Study: AI-Based Treatment May Benefit Patients with Chronic Pain

A new study shows that cognitive based therapy for chronic pain (CBT-CP) that uses artificial intelligence to adjustment treatment (AI-CBT-CP) is a viable option for patients. The findings were reported in JAMA Internal Medicine.

In this randomized noninferiority, comparative effectiveness trial, researchers assessed 278 patients with chronic back pain from the Department of Veterans Affairs health system. The entire population of interest received CBT-CT. In order to gain an optimal understanding of patient interactions, more patients were randomized to AI-CBT-CP than to the control. The AI-CBT-CP consisted of patient feedback via daily interactive voice response (IVR) calls, which an AI engine used to recommend telephone therapy sessions over either 15 minutes or 45 minutes. The primary outcome of interest was the Roland Morris Disability Questionnaire, which was measured every three months. Secondary outcomes were defined as pain intensity and pain interference.

According to the results, more patients receiving AI-CBT-CP demonstrated clinically meaningful improvements at 6 months as measured by RMDQ (37% vs 19%; P = .01) and pain intensity scores (29% vs 17%; P = .03) compared to the control arm. The researchers did not observe any significant differences in secondary outcomes. They noted that therapy using AI-CBT-CP required less than half of the therapist time as standard CBT-CP.

“The findings of this randomized comparative effectiveness trial indicated that AI-CBT-CP was noninferior to therapist-delivered telephone CBT-CP and required substantially less therapist time. Interventions like AI-CBT-CP could allow many more patients to be served effectively by CBT-CP programs using the same number of therapists,” the researchers concluded.