Patient-Centered Pain Care Using Artificial Intelligence and Mobile Health Tools

Cognitive behavioral therapy (CBT) is one of the most effective treatments for chronic back
pain. However, only half of Veterans have access to trained CBT therapists, and program
expansion is costly. Moreover, VA CBT programs consist of 10 weekly hour-long sessions
delivered using an approach that is out-of-sync with stepped-care models designed to ensure
that scarce resources are used as effectively and efficiently as possible. Data from prior
CBT trials have documented substantial variation in patients' needs for extended treatment,
and the characteristics of effective programs vary significantly. Some patients improve after
the first few sessions while others need more extensive contact. After initially establishing
a behavioral plan, still other Veterans may be able to reach behavioral and symptom goals
using a personalized combination of manuals, shorter follow-up contacts with a therapist, and
automated telephone monitoring and self-care support calls. In partnership with the National
Pain Management Program, the investigators propose to apply state-of-the-art principles from
"reinforcement learning" (a field of artificial intelligence or AI used successfully in
robotics and on-line consumer targeting) to develop an evidence-based, personalized CBT pain
management service that automatically adapts to each Veteran's unique and changing needs
(AI-CBT). AI-CBT will use feedback from patients about their progress in pain-related
functioning measured daily via pedometer step-counts to automatically personalize the
intensity and type of patient support; thereby ensuring that scarce therapist resources are
used as efficiently as possible and potentially allowing programs with fixed budgets to serve
many more Veterans. The specific aims of the study are to: (1) demonstrate that AI-CBT has
non-inferior pain-related outcomes compared to standard telephone CBT; (2) document that
AI-CBT achieves these outcomes with more efficient use of scarce clinician resources as
evidenced by less overall therapist time and no increase in the use of other VA health
services; and (3) demonstrate the intervention's impact on proximal outcomes associated with
treatment response, including program engagement, pain management skill acquisition,
satisfaction with care, and patients' likelihood of dropout. The investigators will use
qualitative interviews with patients, clinicians, and VA operational partners to ensure that
the service has features that maximize scalability, broad scale adoption, and impact. 278
patients with chronic back pain will be recruited from the VA Connecticut Healthcare System
and the VA Ann Arbor Healthcare System, and randomized to standard 10-sessions of telephone
CBT versus AI-CBT. All patients will begin with weekly hour-long telephone counseling, but
for patients in the AI-CBT group, those who demonstrate a significant treatment response will
be stepped down through less resource-intensive alternatives to hour-long contacts,
including: (a) 15 minute contacts with a therapist, and (b) CBT clinician feedback provided
via interactive voice response calls (IVR). The AI engine will learn what works best in terms
of patients' personally-tailored treatment plan based on daily feedback via IVR about
patients' pedometer-measured step counts as well as their CBT skill practice and physical
functioning. The AI algorithm the investigators will use is designed to be as efficient as
possible, so that the system can learn what works best for a given patient based on the
collective experience of other similar patients as well as the individual's own history. The
investigator's hypothesis is that AI-CBT will result in pain-related functional outcomes that
are no worse (and possibly better) than the standard approach, but by scaling back the
intensity of contact that is not resulting in marginal gains in pain control, the AI-CBT
approach will be significantly less costly in terms of therapy time. Secondary hypotheses are
that AI-CBT will result in greater patient engagement and patient satisfaction. Outcomes will
be measured at three and six months post recruitment and will include pain-related
interference, treatment satisfaction, and treatment dropout.

Inclusion Criteria:

- Back pain-related dx including back and spine conditions and nerve compression and a
score of >=4 (indicating moderate pain) on the 0-10 Numerical Rating Scale on at least
two separate outpatient encounters in the past year

- At least 1 outpatient visit in last 12 months

- At least moderate pain-related disability as determined by a score of 5+on the Roland
Morris Disability Questionnaire

- At least moderate musculoskeletal pain as indicated by a pain score of >=4 on the
Numeric Rating Scale

- Pain on at least half the days of the prior 6 months as reported on the Chronic Pain
item

- Touch-tone cell or land line phone.

Exclusion Criteria:

- COPD requiring oxygen

- Cancer requiring chemotherapy

- Currently receiving CBT

- Suicidality

- Receiving surgical tx related to back pain

- Active psychotic symptoms

- Severe depressive symptoms

- Can't speak English

- Sensory deficits that would impair participation in telephone calls

- Patient not planning to get care at study site

- PCP not affiliated with study site

- Limited life expectancy (COPD requiring oxygen or Cancer requiring chemotherapy

- Active psychotic symptoms, suicidality, severe depressive symptoms (Beck Depression
Inventory (BDI) score or 30+)

- Substance use disorder or dependence, active manic episode, or poorly controlled
bipolar disorder as identified by MMini International Neuropsychiatric Interview

- Severe depression identified by chart review of diagnoses and mental health treatment
notes

- Cognitive impairment defined by a score of <=5 on the Six-Item screener

- Current CBT or surgical treatment related to back pain.