Automated screening programs can be as good as highly trained human experts at detecting early diabetic eye disease, according to a study published in the April 15th online edition of Ophthalmology.

Researchers at the University of Iowa (UI) compared the ability of two screening algorithms, the EyeCheck and the Challenge2009, to detect potential eye problems in 16,670 patients with diabetes. Two fundus photographs of each eye were taken and evaluated for diabetic eye damage by the two algorithms and by human retina specialists.

Following the evaluation, the retina specialists determined that 793 eyes demonstrated at least minimal signs of diabetic retinopathy, including small hemorrhages and the presence of fluid. The outcomes from both screening algorithms were analyzed separately and compared to the retina specialists’ findings. Upon final comparison, the researchers determined that the findings from both algorithms were extremely similar to those made by the retina specialists.

“It is an important question: Whether a computer can substitute for a human to detect the initial signs of diabetic eye disease,” says lead author Michael Abràmoff, M.D., Ph.D., associate professor of ophthalmology and visual sciences at the UI Roy J. and Lucille A. Carver College of Medicine and associate professor of electrical and computer engineering in the UI College of Engineering. “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.”

Using the computerized programs allows eye doctors “to spend time on patients who actually need care and to provide better care to those patients,” Dr. Abràmoff says. “Also, through this technology, people with diabetes can have an opportunity for screening that they might not otherwise have.”

“A computer alone will never be a substitute for the care of a good doctor, but it’s exciting to think that computers can be partners in finding the patient at risk of blindness,” says study coauthor Vinit Mahajan, M.D., Ph.D., assistant professor of ophthalmology and visual sciences at UI. “In the United States alone, between 40% and 50% of people with diabetes are not getting the eye screening exams they need. We think these detection programs can meet this critical need very cost-effectively.”

Abràmoff MD, Reinhardt JM, Russell SR, et al. Automated early detection of diabetic retinopathy. Ophthalmology. 2010 Apr 15. [Epub ahead of print]