Trial Outcomes & Findings for Woebot for Substance Use Disorders (NCT NCT04096001)
NCT ID: NCT04096001
Last Updated: 2022-08-31
Results Overview
The AUDIT-C is a widely used 3-item self-report screen for hazardous or harmful alcohol consumption that is based off of the 10-item original AUDIT. The AUDIT-C is scored on a scale of 0-12 (scores of 0 reflect no alcohol use). In men, a score of 4 or more is considered positive; in women, a score of 3 or more is considered positive. Generally, the higher the AUDIT-C score, the more likely it is that the patient's drinking is affecting his/her health and safety.
Recruitment status
COMPLETED
Study phase
PHASE1
Target enrollment
101 participants
Primary outcome timeframe
Change from Baseline to Post-treatment at 8 weeks
Results posted on
2022-08-31
Participant Flow
Participant milestones
| Measure |
Woebot-SUDs (W-SUDs)
Woebot-SUDs (W-SUDS), an artificially intelligence-powered conversational agent on a smartphone app, eliminates most current SUDs treatment barriers while simultaneously leveraging technology to enhance user experience and engagement. W-SUDs expands and refines existing SUDs treatments by adapting skills from cognitive behavioral therapy, motivational interviewing, and dialectical behavior therapy.
|
|---|---|
|
Overall Study
STARTED
|
101
|
|
Overall Study
COMPLETED
|
51
|
|
Overall Study
NOT COMPLETED
|
50
|
Reasons for withdrawal
Withdrawal data not reported
Baseline Characteristics
The overall number of participants analyzed N=101, where n=24 men and n=77 women.
Baseline characteristics by cohort
| Measure |
Woebot-SUDs (W-SUDs)
n=101 Participants
Woebot-SUDs (W-SUDS), an artificially intelligence-powered conversational agent on a smartphone app, eliminates most current SUDs treatment barriers while simultaneously leveraging technology to enhance user experience and engagement. W-SUDs expands and refines existing SUDs treatments by adapting skills from cognitive behavioral therapy, motivational interviewing, and dialectical behavior therapy.
|
|---|---|
|
Age, Continuous
|
36.8 years
STANDARD_DEVIATION 10.0 • n=101 Participants
|
|
Sex: Female, Male
Female
|
77 Participants
n=101 Participants
|
|
Sex: Female, Male
Male
|
24 Participants
n=101 Participants
|
|
Ethnicity (NIH/OMB)
Hispanic or Latino
|
9 Participants
n=101 Participants
|
|
Ethnicity (NIH/OMB)
Not Hispanic or Latino
|
92 Participants
n=101 Participants
|
|
Ethnicity (NIH/OMB)
Unknown or Not Reported
|
0 Participants
n=101 Participants
|
|
Race (NIH/OMB)
American Indian or Alaska Native
|
2 Participants
n=101 Participants
|
|
Race (NIH/OMB)
Asian
|
3 Participants
n=101 Participants
|
|
Race (NIH/OMB)
Native Hawaiian or Other Pacific Islander
|
0 Participants
n=101 Participants
|
|
Race (NIH/OMB)
Black or African American
|
4 Participants
n=101 Participants
|
|
Race (NIH/OMB)
White
|
80 Participants
n=101 Participants
|
|
Race (NIH/OMB)
More than one race
|
6 Participants
n=101 Participants
|
|
Race (NIH/OMB)
Unknown or Not Reported
|
6 Participants
n=101 Participants
|
|
Marital status
Married or cohabitating or partnered
|
54 Participants
n=101 Participants
|
|
Marital status
Divorced or separated or widowed
|
14 Participants
n=101 Participants
|
|
Marital status
Single or never married
|
33 Participants
n=101 Participants
|
|
Employment status
Employed full-time
|
62 Participants
n=101 Participants
|
|
Employment status
Employed part-time
|
11 Participants
n=101 Participants
|
|
Employment status
Unemployed, job-seeking
|
12 Participants
n=101 Participants
|
|
Employment status
Other (eg, retired, disabled, homemaker, and student)
|
16 Participants
n=101 Participants
|
|
COVID-19 situation
Sheltering in place, lockdown, quarantined
|
99 Participants
n=101 Participants
|
|
COVID-19 situation
