Artificial intelligence improves outcomes of cognitive behavioral therapy in chronic pain: JAMA

USA: Use of artificial intelligence for adjusting treatment in cognitive behavioral therapy intervention for chronic pain (AI-CBT-CP) can achieve noninferior and possibly better outcomes relative to standard cognitive behavioral therapy while increasing access and reducing therapist costs, reports an article published in the JAMA Internal Medicine. 

Globally, approximately 1.5 billion people, suffer from chronic pain (CP), with prevalence increasing with age. Chronic pain can interfere with daily activities and may result in work interruption, emotional distress, and risky behaviors, including substance use. Cognitive behavioral therapy for chronic pain (CBT-CP) is a safe and effective alternative to opioid analgesics, but it requires multiple sessions and therapists are scarce, so many patients have limited access or fail to complete treatment. Researchers developed a CBT-CP intervention using reinforcement learning, a field of artificial intelligence (AI), and interactive voice response (IVR) calls artificial intelligence (AI). It automatically adjusts the modality of weekly therapist interactions based on patient feedback reported daily via interactive voice response (IVR.)

Piette JD, University of Michigan, Ann Arbor, and his colleagues conducted a randomized noninferiority, comparative effectiveness trial to determine if a CBT-CP program that personalizes patient treatment using artificial intelligence is noninferior to standard telephone CBT-CP and saves therapist time.

Researchers included 278 patients (mean [SD] age, 63.9 [12.2] years) with chronic back pain in the study. More patients were randomized to the AI-CBT-CP group than to the control (1.4:1) to maximize the system's ability to learn from patient interactions. All patients received 10 weeks of CBT-CP. For the AI-CBT-CP group, patient feedback via daily IVR calls was used by the AI engine to make weekly recommendations for either a 45-minute or 15-minute therapist-delivered telephone session or an individualized IVR-delivered therapist message. Patients in the comparison group were offered 10 therapist-delivered telephone CBT-CP sessions (45 minutes/session). The primary outcome was the Roland Morris Disability Questionnaire (RMDQ; range 0-24), measured at 3 months (primary endpoint) and 6 months. Secondary outcomes included pain intensity and pain interference.

Key findings of the study,

•  The mean RMDQ score difference between AI-CBT-CP and standard CBT-CP was −0.72 points and -1.24 points at 3-month and  6-month respectively; noninferiority criteria were met at both the 3- and 6-month endpoints.

• At 6 months RMDQ was (37% vs 19%) and pain intensity scores (29% vs 17%), indicated that a greater proportion of patients receiving AI-CBT-CP had clinically meaningful improvements.

• There were no significant differences in secondary outcomes.

• Pain therapy using AI-CBT-CP required less than half of the therapist's time as standard CBT-CP.

The authors conclude that despite using less therapist time, AI-CBT-CP achieved outcomes that were noninferior to standard CBT-CP. AI-CBT-CP interventions would allow many more patients to be served effectively by CBT-CP programs using the same number of therapists.

Reference:

Piette JD, Newman S, Krein SL, et al. Patient-Centered Pain Care Using Artificial Intelligence and Mobile Health Tools: A Randomized Comparative Effectiveness Trial. JAMA Intern Med. Published online August 08, 2022. doi:10.1001/jamainternmed.2022.3178