The rheumatologist of the future will see patients who have been assessed and triaged with artificial intelligence utilizing data from remote kiosk-placed ultrasound scanners and physician-directed algorithms. Practices will be broadly fueled by AI, which will screen charts, produce notes, handle prior authorizations and insurance issues, aid in earlier diagnoses, find patients for clinical trials, and maybe even suggest the next best therapy for individual patients.

Such is the future envisioned by Alvin F. Wells, MD, PhD, and John J. Cush, MD, who discussed the current and forthcoming reach of AI — and their own uses of it — at the 2024 Rheumatology Winter Clinical Symposium.

“We’re not at the stage where ChatGPT and AI can tell us what the next best therapy is, but we’re getting there,” said Dr. Cush, a rheumatologist based in Dallas and executive director of RheumNow.com. For now, he said, “AI affords us a truly big-time increase in efficiency. It helps you deal with your time constraints in managing information overload and task overload.”

At a time when “PubMed doubles every 73 days ... and it’s getting harder and harder to stay abreast,” for example, new applications such as Scite, SciSpace, and Consensus can help curate, focus, and analyze the literature to match one’s own clinical interests. Such review tools are “just now getting into play and are evolving,” Dr. Cush said, noting that many but not all of them are based on ChatGPT, OpenAI’s chatbot that had a over 100 million users by January 2023 — just over a month after its version 3.5 was released.

For Dr. Wells, a rheumatologist and Midwest Region director in the department of rheumatology for the Advocate Health Medical Group in Franklin, Wisconsin, clinician-developed algorithms are helping his group assess patients — often remotely — and triage them to be seen fairly immediately by a rheumatologist versus in 4-6 weeks or in several months. “You can use AI to guide your access,” he said.

A patient “with a family history of RA, sed rate above 50, and osteopenia on x-rays” would be seen within a week, for example, while “another patient who’s had a [positive] ANA with no other symptoms, and maybe a family history, might be seen in 4-6 weeks,” said Dr. Wells, sharing his belief that “there is not a shortage of rheumatologists, [but a] shortage of using rheumatologists efficiently.”

AI for Improving Workflow

Current and future advances will enrich the intersection of AI and virtual medicine and improve outcomes and the rheumatologist-patient interaction, Dr. Wells said, pointing to research presented at the American College of Rheumatology (ACR) 2023 annual meeting on the use of computer vision technology for remotely assessing disease activity in rheumatoid arthritis (RA).

In the proof-of-concept “MeFisto” study, 28 patients with RA used an app that enabled computer vision inference of hand motion data. Upon recording, an algorithm tracked the mean degree change of joint angle on flexion and the mean time to maximal flexion for each joint.

The researchers found a strong correlation between flexion of the distal interphalangeal (DIP) joint and the Disease Activity Score in 28 joints, the Swollen Hand Joint Count, and the Tender Hand Joint Count. DIP flexion was found to be a significant predictor of low disease activity/remission and high disease activity, the researchers reported in their abstract.

“This blows you away — that a single camera on [one’s] smartphone can look at the manipulation of a hand … and that AI can tell me, there’s a chance this might be an inflammatory arthritis,” said Dr. Wells, noting that researchers are also developing ways to detect joint swelling in RA by AI.

AI can also be used for remote ultrasound scanning in RA, as evidenced by use of the ARTHUR system in Europe, he said. Developed by the Danish company ROPCA, the ARTHUR technology (Rheumatoid Arthritis Ultrasound Robot) interacts directly with the patient who has new joint pain or established RA to capture ultrasound images in grayscale and color flow of 11 joints per hand. AI analyzes the images and creates a report for the specialist.

“They’re trying to get a foothold in the US,” Dr. Wells said, sharing his prediction that similar technology will someday be seen not only in pharmacies but also — in support of equitable access — in locations such as grocery stores. “Again,” he said, “nothing will replace us. I’m taking all [such] information and saying, who needs to be seen in 7 days and who can wait.”