No restrictions
|
2 Participants
n=101 Participants
|
|
Lifetime psychiatric diagnoses
Unipolar depression
|
45 participants
n=101 Participants
|
|
Lifetime psychiatric diagnoses
Bipolar or manic depression
|
10 participants
n=101 Participants
|
|
Lifetime psychiatric diagnoses
Anxiety disorder
|
49 participants
n=101 Participants
|
|
Lifetime psychiatric diagnoses
Posttraumatic stress disorder
|
19 participants
n=101 Participants
|
|
Lifetime psychiatric diagnoses
Attention deficit hyperactivity disorder
|
15 participants
n=101 Participants
|
|
Lifetime psychiatric diagnoses
Other (eg, obsessive compulsive disorder, eating disorder, and personality disorder)
|
12 participants
n=101 Participants
|
|
Lifetime psychiatric diagnoses
Substance use disorder
|
6 participants
n=101 Participants
|
|
Lifetime psychiatric diagnoses
Multiple psychiatric diagnoses
|
48 participants
n=101 Participants
|
|
Lifetime psychiatric diagnoses
No lifetime psychiatric diagnoses
|
28 participants
n=101 Participants
|
|
Therapy experience
Never
|
30 participants
n=101 Participants
|
|
Therapy experience
Formerly
|
45 participants
n=101 Participants
|
|
Therapy experience
Currently
|
26 participants
n=101 Participants
|
|
Therapy experience
Currently taking psychiatric medication
|
44 participants
n=101 Participants
|
|
Patient Health Questionnaire-8 item depression
|
10.8 units on a scale
STANDARD_DEVIATION 5.8 • n=101 Participants
|
|
General Anxiety Disorder-7 item anxiety
|
9.6 units on a scale
STANDARD_DEVIATION 5.7 • n=101 Participants
|
|
Pain intensity in the past 7 days (possible range 0-100)
|
20.4 units on a scale
STANDARD_DEVIATION 22.3 • n=101 Participants
|
|
Pain interfere with normal work in the past 30 days
Not at all
|
60 Participants
n=101 Participants
|
|
Pain interfere with normal work in the past 30 days
A little bit
|
23 Participants
n=101 Participants
|
|
Pain interfere with normal work in the past 30 days
Moderately
|
9 Participants
n=101 Participants
|
|
Pain interfere with normal work in the past 30 days
Quite a bit
|
7 Participants
n=101 Participants
|
|
Pain interfere with normal work in the past 30 days
Extremely
|
2 Participants
n=101 Participants
|
|
Primary substance
Alcohol
|
69 Participants
n=101 Participants
|
|
Primary substance
Cannabis
|
20 Participants
n=101 Participants
|
|
Primary substance
Stimulants or cocaine
|
7 Participants
n=101 Participants
|
|
Primary substance
Other (eg, club drugs, pain killers, and sedatives)
|
5 Participants
n=101 Participants
|
|
Primary substance
Indicated multi-substances
|
37 Participants
n=101 Participants
|
|
Past 30 days of substance use
Alcohol
|
88 Participants
n=101 Participants
|
|
Past 30 days of substance use
Cannabis
|
50 Participants
n=101 Participants
|
|
Past 30 days of substance use
Sedatives
|
19 Participants
n=101 Participants
|
|
Past 30 days of substance use
Hallucinogens
|
10 Participants
n=101 Participants
|
|
Past 30 days of substance use
Prescription stimulants
|
10 Participants
n=101 Participants
|
|
Past 30 days of substance use
Cocaine
|
5 Participants
n=101 Participants
|
|
Past 30 days of substance use
Methamphetamine
|
4 Participants
n=101 Participants
|
|
Past 30 days of substance use
Inhalants
|
4 Participants
n=101 Participants
|
|
Past 30 days of substance use
Prescription opioids
|
5 Participants
n=101 Participants
|
|
Past 30 days of substance use
Street opioids
|
0 Participants
n=101 Participants
|
|
Number of substance use occasions in the past 30 days
|
31.8 occassions
STANDARD_DEVIATION 17.7 • n=101 Participants
|
|
Alcohol Use Disorders Identification Test-Concise
Men
|
5.2 units on a scale
STANDARD_DEVIATION 3.2 • n=24 Participants • The overall number of participants analyzed N=101, where n=24 men and n=77 women.
