now being used to diagnose a common eye disease.

The device, called IDx-DR, uses software and a retinal camera to take images of a patient's retina. It then uses an artificial intelligence algorithm to evaluate the images and effectively diagnose diabetic retinopathy, a diabetes complication that can lead to blindness. Developers hope this new device will make it easier for patients to get diagnosed outside of a clinical environment, leading perhaps to catching the condition earlier.

The University of Iowa Hospitals and Clinics became the first to use the new technology in June, according to reports from The Gazette newspaper.

AI software that helps doctors diagnose like specialists is approved by FDA- “It makes the clinical decision on its own”.#AI #Software #EyeCare #Ophthalmology #ClinicalTrials #algorithms #IDxDR

— Matthew Suits™ (@BusinessConquer) May 3, 2018

Developed by medical diagnostics company IDx, the device analyzes the images to determine if a patient has tissue damage in the back of their eyes.

"It looks for different lesions like hemorrhages, microaneurysms, many other abnormalities you get from diabetes in the retina if it's abnormal, which is what I do when I look for a patient," Dr. Michael Abramoff, an ophthalmologist and president and director of IDx and UI Health Care, told the Gazette.

"Then it analyzes the combination of all these different features and it gives you a clinical decision by itself."

The device was approved by the U.S. Food and Drug Administration in April for diabetic retinopathy.

The condition can manifest in anyone with Type 1 or Type 2 diabetes and is one of the leading causes of blindness in the United States. Diabetic retinopathy occurs when diabetes affects the blood vessels in the retina—the light-sensitive tissue in the back of the eye—causing them to leak and distort vision. Without early medical intervention, diabetic retinopathy can cause blindness, according to the Centers for Disease Control and Prevention (CDC).

The numbers of people affected are only expected to grow. Over the next 30-plus years, the CDC estimates that amount of Americans with diabetic retinopathy will nearly double, from 7.7 million to 14.6 million.

Since diabetic retinopathy often doesn't present any early symptoms, people must have regular eye exams, Abramoff said.

Devices like the IDx-DR that use artificial intelligence to pinpoint disease could provide more accessible exams outside of an eye specialist's office, potentially catching more cases of this eye disease before serious damage is done.