Predictive tool fails to improve patient preference and decision quality about TKA surgery: JAMA

The findings, published in JAMA Network Open, indicate the need for additional research to optimize patient decision-making in total knee arthroplasty (TKA).

Rapid advancements in artificial intelligence (AI) technologies have led to the development of several clinical predictive tools, including those for patients with knee osteoarthritis considering TKA. While there is a quick progression of the integration of predictive tools into clinical practice, few of those tools have undergone rigorous evaluation through RCTs. Consequently, the effectiveness of these tools in surgical decision-making remains uncertain for both patients and clinicians.

Against the above background, Yushy Zhou, The University of Melbourne, Melbourne, Victoria, Australia, and colleagues aimed to assess the effect of an online predictive tool on patient-reported willingness to undergo total knee arthroplasty.

For this purpose, the researchers conducted a parallel, double-masked, 2-arm randomized clinical trial comparing predictive tool use with treatment as usual (TAU) between 2022 and 2023. After enrollment, participants were followed up for six months.

Participants were recruited from a major Australian private health insurance company and the surgical waiting list for publicly funded TKA at a tertiary hospital. Eligible participants had unilateral knee osteoarthritis, were contemplating TKA, and had tried previously nonsurgical interventions, such as physiotherapy, lifestyle modifications, and pain medications.

The intervention group was provided access to an online predictive tool at the study's beginning. The tool offered information concerning the likelihood of improvement in quality of life (QoL) if patients chose to undergo TKA. The predictions were based on the patient’s sex, age, and baseline symptoms. The control group received TAU without access to the predictive tool.

The study's primary outcome measure was a reduction in the willingness of the patient to undergo surgery at six months after tool use, which was measured using binomial logistic regression. Secondary outcome measures were the quality of their decision-making process as measured by the Knee Decision Quality Instrument and participant treatment preference.

The following were the key findings of the study:

• Of 211 randomized participants (mean age, 65.8 years; 55.9% females), 105 were allocated to the predictive tool group and 106 to the TAU group.
• After adjusting for baseline differences in willingness for surgery, the predictive tool did not significantly reduce the primary outcome of willingness for surgery at six months (adjusted odds ratio, 0.85).

"Predictive tools might still enhance health outcomes of patients with knee osteoarthritis despite the absence of treatment effect on willingness for TKA," the researchers wrote.

"Additional research is needed to optimize the implementation and design of predictive tools, address limitations, and fully understand their impact on the decision-making process in TKA," they concluded.

Reference:

Zhou Y, Patten L, Spelman T, et al. Predictive Tool Use and Willingness for Surgery in Patients With Knee Osteoarthritis: A Randomized Clinical Trial. JAMA Netw Open. 2024;7(3):e240890. doi:10.1001/jamanetworkopen.2024.0890