|
|
Alcohol Use Disorders Identification Test-Concise
Women
|
5.5 units on a scale
STANDARD_DEVIATION 3.1 • n=77 Participants • The overall number of participants analyzed N=101, where n=24 men and n=77 women.
|
|
Drug Abuse Screening Test-10 item
|
3.0 units on a scale
STANDARD_DEVIATION 2.6 • n=101 Participants
|
|
Bothered by cravings in the past 7 days
Not at all
|
7 Participants
n=101 Participants
|
|
Bothered by cravings in the past 7 days
A little bit
|
31 Participants
n=101 Participants
|
|
Bothered by cravings in the past 7 days
Moderately
|
33 Participants
n=101 Participants
|
|
Bothered by cravings in the past 7 days
Quite a bit
|
23 Participants
n=101 Participants
|
|
Bothered by cravings in the past 7 days
Extremely
|
7 Participants
n=101 Participants
|
|
Brief Situational Confidence Questionnaire (BSCQ)
|
48.1 units on a scale
STANDARD_DEVIATION 22.1 • n=101 Participants
|
PRIMARY outcome
Timeframe: Change from Baseline to Post-treatment at 8 weeksThe AUDIT-C is a widely used 3-item self-report screen for hazardous or harmful alcohol consumption that is based off of the 10-item original AUDIT. The AUDIT-C is scored on a scale of 0-12 (scores of 0 reflect no alcohol use). In men, a score of 4 or more is considered positive; in women, a score of 3 or more is considered positive. Generally, the higher the AUDIT-C score, the more likely it is that the patient's drinking is affecting his/her health and safety.
Outcome measures
| Measure |
Woebot-SUDs (W-SUDs)
n=51 Participants
Woebot-SUDs (W-SUDS), an artificially intelligence-powered conversational agent on a smartphone app, eliminates most current SUDs treatment barriers while simultaneously leveraging technology to enhance user experience and engagement. W-SUDs expands and refines existing SUDs treatments by adapting skills from cognitive behavioral therapy, motivational interviewing, and dialectical behavior therapy.
|
|---|---|
|
Change in Alcohol Use Disorders Identification Test-Consumption (AUDIT-C) From Baseline to Post-treatment at 8 Weeks
|
-9.3 score on a scale
Standard Deviation 4.1
|
PRIMARY outcome
Timeframe: Change from Baseline to Post-treatment at 8 weeksThe DAST-10 is a brief, 10-item self-report assesses consequences related to drug abuse, excluding alcohol and tobacco. The range is 0-10, where higher scores indicate greater severity.
Outcome measures
| Measure |
Woebot-SUDs (W-SUDs)
n=51 Participants
Woebot-SUDs (W-SUDS), an artificially intelligence-powered conversational agent on a smartphone app, eliminates most current SUDs treatment barriers while simultaneously leveraging technology to enhance user experience and engagement. W-SUDs expands and refines existing SUDs treatments by adapting skills from cognitive behavioral therapy, motivational interviewing, and dialectical behavior therapy.
|
|---|---|
|
Change in The Drug Abuse Screening Test 10 (DAST-10) From Baseline to Post-treatment at 8 Weeks
|
-1.2 score on a scale
Standard Deviation 2.0
|
PRIMARY outcome
Timeframe: Change from Baseline and Post-treatment at 8 weeksThe number of days a substance was used the past 30 days
Outcome measures
| Measure |
Woebot-SUDs (W-SUDs)
n=51 Participants
Woebot-SUDs (W-SUDS), an artificially intelligence-powered conversational agent on a smartphone app, eliminates most current SUDs treatment barriers while simultaneously leveraging technology to enhance user experience and engagement. W-SUDs expands and refines existing SUDs treatments by adapting skills from cognitive behavioral therapy, motivational interviewing, and dialectical behavior therapy.
|
|---|---|
|
Change in Number of Days Substance Use From Baseline to Post-treatment at 8 Weeks
|
-9.3 days
Standard Deviation 14.1
|
SECONDARY outcome
Timeframe: Post-treatment at 8 weeksThe CSQ-8 is an 8-item self-report scale measuring satisfaction with treatment. Scores from 8 to 32, with higher values indicating higher satisfaction.
