New Computer System Detects Diabetes-Related Blindness

One of the most common side-effects of diabetes is blindness, that much all patients suffering from the condition know. Regardless, only a very small portion of people who have the condition get their eyes checked out. In the United States, the situation is disastrous, with about 11 million people of the 23 million sufferers refusing to go see a doctor and get their eyes looked at. Annual exams are mandatory if eye degeneration is to be detected and delayed, and yet only half of patients appear interested in doing so. Now, a new computerized method holds great promise for identifying the onset of diabetes-related ocular degeneration with great ease and increased efficiency.

“It is an important question: whether a computer can substitute for a human to detect the initial signs of diabetic eye disease,” says University of Iowa Roy J. and Lucille A. Carver College of Medicine associate professor of ophthalmology and visual sciences Michael Abramoff, MD, PhD. The expert is also an ophthalmology expert with the UI Hospitals and Clinics. The science team at the university tested two computer programs in parallel, on about 16,670 people who had been diagnosed with diabetes. Both the EyeCheck and Challenge 2009 software managed to achieve optimal results, reaching the limits that had been theoretically-predicted.

“Our analysis shows that the computerized programs appear to be as accurate and thorough as a highly trained expert in determining if these initial signs of an eye problem are developing in someone with diabetes. Once the initial problems are found, an eye specialist can treat the patient,” says Abramoff, who is also an UI College of Engineering an associate professor of electrical and computer engineering. Details of the investigation were published in the April 16 online issue of the esteemed scientific journal Ophthalmology, the team says.

The computerized system is very simple. A lab technician uses a digital camera to snap photos of the retina, the light-sensitive portion of the eye. The data is then transferred to a computer, where especially-designed algorithms identify small hemorrhages (internal bleedings) on the structure. These are clear indicators that diabetes is affecting the eye. Left untreated, such bleedings can lead to partial or total blindness. “The computerized programs are accurate and allow ophthalmologists to spend time on patients who actually need care and provide better care to those patients. Also, through this technology, people with diabetes can have an opportunity for screening that they might not otherwise have,” the expert concludes.