The University of Iowa Hospitals and Clinics has recently begun using an artificial intelligence (AI) system to diagnose eye disease. The system created by medical diagnostics firm IDx, called IDx-DR, uses its software to analyze images from a retinal camera for evidence of lesions. These lesions are a sign of retinal abnormality associated with diabetes, and are what physicians look for in diagnosing eye disease in diabetic patients.
Dr. Michael Abramoff, UI Health Care ophthalmologist and president and director of IDx, claims that the AI conducts image analysis in the same manner a practitioner would. “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,” he states.
The artificial intelligence algorithm was approved by the FDA this past April and will hopefully aid in early detection of diabetic retinopathy. The disease is one of the leading causes for blindness in the U.S. and currently requires regular retinal exams to be detected. Early diabetic retinopathy does not display prominent symptoms, making it particularly challenging to diagnose.
Abramoff hopes that this system can aid in diabetic retinopathy diagnosis by offering an examination that does not require an eye specialist. The IDx-DR technology is used by healthcare staff in routine visits, yielding instant results. In the devices trial including 900 patients, it was found to have a disease detection rate of 87% in all patients.
University officials claim that UI Health Care plans to expand usage of IDx-DR throughout their territory. Abramoff believes that AI diagnostics will be the future in disease detection, facilitating healthcare processes for diabetic patients. “Autonomous AI systems have massive potential to improve healthcare productivity, lower healthcare costs, and improve accessibility and quality. As the first of its kind to be authorized for commercialization, IDx-DR provides a roadmap for the safe and responsible use of AI in medicine,” he says.