REACT (AI CBT): Patient-Centered Pain Care Using Artificial Intelligence and Mobile Health Tools

• Sponsor: VA Office of Research and Development (U.S. Fed)
• Overall Status: Completed
• CT.gov ID: NCT02464449
• Collaborator: (none)
• Enrollment: 278
• Locations: 2
• Arms: 2
• Actual Duration (Months): 33.2
• Patients Per Site: 139
• Patients Per Site Per Month: 4.2

Study Details

Study Description

Brief Summary

This study will evaluate a new approach for back pain care management using artificial intelligence and evidence-based cognitive behavioral therapy (AI-CBT) so that services automatically adapt to each Veteran's unique needs, achieving outcomes as good as standard care but with less clinician time.

Condition or Disease	Intervention/Treatment	Phase
Back Pain	Behavioral: Behavioral: AI-CBT; Behavioral: Behavioral: Standard Telephone CBT	N/A

Detailed Description

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.

Study Design

• Study Type: Interventional
• Actual Enrollment: 278 participants
• Allocation: Randomized
• Intervention Model: Parallel Assignment
• Masking: None (Open Label)
• Primary Purpose: Health Services Research
• Official Title: Patient-Centered Pain Care Using Artificial Intelligence and Mobile Health Tools
• Actual Study Start Date: Jul 24, 2017
• Actual Primary Completion Date: Apr 30, 2020
• Actual Study Completion Date: Apr 30, 2020

Arms and Interventions

Arm	Intervention/Treatment
Experimental: AI CBT AI CBT engine will make recommendations to step-down or step-up intensity of CBT FU based on what patient reports and what other similar patients report. Stepped care model.	Behavioral: Behavioral: AI-CBT; AI CBT engine will make recommendations to step-down or step-up intensity of CBT follow-up based on what patient reports and what other similar patients report. Stepped care model.
Active Comparator: Standard telephone CBT Controls receive 10 hour-long standard telephone CBT sessions, a pedometer/log after baseline, and a Patient Handbook.	Behavioral: Behavioral: Standard Telephone CBT; Controls receive 10 hour-long standard telephone CBT sessions, a pedometer/log after baseline, and a Patient Handbook.

Outcome Measures

Primary Outcome Measures

1. Pain-related Disability [3 and 6 months post enrollment]

   The Roland Morris Disability Questionnaire (RMDQ) is a 24-item checklist designed for patients to identify the level of disability and functional status associated with chronic low back pain. Patients are instructed to endorse items that describe their functional status that day. Scores range from 0-24, with higher scores indicating more disability.

Secondary Outcome Measures

1. Global Pain Intensity [3 and 6 months post enrollment]

   An 11-point Numeric Rating Scale (NRS) for pain severity, with 0 representing "No pain" and 10 representing the "Worst pain imaginable." Patients were asked to rate their level of pain on average in the last week.

2. Pain-Related Interference [3 and 6 months post enrollment]

   Pain-related interference was measured using the Brief Pain Inventory - Short Form (BPI). Scores range from 0-10, with higher scores indicating more interference.

3. Depression Symptom Severity [3 and 6 months post enrollment]

   Depression symptom severity was assessed using the 9-item Patient Health Questionnaire (PHQ-9). Scores range from 0-27, with higher scores indicating more depression symptom severity.

Eligibility Criteria

Criteria

• Ages Eligible for Study: 18 Years and Older
• Sexes Eligible for Study: All
• Accepts Healthy Volunteers: No

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.

Contacts and Locations

Locations

	Site	City	State	Country	Postal Code
1	VA Connecticut Healthcare System West Haven Campus, West Haven, CT	West Haven	Connecticut	United States	06516
2	VA Ann Arbor Healthcare System, Ann Arbor, MI	Ann Arbor	Michigan	United States	48105

Sponsors and Collaborators

• VA Office of Research and Development

Investigators

• Principal Investigator: John D. Piette, PhD, VA Ann Arbor Healthcare System, Ann Arbor, MI
• Principal Investigator: Alicia A. Heapy, PhD, VA Connecticut Healthcare System West Haven Campus, West Haven, CT

Study Documents (Full-Text)

• Study Protocol and Statistical Analysis Plan - Dec 14, 2018

More Information

Publications

None provided.

