ADA gives green light for AI to detect diabetic eye problems
January 14, 2020
The American Diabetes Association's 2020 Standards of Medical Care in Diabetes now include FDA-authorised artificial intelligence systems that detect diabetic retinopathy and macular oedema.
The US association that fights against diabetes has released clinical standards that for the first time include the use of autonomous artificial intelligence (AI).
The ADA's 2020 Standards of Medical Care in Diabetes states that: "AI systems that detect more than mild diabetic retinopathy and diabetic macular oedema authorised for use by the FDA represent an alternative to traditional screening approaches."
To date, IDx-DR is the first and only FDA-authorised autonomous AI diagnostic system for the detection of diabetic retinopathy and macular oedema. It is in use at a number of large health systems that each serve tens of thousands of people with diabetes and have struggled to implement diabetic retinopathy eye exams at scale for their large diabetes population.
"The ADA's inclusion of our technology in its Standards of Care marks a significant move towards mainstream adoption of autonomous AI in clinical care," said Michael Abramoff, founder and executive chairman at IDx. "Our early customers are visionary leaders who foresaw that autonomous AI would one day become a standard of care for diabetic retinopathy screening, and taking that leap is paying off for them. Already, health systems that are using IDx-DR have experienced significant improvements in accessibility, efficiency and compliance rates, unleashing massive potential for cost savings and improved patient outcomes."
The Standards of Care were published last month in Diabetes Care, a peer-reviewed journal in the field of diabetes treatment and prevention. Physicians, healthcare systems, health insurers and quality of care organisations look to the ADA's Standards of Care for consensus and evidence-based best practices to improve health outcomes for people with diabetes.
IDx-DR is an FDA-authorised AI-based diagnostic system designed for use at the front lines of care to detect diabetic retinopathy and macular oedema, common complications of diabetes and leading causes of blindness. IDx-DR is cleared by the FDA to make an assessment without the need for a clinician to interpret the image or results, making it usable by health care providers who may not normally be involved in eye care.
The exam typically takes five to ten minutes. Operators use a robotic fundus camera to take pictures of the patient's retinas – the back part of the eye – which are then analysed by the autonomous AI's algorithms for signs of diabetic retinopathy. An immediate diagnostic report is produced at the point of care, allowing the physician to discuss the results with the patient while they are still in the office.
Founded in 2010 by a team of clinician scientists, Iowa-based IDx is an AI diagnostics company on a mission to transform the quality, accessibility and affordability of healthcare. The company is focused on developing clinically aligned autonomous algorithms that detect disease in medical images. By enabling diagnostic assessment in primary care settings, IDx aims to increase patient access to high-quality, affordable disease detection.