Evidence map›Paper›PMID 40334327›Full record

ArticleDrug and alcohol dependence2025

Development and preliminary testing of a secure large language model-based chatbot for brief alcohol counseling in young adults.

Brian Suffoletto, Duncan B Clark, Christine Lee, Michael Mason, Jordan Schultz, Irvin Szeto, Denise Walker

Abstract read
PubMed Full text at PMC Publisher
In one paragraph

Article in Drug and alcohol dependence, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 4 papers, 1 of them a synthesis that pooled it.

0numbers the graph read from it
0cells of the map it votes in
4citing papers in PubMed, 1 pooled it
–field-weighted citation impact
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

4 citing papers in PubMed, 1 synthesis or guideline pooled it.

  1. Pooled it
  2. Trial
  3. Article
  4. Review
4 · The record

Corrections and comments

PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.

5 · Who and what money

Authors and funding

7 authors.

Brian SuffolettoDepartment of Emergency Medicine, Stanford University, USA. Electronic address: suffbp@stanford.edu.
Duncan B ClarkDepartment of Psychiatry, University of Pittsburgh, USA.
Christine LeeDepartment of Psychiatry and Behavioral Sciences, University of Washington, USA.
Michael MasonCollege of Social Work, University of Tennessee, USA.
Jordan SchultzTechnology & Digital Solutions, Stanford University, USA.
Irvin SzetoTechnology & Digital Solutions, Stanford University, USA.
Denise WalkerSchool of Social Work, University of Washington, USA.

Funding

ASPIRE to Change: Leveraging Text Messaging Peer Support Coaching to Mitigate Hazardous Alcohol Consumption in Non-Collegiate Young AdultsR01AA030986 · NIAAA · STANFORD UNIVERSITY · PI Brian P Suffoletto · 2024 to 2026
$1.9M
NIAAA NIH HHS R01 AA030986
6 · The paper itself

Abstract

objectiveYoung adults face elevated risks from alcohol use yet encounter significant barriers to accessing evidence-based interventions. Large language models (LLMs) represent a promising advancement for delivering personalized behavioral interventions, but their application to alcohol counseling remains unexplored. This study evaluated the development and preliminary outcomes of a Secure GPT-4-powered text-based Motivational Interviewing Conversational Agent (MICA).

methodUsing a prospective single-arm pilot design, we evaluated MICA across two phases (Phase I: n = 8; Phase II: n = 37), editing the LLM prompts between Phases. Participants aged 18-25 who reported consuming ≥ 10 standard alcohol units weekly completed a counseling session with MICA. We evaluated safety and compared MI fidelity (relational and technical sub-scales of the Client Evaluation of MI [CEMI]) and usability (System Usability Scale) between Phases. We also explored surrogate measures of effectiveness (i.e. proportion of change talk to sustain talk from session logs) and qualitative feedback themes.

resultsNo unsafe responses were observed. MI fidelity improved significantly in the CEMI relational sub-scale from Phase I to II (67.2 % to 82.6 %, p = 0.03). Usability remained consistently high across phases (Phase I: 85.4; Phase II: 80.9; p = 0.45). The proportion of within-session change talk was also consistently high (Phase I: 65.2 %; Phase II: 75.8 %; p = 0.10).

conclusionsThis study provides preliminary evidence that LLM-based chatbots can deliver MI-adherent alcohol interventions that are both acceptable to young adults and maintain high MI fidelity. Future research should employ randomized controlled designs with longer follow-up periods to evaluate impact on drinking outcomes.

Indexed as

Alcohol DrinkingCounselingLanguageMotivational InterviewingAdolescentAdultFemaleGenerative Artificial IntelligenceHumansLarge Language ModelsMalePilot ProjectsProspective StudiesYoung AdultAlcoholArtificial intelligenceCounselingInterventionYoung adults

Identifiers

PMID40334327
PMCPMC12207782

What OpenQuestion holds

Textmetadata
LicenceTDM
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.