Retail health clinics have been part of the trend in making healthcare more convenient, and now another option is being offered — testing for diabetic retinopathy.
However, an ophthalmologist won’t make the diagnosis at the clinic; instead, it will be made by an artificial intelligence (AI) system called IDx-DR. Testing will be offered through CarePortMD, the first retail health clinic to adopt this type of AI diagnostic technology, and offered at clinics inside Albertsons grocery stores. The second largest grocery chain in the United States, Albertsons added five CarePortMD clinics to stores in Delaware and Pennsylvania this past year.
“Ours is a hybrid model of telehealth plus the convenience and access of a retail clinic, with the scalability and opportunity to coordinate with telemedicine.” said Ashok Subramanian, MD, the CEO of CarePortMD. “Our clinic has diagnostic equipment, point-of-care testing with a full complement of laboratory testing, and virtual connection to an urgent care doctor or a primary care provider or a specialist and an onsite clinical pharmacy staff.
Although the IDx-DR exam is not performed by a physician, it is also not a self-service device like blood pressure cuff machines that are seen in some retail outlets. By prescription only, it is administered by the clinic staff.
“It is important to understand CarePortMD is a primary care visit hosted within a retail setting,” said Michael D. Abramoff, MD, PhD, founder and president of IDx and a professor of ophthalmology and visual sciences, electrical and computer engineering, and biomedical engineering at the University of Iowa in Iowa City. “Primary care physicians place orders for the IDx-DR diabetic retinopathy exam just like a physician in a traditional clinic setting as part of their diabetes management.”
He told Medscape Medical News a clinician reviews the results with the patient as in a primary care setting. “Positive patients are routed to an eye care provider for closer management and treatment where required,” Abramoff said. “This is in line with the AMA’s Medical Home concept as well as the [US Food and Drug Administration’s] mandate that AI is safe, effective, and equitable.”
Accelerated Approval
Interest in AI is growing across the board in healthcare, and its use in ophthalmology is no exception. One recent study found that it was at least as effective as experts, and sometimes more effective, at detecting 53 kinds of vision-threatening retinal diseases. Researchers used Google’s DeepMind deep-learning technology, and the computer system was able to make a diagnosis in seconds with an accuracy rate of 94%.
Results from a prospective study that evaluated the IDx-DR were convincing enough for the FDA to fast-track its approval last year. As reported by Medscape Medical News, the AI system had a sensitivity of 87.2%, a specificity of 90.7%, and an imageability rate of 96.1%, when tested in a primary care setting.
Those researchers pointed out that, in comparison, three previous studies showed board-certified ophthalmologists who perform indirect ophthalmoscopy have an average sensitivity of 33% to 73% compared with the same Early Treatment Diabetic Retinopathy Study severity scale standard.
Commenting on the study at the time for Medscape Medical News, T.Y. Alvin Liu, MD, had predicted the system would be available in places such as major drugstore chains within 3 years. Liu is a retina specialist and assistant professor of ophthalmology at Wilmer Eye Institute at Johns Hopkins Medicine in Baltimore, Maryland.
His prediction has seemingly come to pass.
One-Stop Shopping
The exam typically takes 5 to 10 minutes and the device can easily be operated by someone who is not a physician. An automated fundus camera is used to take pictures of the retina and it only takes a few hours for nonmedical personnel to learn the procedure. The photos are then scanned by the autonomous AI’s diagnostic software, which searches 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 he or she is still in the office.
“Once we have the diagnosis, it does two things for us,” said Subramanian. “It recognizes patients that need linkage, and if they have their own eye doctor, we will go ahead and set up an appointment. If they don’t, we will give them same-day or next-day follow up with a specialist.”
IDx-DR has been up and running for approximately 6 weeks, and patient feedback so far is positive. “We are excited to work with partners who offer IDx-DR diabetic retinopathy exam in convenient retail settings,” said Abramoff. “Given the national rate for screening is as low as 15%, improving access to this care is paramount to improve clinical outcomes and patients’ lives.”
Charles C. Wykoff, MD, PhD, is also enthused about the technology and the push to implement access to it. “This is exciting technology and I believe still just the beginning of efficient and effective tele-screening options for retinal diseases, including diabetic retinopathy,” said Wykoff, a retina surgeon and ophthalmologist at Retina Consultants of Houston and the Houston Methodist Blanton Eye Institute in Texas. “There remains far too much needless visual loss and blindness from diabetic retinopathy across the US, much of it attributable to lack of appropriate screening.”
“Most cases of blindness from diabetic retinopathy are preventable if identified early in the disease course,” he added. “I look forward to widespread, easy-access screening technologies that meaningfully improve diabetic retinopathy screening rates across the US.”
lDx is currently developing additional AI-based diagnostic systems for the detection of macular degeneration, glaucoma, stroke risk, and ear infection.