FDA approves diabetic retinopathy-detecting AI algorithm

Michael Abràmoff, M.D., Ph.D., the founder and president of IDx. (IDx)(IDx-DR)

The FDA has approved an artificial intelligence algorithm that detects possible cases of diabetic retinopathy from images of the eye. IDx developed the system, IDx-DR, to enable primary care clinics to assess whether patients with diabetes are at risk of vision loss.

Early detection of diabetic retinopathy improves outcomes in a disease that is a major cause of vision loss. Despite that, many patients with diabetes go years without being screened for the condition. Screening tests are performed at dedicated eye clinics by specialists trained in the detection of the condition. As only around 50% of patients with diabetes visit an eye specialist each year, this is a barrier to screening.

IDx wants to remove the barrier by enabling screening to take place at primary care sites without the involvement of specialists. The centerpiece of the plan is IDx-DR, a cloud-based piece of software that analyzes pictures of the eye taken with a retinal camera. The software is designed to detect mild or worse cases of diabetic retinopathy. In those cases, patients will then visit an eye specialist.

Free Webinar

From Patient Adherence to Manufacturing Ease - Why Softgels Make Sense for Rx

Join Thermo Fisher Scientific’s upcoming webinar to learn why softgels offer numerous benefits for Rx drug development, including enhanced bioavailability, patient compliance and easy scale-up. Register Today.

The FDA signed off on the device through its de novo premarket review process after getting a look at data from a 900-patient study. In the trial, IDx-DR correctly identified whether a patient had or did not have diabetic retinopathy almost 90% of the time, resulting in false positive and negative rates low enough to win over the FDA. 

IDx is now poised to find out whether doctors and healthcare systems embrace the technology. The success or otherwise of IDx-DR will provide an early indicator of the potential rate of AI uptake in healthcare. While the indication targeted by IDx-DR differs from that of other products in development, the broad idea of democratizing access to specialist healthcare services by having machines—not people—perform analysis is the same.

Michael Abràmoff, M.D., Ph.D., the founder and president of IDx, is bullish about the potential of this idea.    

“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,” Abràmoff said in a statement.

Suggested Articles

A COVID-19 antibody diagnostic developed through a joint venture between Mount Sinai Health System and RenalytixAI has been authorized by the FDA.

Researchers at Northwestern University have trained an AI algorithm to automatically detect the signs of COVID-19 on a basic X-ray of the lungs.

Hand-held ultrasound developer Butterfly Network is going public through a $1.5 billion acquisition deal backed by Glenview Capital.