• Responsible Party: VA Office of Research and Development
• ClinicalTrials.gov Identifier: NCT02464449
• Other Study ID Numbers: IIR 13-350
• First Posted: Jun 8, 2015
• Last Update Posted: Sep 2, 2021
• Last Verified: Aug 1, 2021

• Individual Participant Data (IPD) Sharing Statement: No
• Plan to Share IPD: No
• Studies a U.S. FDA-regulated Drug Product: No
• Studies a U.S. FDA-regulated Device Product: No
• Product Manufactured in and Exported from the U.S.: No
• Keywords provided by VA Office of Research and Development: Cognitive Behavioral Therapy; Mobile Health Technology; Patient Care Management
• Additional relevant MeSH terms: Back Pain

Study Results

Participant Flow

Arm/Group Title	AI CBT	Standard Telephone CBT
Arm/Group Description	AI CBT engine will make recommendations to step-down or step-up intensity of CBT FU based on what patient reports and what other similar patients report. Stepped care model. Behavioral: AI-CBT: AI CBT engine will make recommendations to step-down or step-up intensity of CBT follow-up based on what patient reports and what other similar patients report. Stepped care model.	Controls receive 10 hour-long standard telephone CBT sessions, a pedometer/log after baseline, and a Patient Handbook. Behavioral: Standard Telephone CBT: Controls receive 10 hour-long standard telephone CBT sessions, a pedometer/log after baseline, and a Patient Handbook.
Period Title: Overall Study
STARTED	166	112
COMPLETED	151	100
NOT COMPLETED	15	12

Baseline Characteristics

Arm/Group Title	AI CBT	Standard Telephone CBT	Total
Arm/Group Description	AI CBT engine will make recommendations to step-down or step-up intensity of CBT FU based on what patient reports and what other similar patients report. Stepped care model. Behavioral: AI-CBT: AI CBT engine will make recommendations to step-down or step-up intensity of CBT follow-up based on what patient reports and what other similar patients report. Stepped care model.	Controls receive 10 hour-long standard telephone CBT sessions, a pedometer/log after baseline, and a Patient Handbook. Behavioral: Standard Telephone CBT: Controls receive 10 hour-long standard telephone CBT sessions, a pedometer/log after baseline, and a Patient Handbook.	Total of all reporting groups
Overall Participants	166	112	278
Age (years) [Mean (Standard Deviation) ]
Mean (Standard Deviation) [years]	62.8 (13.1)	65.6 (10.6)	63.9 (12.2)
Sex: Female, Male (Count of Participants)
Female	21 12.7%	9 8%	30 10.8%
Male	145 87.3%	103 92%	248 89.2%
Ethnicity (NIH/OMB) (Count of Participants)
Hispanic or Latino	6 3.6%	7 6.3%	13 4.7%
Not Hispanic or Latino	160 96.4%	105 93.8%	265 95.3%
Unknown or Not Reported	0 0%	0 0%	0 0%
Race (NIH/OMB) (Count of Participants)
American Indian or Alaska Native	0 0%	0 0%	0 0%
Asian	0 0%	0 0%	0 0%
Native Hawaiian or Other Pacific Islander	0 0%	0 0%	0 0%
Black or African American	27 16.3%	10 8.9%	37 13.3%
White	131 78.9%	94 83.9%	225 80.9%
More than one race	8 4.8%	7 6.3%	15 5.4%
Unknown or Not Reported	0 0%	1 0.9%	1 0.4%
Pain-related Disability (units on a scale) [Mean (Standard Deviation) ]
Mean (Standard Deviation) [units on a scale]	13.7 (4.1)	13.5 (4.2)	13.6 (4.1)
Global Pain Intensity (units on a scale) [Mean (Standard Deviation) ]
Mean (Standard Deviation) [units on a scale]	6.2 (1.6)	6.3 (1.4)	6.2 (1.5)
Pain-Related Interference (units on a scale) [Mean (Standard Deviation) ]
Mean (Standard Deviation) [units on a scale]	4.9 (2.2)	5.0 (2.1)	4.9 (2.1)
Depression Symptom Severity (units on a scale) [Mean (Standard Deviation) ]
Mean (Standard Deviation) [units on a scale]	6.3 (5.2)	6.6 (5.1)	6.5 (5.1)

