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

NCT06920238 | Recruiting Phase 1

• 2 other identifiers: STUDY000332195P30DA029926-14
• Study Type: interventional
• Target: 15
• Locations: 1 country
• Sites: 1

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

Conditions

Cannabis Use Disorder; Anxiety; 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

Outcome Measures

Primary Outcomes (3)

• Feasibility

  Feasibility 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.

  From enrollment to the end of the third interview at around 10 months

• Usability

  Usability 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.

  From enrollment to the end of the third interview at around 10 months

• Acceptability

  Acceptability 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.

  From enrollment to the end of the third interview at around 10 months

Study Arms (1)

Therabot-CALM

EXPERIMENTAL

Participants will engage in three one-hour interviews and a 4-week clinical trial where they may interact with Therabot-CALM as much or as little as they want.

Device: Therabot-CALM

Interventions

Therabot-CALM DEVICE

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.

Therabot-CALM

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• 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.

You may not qualify if:

• 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.

Sponsors & Collaborators

• Trustees of Dartmouth College: lead
• National Institute on Drug Abuse (NIDA): collaborator

Study Sites (1)

46 Centerra Parkway, Suite 300, Office #333S

Lebanon, New Hampshire, 03766, United States

RECRUITING

Related Publications (2)

• Heinz, M. V., Mackin, D., Trudeau, B., Bhattacharya, S., Wang, Y., Banta, H. A., Jewett, A. D., Salzhauer, A., Griffin, T., & Jacobson, N. C. (2024). Evaluating Therabot: A Randomized Control Trial Investigating the Feasibility and Effectiveness of a Generative AI Therapy Chatbot for Depression, Anxiety, and Eating Disorder Symptom Treatment. OSF. https://doi.org/10.31234/osf.io/pjqmr

  BACKGROUND

• Collins AC, Bhattacharya S, Oh JY, Salzhauer A, Taylor CT, Wolitzky-Taylor K, Aupperle RL, Budney AJ, Jacobson NC. Inclusion of Individuals With Lived Experiences in the Development of a Digital Intervention for Co-Occurring Depression and Cannabis Use: Mixed Methods Investigation. JMIR Form Res. 2024 Oct 7;8:e54751. doi: 10.2196/54751.

  PMID: 39374076 BACKGROUND

MeSH Terms

Conditions

Anxiety Disorders; Depression; Substance-Related Disorders

Condition Hierarchy (Ancestors)

Mental Disorders; Behavioral Symptoms; Behavior; Chemically-Induced Disorders

Study Officials

• Nicholas C Jacobson, Ph.D.

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

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Michael V Heinz, MD

CONTACT

(603) 277-9110; michael.v.heinz@hitchcock.org

Amanda C Collins, Ph.D.

CONTACT

Amanda.C.Collins@dartmouth.edu

Study Design

• Study Type: interventional
• Phase: phase 1
• Allocation: NA
• Masking: NONE
• Purpose: DEVICE FEASIBILITY
• Intervention Model: SINGLE GROUP
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Associate Professor

Model Details: Therabot-CALM Model

Study Record Dates

• First Submitted: March 10, 2025
• First Posted: April 9, 2025
• Study Start: April 13, 2025
• Primary Completion: December 1, 2025
• Study Completion: December 1, 2025
• Last Updated: September 8, 2025

Record last verified: 2025-09

Data Sharing

• IPD Sharing: Will not share

Locations

US (1)