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

Journal: Drug and alcohol dependence
Published Date: Apr 28, 2025

Abstract

OBJECTIVE: Young 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).

Authors

  • Brian Suffoletto
    Department of Emergency Medicine, Stanford University, USA. Electronic address: suffbp@stanford.edu.
  • Duncan B Clark
    Department of Psychiatry, University of Pittsburgh, USA.
  • Christine Lee
    Department of Psychiatry and Behavioral Sciences, University of Washington, USA.
  • Michael Mason
    College of Social Work, University of Tennessee, USA.
  • Jordan Schultz
    Technology & Digital Solutions, Stanford University, USA.
  • Irvin Szeto
    Technology & Digital Solutions, Stanford University, USA.
  • Denise Walker
    School of Social Work, University of Washington, USA.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals