At a routine doctor’s visit, the member of the clinic staff takes digital pictures of a patient’s retinas.
Within seconds, an artificial intelligence (AI) algorithm determines if the patient has diabetic retinopathy , a complication of diabetes that can lead to blindness.
If they do, the physician refers the patient to an eye care specialist for further evaluation and treatment.
This scene already is playing out in primary care clinics around the particular United States and in other countries, and it may become more common.
Healthcare systems intend to expand their use of AI to screen with regard to diabetic retinopathy in 2023, and companies are developing more algorithms for this purpose.
In May, OSF HealthCare, a network of medical facilities headquartered in Peoria, Illinois, piloted an AI system in order to diagnose diabetic retinopathy, the condition that will affects an estimated 4 million Americans . Next year, the healthcare system plans to increase the technology to 34 locations.
Meanwhile, the Food plus Drug Administration in November approved a new AI system to diagnose diabetic retinopathy, making AEYE-DS from AEYE Health the third such product on the market.
Roomasa Channa, MD, the clinician-scientist with the McPherson Eye Research Institute at the University associated with Wisconsin-Madison, offers studied the use of AI in teenage patients with diabetes . She said she soon programs to use AI screening in federally qualified health centers in order to screen adults with diabetes.
Channa welcomed the latest regulatory clearance and said the girl hopes another FDA cleared algorithm item will improve accessibility to the technology.
“It is good to see a lot more players in the field: We need this technology to be readily available and affordable, ” the lady told Medscape Medical News .
A Mixed Reception
Responses through physicians to this type of AI have been mixed. Some worry, for instance, that the algorithms might be programmed with unrecognized biases that could lead them to less accurately interpret images from certain patient groups. Researchers should be on the particular lookout out for this possibility, Channa said.
“We need more real-world studies in different settings, ” she stated. “We also need to keep collecting data on AI performance post-approval, inch like investigators do regarding newly approved drugs.
The first AI system to diagnose diabetic retinopathy, IDx-DR, was approved by the FDA within 2018 plus rolled away in retail clinics soon after. A second system, EyeArt, gained clearance from the agency in 2020.
Adding AI algorithms into primary treatment practice provides changed how patients along with diabetes can receive a screening. It also has introduced a new way for certain medical conditions to be diagnosed in main care.
The American Medical Association in 2021 released a brand new Current Procedural Terminology (CPT) code to allow clinicians to bill government and private insurers for use associated with these services. CPT program code 92229 refers to imaging from the retina in order to detect disease with a good automated analysis and report in the point of care.
Meeting a Need
Health care clinics within underserved areas often do not possess eye treatment providers onsite to conduct recommended screening exams, so AI could help individuals receive screening who otherwise would not get it, Channa said.
Channa and her colleagues successfully used one AI program, IDx-DR, to screen children at a pediatric diabetes clinic . Over a year, screening rates jumped from 49% in order to 95%.
This technology “can potentially help us inside decreasing disparities in care and focusing our efforts on patients with the most severe diseases, inches she mentioned.
OSF Health care recently obtained an approximately $1 mil grant through drug company Regeneron to expand the particular use of AI-based testing for diabetic retinopathy, following a successful pilot. Regeneron markets a treatment for diabetic retinopathy.
Without an AI option, recommended eye screening intended for patients with diabetes often falls through the cracks, according to Mark Meeker, DO, vice president associated with community medicine at OSF. Primary treatment physicians may refer sufferers elsewhere for their annual retinopathy screening exam.
“That frequently doesn’t get completed because it’s an additional trip, one more appointment, another time away from work, ” Meeker said.
All patients with diabetes should have got their eyes screened each year, but between one- to two-thirds of individuals nationwide do not , he said.
A member of the clinic personnel takes electronic pictures of the retina, almost always through undilated pupils.
If the result is normal, the patient is scheduled for another follow-up screening in a 12 months. If early signs of diabetic retinopathy are spotted, patients are referred to an eye care specialist.
After 7 months of the pilot program, OSF had screened about 350 sufferers. Approximately 20% had diabetic retinopathy, based on OSF.
“A Huge Impact”
OSF has about 66, 000 patients with diabetes. About two-thirds do not really receive annual screening, Meeker estimated.
“This can have a huge impact on the particular quality associated with life within the coming years for our diabetic individuals, ” this individual said. “It’s pretty profound. ”
Eye care specialists typically treat diabetic retinopathy with lasers, surgery, or medication.
For primary care clinicians, however, AI testing for retinopathy is an opportunity to emphasize how important it is to manage the disease plus what its consequences can be.
AI screening is “another tool for us to make use of to get sufferers more engaged in their own care, inch Meeker stated. “This is probably the biggest advance in AI affecting our day-to-day interaction with patients that we’ve seen in primary treatment. ”
A Business Opportunity, Too?
The IDx-DR platform OSF is using in its clinics is owned by the company Digital Diagnostics. OSF Ventures, an investment arm of OSF HealthCare, offers invested within the company, the particular healthcare system announced inside August . ( Another investor in Electronic Diagnostics, KKR, is the majority owner of Internet Brands, Medscape’s parent company. )
Other companies have had their products used in practice. In 2019, to get example, Eyenuk described exactly how its EyeArt system had been used in order to screen thousands of individuals in Germany and within Italy .
And in 2021, Eyenuk reported that is customer base in the United States had expanded to more than 25 locations . The company credited the Centers pertaining to Medicare & Medicaid Services plan to cover CPT code 92229 with supporting this growth.
Zack Dvey-Aharon, PhD, the CEO associated with AEYE Wellness, said the particular company has been motivated in order to enter this particular space when regulators decided that AI could be used to identify a condition — not just as a tool to assist doctors arrive at a diagnosis.
With proper training, a person can diagnose diabetic retinopathy relatively easily if the image of the retina is of excellent quality.
In case image will be dark or even blurry, nevertheless, it’s a different story.
AI has the advantages within this scenario, according to Dvey-Aharon.
“For AI, those darker, more blurry images are actually highly readable along with fantastic accuracy, ” he or she said.
More in order to Come?
The possibilities of AI in analyzing retinal images are vast.
New research shows that AI may be able to detect Alzheimer’s illness or predict a person’s risk for heart attack and stroke based on snapshots from the retina.
The particular retina may also shed light on kidney disease, control of blood glucose and blood pressure, hepatobiliary disease, plus coronary artery calcium , according to Eric J. Topol, MD, director associated with Scripps Study Translational Institute in La Jolla, California, and Medscape’s editor-in-chief.
Beyond retinas, interpretation of electrocardiograms (ECGs) might be an additional frontier meant for AI in primary care. In one trial , an AI-enhanced ECG reading facilitated earlier diagnosis of low ejection fraction, and some doctors now receive these reports routinely, Topol wrote.
The potential value associated with AI in medicine “extends to virtually all forms of medical pictures that have been assessed to date, ” Topol wrote upon his “Ground Truths” substack.
Although much of the focus has been on what AI can see, researchers also are exploring what AI can do with what it hears. Early research suggests that methods may become able in order to diagnose condition by examining patients’ voices .