Artificial Intelligence Decision Aid A Significant Benefit For Patients with OA Considering Knee Replacement

Patients with osteoarthritis (OA) of the knee who are thinking of undergoing total knee replacement (TKR) may benefit from an artificial intelligence (AI)-enabled decision aid, according to a randomized, clinical trial.

The prevalence of knee OA is on the rise, bringing with it an increased concern around healthcare spending. Treatments for knee OA vary widely, from weight loss and physical therapy to orthopedic surgery. Given the variety of choices for treatment, knee OA provides an opportunity for shared decision-making (SDM). Also of growing interest are patient-reported outcome measures (PROMs), which encompass the patient’s view of physical, emotional, and social aspects of health.

There were 129 new adult patients reporting OA-related knee pain at an academic orthopedic center. They randomly received a decision aid that consisted of patient education, preference assessment, and personalized outcome estimations or educational material only plus usual care. The groups were classified as intervention (n=69) and control (n=60), respectively. The main outcome, decision quality, was determined per the Knee OA Decision Quality Instrument (K-DQI). Other outcomes included collaborative decision-making (per the CollaboRATE survey), patient satisfaction with consultation (per a numerical rating scale), Knee Injury and Osteoarthritis Outcome Score Joint Replacement (KOOS JR) score, consultation time, TKR rate, and treatment concordance.

The main outcome was better in the intervention group, with a mean difference in K-DQI of 20% (SE, 3.02; 95% confidence interval [CI], 14.2-26.1%; P<0.001).

Regarding secondary outcomes, fewer intervention patients were below the median in terms of collaborative decision-making (12% vs. 47%; P<0.001) and satisfaction (14% vs. 33%; P=0.01), and intervention patients’ mean KOOS JR score was 4.9 points higher (95% CI, 0.8-9.0 points; P=0.02). Outcomes that did not largely differ between the groups were consultation, time, TKR rates, and treatment concordance.

“The findings of this study suggest that multifaceted decision aids integrating patient education, preference assessment, and AI-enabled analytics built with PROM data can provide a personalized, data-driven approach to SDM for patients with advanced knee OA considering TKR,” the researchers wrote in their conclusion. “The patient-centered, data-driven approach to SDM in this study may mark a step-change in the application of patient decision aids in orthopedic practice.”

The study was published in JAMA Network Open.