Skip to content

Use of a Generative AI (Gen-AI) Chatbot for Anxiety and Depression Among Persons With Cannabis Use

A Phase I Single-Arm Trial to Test the Use of a Generative AI (Gen-AI) Chatbot for Anxiety and Depression Among Persons With Cannabis Use Disorder (CUD)

Status
Completed
Phases
Phase 1
Study type
Interventional
Source
ClinicalTrials.gov
Registry ID
NCT06920238
Enrollment
15
Registered
2025-04-09
Start date
2025-04-13
Completion date
2026-04-28
Last updated
2026-07-06

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Anxiety, Cannabis Use Disorder, Depression, Anxiety, Depression - Major Depressive Disorder

Keywords

Artifical Intelligence, Generative AI, Generative Artificial Intelligence, Therabot, Therabot-CALM, Cannabis Use Disorder, Anxiety, Depression, Chatbot, Cannabis Use, Drug Abuse, Drug Use, Drug Use Disorder, Interview, Screening, Application, REDCap, post-intervention measures, System Usability Scale, Treatment Acceptability and Adherence Scale, Cannabis Use Disorders Identification Test - Revised, Cannabis Use Disorders Identification Test, Quantity of Cannabis Use Inventory, Patient Health Questionnaire for depression, generalized anxiety disorder screener, DSM-5, Zoom

Brief summary

The goal of this clinical trial is to learn if Therabot-CALM (Cannabis, Anxiety, Low Mood) has acceptability among users and could work to improve the symptoms of persons with cannabis use disorder and anxiety and/or depression. The main question it aims to answer is: What is the usability, feasibility, and acceptability of Therabot-CALM in persons with Cannabis Use Disorder and Anxiety and/or Depression? Participants will * Take a screening questionnaire * Participate in two virtual 1-hour interviews to provide feedback on app design and suggest features. * Engage with Therabot-CALM in a 4-week clinical trial and provide feedback on their app experience in a third virtual interview

Detailed description

Participants will complete a two-stage screening process via REDCap to determine their eligibility for enrollment. Participants who meet criteria and provide informed consent will be enrolled and participate in three interviews and the 4-week clinical trial. After the first interview, researchers will fine-tune Therabot-CALM based on feedback received during the interview. After the second interview, experts by experience (EBEs) will engage with Therabot-CALM at least once per day for 4 weeks. After the clinical trial period, participants will receive an email with a link to complete the post-intervention measures delivered via REDCap, including the System Usability Scale (SUS), Treatment Acceptability and Adherence Scale (TAAS), Cannabis Use Disorders Identification Test - Revised (CUDIT-R), the Daily Sessions, Frequency, Age of Onset, and Quantity of Cannabis Use Inventory (DFAQ-CU), the 9-item Patient Health Questionnaire for depression (PHQ-9), and the 7-item generalized anxiety disorder screener for DSM-5 (GAD-7). Participants will then be asked to return for a third interview to provide feedback on their experience with Therabot-CALM. Researchers will use the IDEAS (Innovate, Develop, Evaluate, Adapt, Scale) Impact Framework to plan and conduct three, one-on-one interviews with a trained research assistant (RA). Each interview script will be developed using the IDEAS Impact Framework and follow a semi-structured design, such that the RA will follow a set of questions, with as-needed probing for follow-up. Interviews will be recorded via a virtual platform.

Interventions

DEVICETherabot-CALM

Therabot is a generative-AI-driven mobile app designed to provide mental health treatment. The feasibility of Therabot-CALM, an adapted Therabot application, is being tested for the future use of treating co-occurring substance use disorders and anxiety and/or depression. The primary purpose of this study is application feasibility.

Sponsors

Trustees of Dartmouth College
Lead SponsorOTHER
National Institute on Drug Abuse (NIDA)
CollaboratorNIH

Study design

Allocation
NA
Intervention model
SINGLE_GROUP
Primary purpose
DEVICE_FEASIBILITY
Masking
NONE

Intervention model description

Therabot-CALM Model

Eligibility

Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
No

Inclusion criteria

* Is 18 years or older. * Meet criteria for current CUD (CUDIT-R\>=12) and MDD (PHQ-9\>=10), and/or GAD (GAD-7\>=10). * Have reliable access to the internet and a compatible device for Therabot-CALM. * Have willingness and capacity to provide informed consent and commit to participating in all assessments and interventions during the study. * Attend the first interview.

Exclusion criteria

* Moderate to High risk of STBs as determined by the C-SSRS or baseline questionnaires. * Current psychosis (as determined by brief psychosis screen). * Current participation in another digital mental health intervention.

Design outcomes

Primary

MeasureTime frameDescription
FeasibilityFrom enrollment to the end of the third interview at around 10 monthsFeasibility of the application is measured by engagement rates of participants. Engagement rates will be quantified based on the frequency and duration of interactions with the application during the clinical trial period.
UsabilityFrom enrollment to the end of the third interview at around 10 monthsUsability is measured by participant responses on the System Usability Scale (SUS). The SUS score will range from 0 to 100, where higher scores indicate better usability.
AcceptabilityFrom enrollment to the end of the third interview at around 10 monthsAcceptability is measured by the Treatment Acceptability and Adherence Scale (TAAS), the Likert-style satisfaction rating scale to assess satisfaction with Therabot-CALM. The TAAS scale will range from 0 to 100, where higher scores indicate higher acceptability. The Likert-style satisfaction rating scale will range from 1 to 5, with 1 indicating very dissatisfied and 5 indicating very satisfied.

Countries

United States

Contacts

PRINCIPAL_INVESTIGATORNicholas C Jacobson, Ph.D.

Center for Technology and Behavioral Health, Geisel School of Medicine, Dartmouth College

Outcome results

None listed

Source: ClinicalTrials.gov · Data processed: Jul 7, 2026