Outcome measures
| Measure |
Woebot-SUDs (W-SUDs)
n=51 Participants
Woebot-SUDs (W-SUDS), an artificially intelligence-powered conversational agent on a smartphone app, eliminates most current SUDs treatment barriers while simultaneously leveraging technology to enhance user experience and engagement. W-SUDs expands and refines existing SUDs treatments by adapting skills from cognitive behavioral therapy, motivational interviewing, and dialectical behavior therapy.
|
|---|---|
|
The Client Satisfaction Questionnaire (CSQ-8) at Post-treatment at 8 Weeks
|
23.2 score on a scale
Standard Deviation 5.5
|
SECONDARY outcome
Timeframe: Post-treatment at 8 weeksURPI-Acceptability Subscale is 6-item subscale from the URP Intervention Revised (URP-IR) scale. The URPI-Acceptability inquires about intervention acceptability. Responses range from 1= "slightly disagree" to 6="strongly agree". Scores are averages, with greater scores indicating greater intervention acceptability.
Outcome measures
| Measure |
Woebot-SUDs (W-SUDs)
n=51 Participants
Woebot-SUDs (W-SUDS), an artificially intelligence-powered conversational agent on a smartphone app, eliminates most current SUDs treatment barriers while simultaneously leveraging technology to enhance user experience and engagement. W-SUDs expands and refines existing SUDs treatments by adapting skills from cognitive behavioral therapy, motivational interviewing, and dialectical behavior therapy.
|
|---|---|
|
Usage Rating Profile Intervention (URPI) - Acceptability at Post-treatment at 8 Weeks
|
25.6 score on a scale
Standard Deviation 7.3
|
SECONDARY outcome
Timeframe: Post-treatment at 8 weeksURPI-Feasibility Subscale is 6-item subscale from the URP Intervention Revised (URP-IR) scale. The URPI-Feasibility inquires about factors that impact treatment usage (i.e., intervention quality). Responses range from 1= "slightly disagree" to 6="strongly agree". Scores are averages, with greater scores indicating greater intervention feasibility.
Outcome measures
| Measure |
Woebot-SUDs (W-SUDs)
n=51 Participants
Woebot-SUDs (W-SUDS), an artificially intelligence-powered conversational agent on a smartphone app, eliminates most current SUDs treatment barriers while simultaneously leveraging technology to enhance user experience and engagement. W-SUDs expands and refines existing SUDs treatments by adapting skills from cognitive behavioral therapy, motivational interviewing, and dialectical behavior therapy.
|
|---|---|
|
Usage Rating Profile Intervention (URPI) - Feasibility at Post-treatment at 8 Weeks
|
28.5 score on a scale
Standard Deviation 5.7
|
SECONDARY outcome
Timeframe: Change from Mid-treatment at 4 weeks to Post-treatment at 8 weeksMeasure of working alliance. A measure of therapeutic alliance that assesses three key aspects of the therapeutic alliance: (a) agreement on the tasks of therapy, (b) agreement on the goals of therapy and (c) development of an affective bond. Scores range from 15-60, with higher scores indicating greater alliance. The present study utilized the validated 12-item Short-Revised version (WAI-SR) with minor changes to language, replacing "therapist" with "Woebot".
Outcome measures
| Measure |
Woebot-SUDs (W-SUDs)
n=51 Participants
Woebot-SUDs (W-SUDS), an artificially intelligence-powered conversational agent on a smartphone app, eliminates most current SUDs treatment barriers while simultaneously leveraging technology to enhance user experience and engagement. W-SUDs expands and refines existing SUDs treatments by adapting skills from cognitive behavioral therapy, motivational interviewing, and dialectical behavior therapy.
|
|---|---|
|
Change From Working Alliance Inventory (WAI-SR) From Mid-treatment at 4 Weeks to Post-treatment at 8 Weeks
|
40.8 score on a scale
Standard Deviation 12.5
|
SECONDARY outcome
Timeframe: Change from Baseline to Post-Treatment at 8 weeksMeasure of depression severity. Total score between 0-27, where higher scores indicate greater levels of depression.
Outcome measures
| Measure |
Woebot-SUDs (W-SUDs)
n=51 Participants
Woebot-SUDs (W-SUDS), an artificially intelligence-powered conversational agent on a smartphone app, eliminates most current SUDs treatment barriers while simultaneously leveraging technology to enhance user experience and engagement. W-SUDs expands and refines existing SUDs treatments by adapting skills from cognitive behavioral therapy, motivational interviewing, and dialectical behavior therapy.
|
|---|---|
|
Change Patient Health Questionnaire (PHQ-8) From Baseline to Post-Treatment at 8 Weeks
|
8.6 score on a scale
Standard Deviation 5.1
|
SECONDARY outcome
Timeframe: Change from Baseline to Post-Treatment at 8 weeksMeasure of anxiety. Total score between 0-21, where higher scores indicate greater levels of anxiety.
