A Feasibility and Acceptability Study of a Large Language Model-based Chatbot for Brief Alcohol Intervention Among Emerging Adults

A Feasibility and Acceptability Study of a Large Language Model-based Conversational Agent for Brief Alcohol Intervention Among Emerging Adults

American emerging adults (EAs; aged 18-29 years) have the highest rates of alcohol use disorder (AUD) and the lowest levels of treatment engagement of any age group. Innovative, scalable, and cost-effective strategies are needed to expand early detection and intervention for EAs engaged in patterns of drinking associated with AUD. Because digital technology use is frequent among EAs, digital interventions may be a particularly suitable way to reach this population. Prior studies of digital alcohol interventions demonstrate modest but consistent reductions in alcohol use, but these tools are often limited by a lack of interactivity and personalization. Large language model (LLM)-based chatbots, such as ChatGPT, may address these limitations by enabling personalized, adaptive, and human-like engagement. These features have the potential to increase uptake and engagement with screening and brief interventions among EAs. This study will develop, validate, and conduct an open trial of an LLM-based chatbot-delivered brief intervention designed to reduce alcohol use and problems among EAs, with the primary goal of establishing preliminary feasibility and acceptability.

Study Overview

• Status: Not yet recruiting
• Conditions: Alcohol Use Disorder
• Intervention / Treatment: Behavioral: Large language model-based chatbot brief alcohol intervention session

Detailed Description

This feasibility and acceptability study will develop, validate, and conduct a Phase I single-arm open trial of a large language model (LLM)-based chatbot-delivered brief intervention designed to reduce alcohol use and problems among EAs. To develop the augmented LLM, the investigators will use instruction fine-tuning to enhance conversational abilities within the context of brief interventions based on high-fidelity recordings of sessions from prior clinical trials and simulated patient-provider interactions. A retrieval augmented generation system will be developed to ensure the model delivers accurate information. The augmented LLM will be incorporated into a chatbot interface delivered through a user-friendly web application. To validate the chatbot's capability for delivering brief alcohol interventions, patient actors (clinical or counseling psychology PhD students) will be assigned clinical vignettes depicting diverse EAs with patterns of drinking associated with alcohol use disorder. Patient actors will engage in two randomly ordered online text-based brief intervention sessions for each vignette (one with the chatbot and one with a human clinician). Blinded transcripts from sessions will be reviewed by experts to assess treatment fidelity. To maximize and test initial feasibility and acceptability of the intervention, the investigators will conduct semi-structured interviews with 20 EAs who report hazardous drinking, followed by an open trial with another 20 EAs.

• Study Type: Interventional
• Enrollment (Estimated): 20
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Alex M Russell, PhD; Phone Number: 617-724-0924; Email: arussell11@mgh.harvard.edu
• Study Contact Backup: Name: Samuel F Acuff, PhD; Email: sacuff@mgh.harvard.edu

Study Locations

• United States
  • Massachusetts
    • Boston, Massachusetts, United States, 02114
      • Massachusetts General Hospital
      • Contact: Research Coordinator; Phone Number: 617-724-0924

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult
• Accepts Healthy Volunteers: No

Description

Inclusion Criteria:

• 18-29 years old
• Engaged in past-month hazardous drinking (consuming ≥ 5/4 drinks for men/women on two or more occasions in the past month) or exceeded recommended guidelines for risky drinking (> 14/7 drinks per week for men/women)
• Able to read and comprehend English at a 5th grade level

Exclusion Criteria:

• Report a history of or active psychosis
• Previous or current engagement in alcohol or drug treatment
• Risk for alcohol withdrawal as evidenced by very heavy weekly drinking reports on the alcohol screener (> 40 standard drinks in a typical week in the past month)
• Demonstrate inability or unwillingness to attend in-person office visits
• Demonstrate inability or unwillingness to identify an emergency contact who could be contacted in case the participant becomes lost to follow-up

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Treatment
• Allocation: N/A
• Interventional Model: Single Group Assignment
• Masking: None (Open Label)

Number of Arms

1

Arms and Interventions

Participant Group / Arm

Intervention / Treatment

Experimental: Large language model-based chatbot brief alcohol intervention; All participants will interact with a large language model-based chatbot designed to deliver a brief alcohol intervention session.

Behavioral: Large language model-based chatbot brief alcohol intervention session; The intervention is a large language model-based chatbot designed to delivered brief alcohol interventions using motivational interviewing-consistent strategies. The chatbot session will last approximately 45 minutes and will include a decisional balance exercise, feedback on drinking patterns, normative beliefs about drinking, alcohol-related consequences, goal setting, and harm-reduction strategies.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Acceptability (System Usability Scale)	Acceptability of the conversational agent-delivered intervention will be measured using the 10-item System Usability Scale. Each question is rated on a Likert-type scale ranging from (1) strongly disagree to (5) strongly agree.	Immediate post-intervention session
Acceptability - intervention delivery method	Percentage of participants who agree or strongly agree the intervention delivery method was acceptable	Immediate post-intervention session
Acceptability - usable	Percentage of participants who agree or strongly agree the intervention was easy to interact with	Immediate post-intervention session
Acceptability - helpful	Percentage of participants who agree or strongly agree the intervention was helpful	Immediate post-intervention session
Acceptability - recommend to others	Percentage of participants who agree or strongly agree they would recommend the chatbot to others	Immediate post-intervention session
Time to achieve target enrollment	Recruitment feasibility will be evaluated based on the length of time needed to recruit target enrollment (N = 20)	Enrollment
Rate of participant retention	Retention feasibility will be achieved if >80% of participants who consented to participating in the study complete one-month follow-up assessment.	1-month post intervention1-month post intervention

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Motivation to change drinking (Readiness Ruler)	Motivation to change drinking will measured using the Readiness Ruler.	Enrollment, immediate post-intervention session, and 1 month post-intervention
Daily drinking questionnaire (DDQ)	Past-month typical drinks per week and frequency of heavy drinking will be assessed using the DDQ. Respondents are asked to record the number of drinks they consume each day of a typical week over the previous month.	Enrollment and 1 month post-intervention
Young Adult Alcohol Consequences Questionnaire (YAACQ)	Alcohol-related problems will be assessed using the YAACQ. Respondents will be asked to indicate (yes/no) which of the 48 potential problems they have experienced as a result of their drinking over the previous month.	Enrollment and 1 month post-intervention
Protective behavioral strategies scale (PBSS)	Protective behavioral strategies will be assessed using the 15-item PBSS. Participants will be asked to indicate how often they used each strategy when drinking alcohol during the previous month. Response options are presented on a 6-point Likert type scale ranging from 1 (never) to 6 (always).	Enrollment and 1 month post-intervention
Alcohol treatment utilization	Alcohol treatment utilization, including a variety of options, will be measured by asking respondents to indicate (yes/no) which of the potential options they have utilized.	Enrollment and 1 month post-intervention
Alcohol Use Disorders Identification Test (AUDIT)	Past-month frequency of heavy drinking will be assessed using the AUDIT, a 10-item screening tool used to identify hazardous and harmful drinking patterns. Total scores range from 0 to 40, with higher scores indicating more hazardous or harmful drinking patterns.	Enrollment and 1 month post-intervention

Collaborators and Investigators

• Sponsor: Massachusetts General Hospital
• Collaborators: National Institute on Alcohol Abuse and Alcoholism (NIAAA)
• Investigators: Principal Investigator: Alex M Russell, PhD, Massachusetts General Hospital

Study record dates

Study Major Dates

• Study Start (Estimated): June 1, 2027
• Primary Completion (Estimated): December 31, 2027
• Study Completion (Estimated): August 31, 2028

Study Registration Dates

• First Submitted: October 6, 2025
• First Submitted That Met QC Criteria: October 6, 2025
• First Posted (Estimated): October 9, 2025

Study Record Updates

• Last Update Posted (Estimated): October 22, 2025
• Last Update Submitted That Met QC Criteria: October 20, 2025
• Last Verified: October 1, 2025

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Mental Disorders; Substance-Related Disorders; Chemically-Induced Disorders; Alcohol-Related Disorders; Alcoholism; Organic Chemicals; Alcohols; Ethanol
• Other Study ID Numbers: 2025P001459; R34AA032472 (U.S. NIH Grant/Contract)

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: YES
• IPD Plan Description: De-identified data will be submitted to the NIAAA Data Archive in accordance with NIH requirements.
• IPD Sharing Time Frame: De-identified individual participant data (IPD) and supporting documents will be deposited in the NIAAA Data Archive (NIAAADA) hosted within the NIMH Data Archive. Data will be submitted within 6 months of collection and will be available after study completion, in perpetuity.
• IPD Sharing Access Criteria: Data will be de-identified and available as public use data through the NIAAA Data Archive. Access requires submission of a data use request through the NIAAADA and agreement to the Terms of Use, which limit use to scientific research, prohibit attempts to identify participants, and require reporting of any breaches of confidentiality.
• IPD Sharing Supporting Information Type: STUDY_PROTOCOL; SAP; ICF

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No