Outcome Measures

1. Primary Outcome

Title	Pain-related Disability
Description	The Roland Morris Disability Questionnaire (RMDQ) is a 24-item checklist designed for patients to identify the level of disability and functional status associated with chronic low back pain. Patients are instructed to endorse items that describe their functional status that day. Scores range from 0-24, with higher scores indicating more disability.
Time Frame	3 and 6 months post enrollment

Outcome Measure Data

Analysis Population Description

The number analyzed in rows differs because some participants did not complete the questionnaire at all time points.

Arm/Group Title	AI CBT	Standard Telephone CBT
Arm/Group Description	AI CBT engine will make recommendations to step-down or step-up intensity of CBT FU based on what patient reports and what other similar patients report. Stepped care model. Behavioral: AI-CBT: AI CBT engine will make recommendations to step-down or step-up intensity of CBT follow-up based on what patient reports and what other similar patients report. Stepped care model.	Controls receive 10 hour-long standard telephone CBT sessions, a pedometer/log after baseline, and a Patient Handbook. Behavioral: Standard Telephone CBT: Controls receive 10 hour-long standard telephone CBT sessions, a pedometer/log after baseline, and a Patient Handbook.
Measure Participants	151	100
3 months post enrollment	11.0 (6.1)	11.3 (5.1)
6 months post enrollment	11.0 (5.9)	12.6 (5.3)

2. Secondary Outcome

Title	Global Pain Intensity
Description	An 11-point Numeric Rating Scale (NRS) for pain severity, with 0 representing "No pain" and 10 representing the "Worst pain imaginable." Patients were asked to rate their level of pain on average in the last week.
Time Frame	3 and 6 months post enrollment

Outcome Measure Data

Analysis Population Description

The number analyzed in rows differs because some participants did not complete the questionnaire at all time points.

Arm/Group Title	AI CBT	Standard Telephone CBT
Arm/Group Description	AI CBT engine will make recommendations to step-down or step-up intensity of CBT FU based on what patient reports and what other similar patients report. Stepped care model. Behavioral: AI-CBT: AI CBT engine will make recommendations to step-down or step-up intensity of CBT follow-up based on what patient reports and what other similar patients report. Stepped care model.	Controls receive 10 hour-long standard telephone CBT sessions, a pedometer/log after baseline, and a Patient Handbook. Behavioral: Standard Telephone CBT: Controls receive 10 hour-long standard telephone CBT sessions, a pedometer/log after baseline, and a Patient Handbook.
Measure Participants	151	100
3 months post enrollment	5.1 (2.0)	5.0 (1.8)
6 months post enrollment	5.3 (1.9)	5.7 (1.9)

3. Secondary Outcome

Title	Pain-Related Interference
Description	Pain-related interference was measured using the Brief Pain Inventory - Short Form (BPI). Scores range from 0-10, with higher scores indicating more interference.
Time Frame	3 and 6 months post enrollment

Outcome Measure Data

Analysis Population Description

The number analyzed in rows differs because some participants did not complete the questionnaire at all time points.

