The US FDA has announced the authorization of an AI (artificial intelligence) enabled software diagnostic for the screening of diabetic patients for retinopathy. The approved device, manufactured by US company IDx, uses specialized software to determine the status of a fundus image and adjudicate whether or not specialist ophthalmic consultancy is required. As the number of diabetic patients worldwide reaches epidemic proportion, there are simply an insufficient number of trained ophthalmologists available to assess and grade the numbers of patients at risk. Accoring to information from IDx, over 30 million Americans have diabetes, with an estimated 24,000 individuals losing vision each year from diabetic retinopathy (DR). Such an impact may be reduced through a programme of active screening, earlier detection and earlier treatment. Automated screening procedures have been under development for several years and are expected to make a significant impact in the public health challenge of diabetic co-morbidities.
The IDx-DR device works by capturing a fundus image in a process which can be carried out in a doctor’s office without the need of a specialist ophthalmic consultant. The device, operated by a nurse or technician, captures two colour, 45 degree field of view images per eye and transfers the images to an IDx-DR analysis cloud-based system which, within approximately 1 minute, provides an image quality confirmation and disease output grading of the image. If the images are of sufficient quality, the software returns one of two results: (1) “more than mild diabetic retinopathy detected: refer to an eye care professional” or, (2) “negative for more than mild diabetic retinopathy; rescreen in 12 months.” Commenting on the regulatory approval of the technology, founder and president of IDx, Dr. Michael Abràmoff, stated, “the FDA’s authorization to market IDx-DR is a historic moment that has the potential to launch a transformation in the way U.S. healthcare is delivered. 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.”
The US FDA have recognized the public health care challenges brought about by rapid increases in disease such as diabetes and have been actively creating a regulatory framework for the development of clinical decision support software to help healthcare professionals diagnose or treat diseases. The FDA provided IDxDR with breakthrough-device designation, reviewed under the FDA’s de novo premarket review pathway, “a regulatory pathway for some low- to moderate-risk devices that are novel and for which there is no prior legally marketed device.” The FDA are understood to have reviewed data from a study of 900 patients with diabetes at 10 primary care clinics which demonstrated that IDx-DR correctly identified the presence of more than mild diabetic retinopathy in 87.4% of cases and correctly identified patients who did not have more than mild diabetic retinopathy in 89.5% of cases. In a press release, Malvina Eydelman, M.D., director of the Division of Ophthalmic, and Ear, Nose and Throat Devices at the FDA’s Center for Devices and Radiological Health stated: “Early detection of retinopathy is an important part of managing care for the millions of people with diabetes, yet many patients with diabetes are not adequately screened for diabetic retinopathy since about 50 percent of them do not see their eye doctor on a yearly basis. Today’s decision permits the marketing of a novel artificial intelligence technology that can be used in a primary care doctor’s office.”