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

Official title

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

Overview

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.

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.

Interventions

• 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.

Primary outcome measures

• Time to achieve target enrollment [Time frame: Enrollment]
• Rate of participant retention [Time frame: 1-month post intervention1-month post intervention]
• Acceptability (System Usability Scale) [Time frame: Immediate post-intervention session]
• Acceptability - intervention delivery method [Time frame: Immediate post-intervention session]
• Acceptability - usable [Time frame: Immediate post-intervention session]
• Acceptability - helpful [Time frame: Immediate post-intervention session]
• Acceptability - recommend to others [Time frame: Immediate post-intervention session]

Secondary outcome measures (6)

• Motivation to change drinking (Readiness Ruler) [Time frame: Enrollment, immediate post-intervention session, and 1 month post-intervention]
• Daily drinking questionnaire (DDQ) [Time frame: Enrollment and 1 month post-intervention]
• Alcohol Use Disorders Identification Test (AUDIT) [Time frame: Enrollment and 1 month post-intervention]
• Young Adult Alcohol Consequences Questionnaire (YAACQ) [Time frame: Enrollment and 1 month post-intervention]
• Protective behavioral strategies scale (PBSS) [Time frame: Enrollment and 1 month post-intervention]
• Alcohol treatment utilization [Time frame: Enrollment and 1 month post-intervention]

Eligibility criteria

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

Criteria are shown verbatim from the registry (in English). Final eligibility is always assessed by the study center.

Healthy volunteers: No

Study design

Allocation

N/A

Model

Single group

Masking

Open label

Primary purpose

Treatment

Study locations

United States · 1 center

• Massachusetts General Hospital — Boston

Identifiers

NCT: NCT07214831 · 2025P001459 · R34AA032472

Primary sources (government registries)

• ClinicalTrials.gov (US NIH)

View this study on ClinicalTrials.gov ↗