Arm/Group Title	AI CBT	Standard Telephone CBT
Arm/Group Description	AI CBT engine will make recommendations to step-down or step-up intensity of CBT FU based on what patient reports and what other similar patients report. Stepped care model. Behavioral: AI-CBT: AI CBT engine will make recommendations to step-down or step-up intensity of CBT follow-up based on what patient reports and what other similar patients report. Stepped care model.	Controls receive 10 hour-long standard telephone CBT sessions, a pedometer/log after baseline, and a Patient Handbook. Behavioral: Standard Telephone CBT: Controls receive 10 hour-long standard telephone CBT sessions, a pedometer/log after baseline, and a Patient Handbook.
Measure Participants	151	100
3 months post enrollment	3.9 (2.4)	3.8 (2.1)
6 months post enrollment	3.9 (2.3)	4.5 (2.6)

4. Secondary Outcome

Title	Depression Symptom Severity
Description	Depression symptom severity was assessed using the 9-item Patient Health Questionnaire (PHQ-9). Scores range from 0-27, with higher scores indicating more depression symptom severity.
Time Frame	3 and 6 months post enrollment

Outcome Measure Data

Analysis Population Description

The number analyzed in rows differs because some participants did not complete the questionnaire at all time points.

Arm/Group Title	AI CBT	Standard Telephone CBT
Arm/Group Description	AI CBT engine will make recommendations to step-down or step-up intensity of CBT FU based on what patient reports and what other similar patients report. Stepped care model. Behavioral: AI-CBT: AI CBT engine will make recommendations to step-down or step-up intensity of CBT follow-up based on what patient reports and what other similar patients report. Stepped care model.	Controls receive 10 hour-long standard telephone CBT sessions, a pedometer/log after baseline, and a Patient Handbook. Behavioral: Standard Telephone CBT: Controls receive 10 hour-long standard telephone CBT sessions, a pedometer/log after baseline, and a Patient Handbook.
Measure Participants	151	100
3 months post enrollment	6.7 (5.3)	6.7 (5.1)
6 months post enrollment	6.8 (5.1)	7.5 (6.0)

Adverse Events

Time Frame	During the intervention period (approximately 10 weeks of the standard telephone CBT or the AI CBT).
Arm/Group Title	AI CBT		Standard Telephone CBT
Arm/Group Description	AI CBT engine will make recommendations to step-down or step-up intensity of CBT FU based on what patient reports and what other similar patients report. Stepped care model. Behavioral: AI-CBT: AI CBT engine will make recommendations to step-down or step-up intensity of CBT follow-up based on what patient reports and what other similar patients report. Stepped care model.		Controls receive 10 hour-long standard telephone CBT sessions, a pedometer/log after baseline, and a Patient Handbook. Behavioral: Standard Telephone CBT: Controls receive 10 hour-long standard telephone CBT sessions, a pedometer/log after baseline, and a Patient Handbook.
All Cause Mortality
	AI CBT		Standard Telephone CBT
	Affected / at Risk (%)	# Events	Affected / at Risk (%)	# Events
Total	0/166 (0%)		0/112 (0%)
Serious Adverse Events
	AI CBT		Standard Telephone CBT
	Affected / at Risk (%)	# Events	Affected / at Risk (%)	# Events
Total	5/166 (3%)		3/112 (2.7%)
Cardiac disorders
Chest pain	1/166 (0.6%)	1	0/112 (0%)	0
Gastrointestinal disorders
Emesis	0/166 (0%)	0	1/112 (0.9%)	1
General disorders
Heat stroke	0/166 (0%)	0	1/112 (0.9%)	1
Infections and infestations
Infection	2/166 (1.2%)	2	1/112 (0.9%)	1
Respiratory, thoracic and mediastinal disorders
Shortness of breath	1/166 (0.6%)	1	0/112 (0%)	0
Vascular disorders
Stroke	1/166 (0.6%)	1	0/112 (0%)	0
Other (Not Including Serious) Adverse Events
	AI CBT		Standard Telephone CBT
	Affected / at Risk (%)	# Events	Affected / at Risk (%)	# Events
Total	0/166 (0%)		0/112 (0%)

Limitations/Caveats

[Not Specified]

More Information

Certain Agreements

All Principal Investigators ARE employed by the organization sponsoring the study.

There is NOT an agreement between Principal Investigators and the Sponsor (or its agents) that restricts the PI's rights to discuss or publish trial results after the trial is completed.