Home / Resources / Articles / Point: FDA Approves Artificial Intelligence (AI) To Detect Retinopathy

Point: FDA Approves Artificial Intelligence (AI) To Detect Retinopathy

Apr 28, 2018
 

IDx-DR software provides screening decision without need for a clinician to interpret image or results.

New medical device will be the first to use artificial intelligence (AI) software to detect greater than a mild level of the most common cause of vision loss among more than 30 million Americans living with diabetic retinopathy.

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.

The device, called IDx-DR and produced by Iowa-based IDx LLC, is the first to receive Food and Drug Administration authorization that provides a screening decision without need for a clinician. That makes it usable by health care providers not normally involved in eye care, such as primary care physicians who interact far more frequently with patients with diabetes.

The IDx-DR program uses AI software to analyze images of the eye taken with a retinal camera. The software tells the doctor that the patient either has more than mild diabetic retinopathy and should be referred to eye care professional for possible treatment, or is “negative” for more than mild diabetic retinopathy and should be rescreened in 12 months.

The company was founded by Dr. Michael Abramoff, who was working as an ophthalmology resident at a busy clinic in the Netherlands in 1997 when he decided to research ways to automate the process of detecting diabetic retinopathy by using artificial intelligence.

“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,” Abràmoff said in a press release. “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 device uses an artificial intelligence algorithm to analyze images of the eye taken with a retinal camera called the Topcon NW400. Digital images of the patient’s retinas are then uploaded to an IDx-DR server.

The software provides the doctor two possible results if the image quality is sufficient — more than mild diabetic retinopathy detected: refer to an eye care professional or negative for more than mild diabetic retinopathy; rescreen in 12 months. If the quality is not sufficient, the operator can retake the image while the patient is still in the office.

A clinical study on efficacy of the device included retinal images of 900 patients with diabetes at 10 primary care sites. In the study, IDx-DR correctly identified the presence of more than mild diabetic retinopathy 87.4 percent of the time, and those who did not have more than mild diabetic retinopathy 89.5 percent of the time.

The FDA said patients with a history of laser treatment, surgery, or injections in the eye or certain conditions should not be screened for diabetic retinopathy with IDx-DR. Among the conditions that disqualify a patient from screening with the device are resistant vision loss, blurred vision, floaters, previously diagnosed macular edema, severe non-proliferative retinopathy, proliferative retinopathy, radiation retinopathy or retinal vein occlusion. IDx-DR should not be used in patients with diabetes who are pregnant; diabetic retinopathy can progress very rapidly during pregnancy and IDx-DR is not intended to evaluate rapidly progressive diabetic retinopathy. IDx-DR is only designed to detect diabetic retinopathy, including macular edema; it should not be used to detect any other disease or condition. Patients will still need to get a complete eye examination at the age of 40 and at the age of 60 and also if they have any vision symptoms (for example, persistent vision loss, blurred vision, or floaters).

Dr. Michele Birch of the University of North Carolina School of Medicine, one of the principal investigators, added that, “I am excited that IDx-DR is now cleared for use; there is a definite need for a more affordable and accessible option for the early detection of diabetic retinopathy….Making sure that my patients with diabetes have annual eye exams has always been a challenge, but IDx-DR can make it easier by allowing me to conduct an exam right in my office.”

For counterpoint, see: “The Pros and Cons of AI-based ‘Diagnosis’ of Diabetic Retinopathy” by Dr. A. Paul Chous following this article.

Practice Pearls:

  • 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.
  • Using artificial intelligence can make it easier for patients to get an eye screening from their family doctor.
  • IDx-DR was granted Breakthrough Device designation, meaning the device must represent a breakthrough technology with no approved or cleared alternatives.

FDA News release