Editor’s note: ACR on Air, the official podcast of the ACR, dives into topics important to the rheumatology community, such as the latest research, solutions for practice management issues, legislative policies, patient care and more. Twice a month, host Jonathan Hausmann, MD, a pediatric and adult rheumatologist in Boston, interviews healthcare professionals and clinicians on the rheumatology front lines. In a series for The Rheumatologist, we provide highlights from these relevant conversations. Listen to the podcast online at acronair.org, or download and subscribe to ACR on Air wherever you get your podcasts. Here we highlight episode 80, “AI in Rheumatology,” which aired on July 2, 2024.
Just like other areas of medicine, rheumatology will increasingly rely on artificial intelligence (AI) for efficiency and better patient outcomes. However, there will still be room for the human touch, even if AI may affect some currently available jobs.
That was one of many AI observations shared by Suleman Bhana, MD, a board-certified rheumatologist in northern New Jersey who currently works for Pfizer Medical Affairs, in his conversation with Dr. Hausmann on an episode of ACR on Air.
Dr. Bhana noted there’s excitement around using AI for better diagnostics, disease prediction and patient management. At the same time, “nothing moves in the world without funding,” he said. Much of the funding for AI efforts comes from venture capital investors looking to profit from the system.
Dr. Bhana
“I think we want to be very cognizant that there are two different sides of this coin. Hopefully, it’s the side for patients and the people that take care of them is the side that wins, but we should always look at the other side of the coin, too,” he said.
During the podcast, Dr. Bhana focused on several areas in which AI is or will be used within rheumatology.
Diagnostics & Early Detection
The use of AI to evaluate images in radiology and oncology is already happening. There is some emerging research regarding AI and imaging for inflammatory arthritis, sacroiliac joint imaging for spondylarthritis and other areas of rheumatology, Dr. Bhana said.
“The idea for rheumatology is that AI can evaluate an X-ray of the hand and say, ‘This patient has osteoarthritis or rheumatoid arthritis or gout or psoriatic arthritis’ without a radiologist’s involvement,” Dr. Hausmann said.
Workplace Shortages
As the shortage of rheumatologists continues, especially in rural areas, AI may provide a remedy. Dr. Bhana gave the example of a patient who needs monitoring and may be able to go to a location where smartphone images can be taken—or they may be able take those images themselves under the right lighting and upload them online. An AI model could provide feedback about the person’s rheumatic condition.
“I think with any technology, we also have to make sure there are safeguards for equity in patients and that there isn’t bias that’s creeping in there,” Dr. Bhana said.
He gave the example of cutaneous lupus flares, which present differently in patients who are Black when compared with those who are white. An AI model would need to have recognition models across skin tones.
Disease Prediction
Better disease prediction is an area in which the use of big data may come into play.
“Imaging is a piece of it, but then you can integrate all this data that’s floating around in data warehouses, like clinical records, lab markers, genomics, and then incorporate that along with population-based data,” Dr. Bhana said.
By using information, such as multiomics and symptoms, and placing that in large language models, AI may help the rheumatologist predict disease outset, flares and management.
“That’s coming, but I think a lot of this comes into the battle between who has the data? Where’s the data coming from? What’s the purity of the data? What’s the cost of it going to be to leverage these different warehouses and synthesize and integrate them?” he said.
Rheumatologists and other clinicians may already use AI to help review signs and symptoms or develop a differential diagnosis, Dr. Hausmann noted. On the flip side, some patients look up their symptoms online and get AI-generated feedback—some of which may be accurate and some of which may be wrong or even harmful.
The challenge going forward will be to preserve the human role in shaping this information vs. a techno-autocracy, Dr. Bhana said.
Remote Patient Monitoring
Remote patient monitoring is more common in cardiology, with the use of defibrillators and pacemakers that can hook into telemedicine clinics for monitoring, Dr. Bhana said. Although it’s not yet common in rheumatology, the future may bring the use of smartwatch accelerometer data to detect if a patient’s gait is changing or if they’re having falls. Depending on what’s happening, this type of monitoring may trigger an earlier return to the provider’s office for a check-up.
Treatment Optimization
The rheumatology world would likely welcome a more personalized approach to personalized medicine, Dr. Bhana noted.
“Can you use large data models of proteomics and try to figure out therapeutic targets that were not seen before?” he said.
Dr. Hausmann gives the example of deciding if an interleukin 6, Janus kinase or tumor necrosis factor (TNF) inhibitor may be better for a patient vs. assuming methotrexate or a TNF inhibitor would work for a patient. AI with such data sets may be more efficient than the current trial-and-error approach to medications that is used now to find the right mix for patients.
Burnout
With all of these uses, another hope is that AI can help thwart off burnout due to administrative burdens. Example: AI is already implemented but may be used more frequently to take notes during patient encounters.
“If that helps you get through your day easier, then maybe you have more time for patients,” Dr. Bhana said. However, he wonders if that use would lead to trying to squeeze more patients into any extra time created.
In the future, AI may be able to directly order X-ray or prescriptions, as indicated in the notes from the patient encounter, Dr. Bhana said.
Looking forward five years, Dr. Bhana would like to see rheumatologists taking even better care of patients as they are able to provide a faster diagnosis thanks to AI and potentially see a rheumatologist sooner. After patients start treatment, that treatment and their status may be monitored in a more effective way, and patients may have a more normal life instead of suffering with illness.
“On the preventive medicine end, you would hope that we will have more insights as to what it means to live a healthy life, what causes disease and illness, and how can people who may be at risk be identified early and have interventions made so they don’t go on to develop [disease],” he said.
Vanessa Caceres is a medical writer in Bradenton, Fla.