Outcome measures
| Measure |
Woebot-SUDs (W-SUDs)
n=51 Participants
Woebot-SUDs (W-SUDS), an artificially intelligence-powered conversational agent on a smartphone app, eliminates most current SUDs treatment barriers while simultaneously leveraging technology to enhance user experience and engagement. W-SUDs expands and refines existing SUDs treatments by adapting skills from cognitive behavioral therapy, motivational interviewing, and dialectical behavior therapy.
|
|---|---|
|
Change Generalized Anxiety Disorder (GAD-7) From Baseline to Post-Treatment at 8 Weeks
|
-2.3 score on a scale
Standard Deviation 4.8
|
SECONDARY outcome
Timeframe: Change from Baseline to Post-treatment at 8 weeksThe 8-item BSCQ is a state dependent measure that assesses self-confidence to resist the urge to drink heavily or use drugs in a variety of situations. Each of the 8 scale situations consists of a 100-mm line, anchored by 0% ("not at all confident") and 100% ("totally confident") where clients are asked to indicate confidence on a scale from 0% to 100%. Higher scores are associated with greater confidence.
Outcome measures
| Measure |
Woebot-SUDs (W-SUDs)
n=51 Participants
Woebot-SUDs (W-SUDS), an artificially intelligence-powered conversational agent on a smartphone app, eliminates most current SUDs treatment barriers while simultaneously leveraging technology to enhance user experience and engagement. W-SUDs expands and refines existing SUDs treatments by adapting skills from cognitive behavioral therapy, motivational interviewing, and dialectical behavior therapy.
|
|---|---|
|
Change Brief Situational Confidence Questionnaire (BSCQ) From Baseline to Post-Treatment at 8 Weeks
|
16.9 units on a scale
Standard Deviation 21.4
|
SECONDARY outcome
Timeframe: Change from Baseline to Post-treatment at 8 weeksRange from 0-100 (no pain to worst pain imaginable).
Outcome measures
| Measure |
Woebot-SUDs (W-SUDs)
n=51 Participants
Woebot-SUDs (W-SUDS), an artificially intelligence-powered conversational agent on a smartphone app, eliminates most current SUDs treatment barriers while simultaneously leveraging technology to enhance user experience and engagement. W-SUDs expands and refines existing SUDs treatments by adapting skills from cognitive behavioral therapy, motivational interviewing, and dialectical behavior therapy.
|
|---|---|
|
Change Pain Rating From Baseline to Post-Treatment at 8 Weeks
|
24.2 score on a scale
Standard Deviation 22.0
|
Adverse Events
Woebot-SUDs (W-SUDs)
Serious events: 1 serious events
Other events: 0 other events
Deaths: 0 deaths
Serious adverse events
| Measure |
Woebot-SUDs (W-SUDs)
n=101 participants at risk
Woebot-SUDs (W-SUDS), an artificially intelligence-powered conversational agent on a smartphone app, eliminates most current SUDs treatment barriers while simultaneously leveraging technology to enhance user experience and engagement. W-SUDs expands and refines existing SUDs treatments by adapting skills from cognitive behavioral therapy, motivational interviewing, and dialectical behavior therapy.
|
|---|---|
|
Blood and lymphatic system disorders
Sepsis
|
0.99%
1/101 • Number of events 1 • Serious adverse events were assessed at post-treatment, 8 weeks from baseline.
Serious adverse events occurring during treatment were assessed for hospitalization related to substance use, suicide attempt, alcohol or drug overdose, and severe withdrawal (eg, delirium tremens). Positive endorsements were followed up with questions about the timing, diagnosis, and resolution. If additional details were needed to determine whether the event was study related, a team member reached out to the participant.
|
Other adverse events
Adverse event data not reported
Additional Information
Judith J Prochaska, PhD
Stanford Prevention Research Center, School of Medicine, Stanford University
Phone: 650-724-3608
Email: [email protected]
Results disclosure agreements
- Principal investigator is a sponsor employee
- Publication restrictions are in place