AI-Guided Pain Care Might Work as Well as Phone Therapy
Cognitive behavioral therapy for chronic pain (CBT-CP) is a safe and effective alternative to opioid analgesics for pain treatment. However, because CBT-CP requires multiple sessions and therapists are scarce, many patients have limited access or fail to complete treatment. To improve access to CBT-CP, HSR&D investigators developed an intervention using individually tailored interactive voice response (IVR) calls to deliver CBT-CP content and therapist feedback (JAMA Internal Medicine). As a follow-up to this advance in pain research, investigators in this study developed a CBT-CP intervention using artificial intelligence (AI) to automatically adjust the modality of weekly therapist interactions based on patient feedback reported daily via IVR. This randomized comparative effectiveness trial evaluated this intervention (AI-CBT-CP) relative to therapist-delivered telephone CBT-CP (45-minute telephone sessions over 10 weeks) provided in the REACT (Responsive, Efficient, Accessible Chronic Pain Technology) trial. Investigators identified 278 Veterans with chronic low back pain, who were then randomized to standard 10 sessions of telephone CBT versus AI-CBT. The primary outcome was the Roland Morris Disability Questionnaire (RMDQ). Outcomes were measured via telephone or mailed surveys at three months (primary outcome) and six months post-baseline. Secondary outcomes included pain intensity and pain interference. Sociodemographics were self-reported.
- Veterans with chronic back pain randomized to 10 weeks of AI-CBT-CP had noninferior outcomes for pain-related functioning and pain intensity at three months post-baseline compared with Veterans randomized to 10 weeks of 45-minute telephone sessions with a CBT-CP therapist.
- At six months substantially more Veterans who experienced AI-CBT-CP compared to standard CBT-CP reported clinically meaningful improvements in physical function and pain intensity.
- Even though both interventions were delivered by telephone, patients in the AI-CBT-CP group were less likely to miss weekly sessions.
- Compared with the standard CBT-Chronic Pain intervention, the use of individual tailored interactive voice response (IVR) and brief therapist contacts among the AI-CBT-CP group translated into a substantial reduction in therapist time. Thus, interventions like AI-CBT-CP could allow many more Veterans to be served effectively by CBT-CP programs using the same number of therapists.
- Future studies should seek to maximize the experience of AI-CBT-CP through trials with larger populations and quantify more precisely the influence of program learning on patient health status.
- The results of both interventions (AI-CBT-CP and standard CBT-CP) were relatively modest.
- Outcomes were self-reported.
This study was funded by HSR&D (IIR 13-350). Drs. Piette, Newman, and Krein are part of HSR&D’s Center for Clinical Management Research (CCMR), Ann Arbor, MI.
Piette J, Newman S, Krein S, et al. Patient-Centered Pain Care Using Artificial Intelligence and Mobile Health Tools: A Randomized Comparative Effectiveness Trial. JAMA Internal Medicine. September 1, 2022;182(9):975-83.