Related Experiment Video
Updated: May 12, 2025
A Prediction Error-driven Retrieval Procedure for Destabilizing and Rewriting Maladaptive Reward Memories in Hazardous Drinkers
Published on: January 5, 2018
Development and preliminary testing of a secure large language model-based chatbot for brief alcohol counseling in
Brian Suffoletto1, Duncan B Clark2, Christine Lee3
1Department of Emergency Medicine, Stanford University, USA.
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).
Method:
Using 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.
Results:
No 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).
Conclusions:
This 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.
More Related Videos
07:31Murine Drinking Models in the Development of Pharmacotherapies for Alcoholism: Drinking in the Dark and Two-bottle Choice
Published on: January 7, 2019
08:53Integrating Computerized Linguistic and Social Network Analyses to Capture Addiction Recovery Capital in an Online Community
Published on: May 31, 2019
Related Concept Videos
02:15Preparation of Alcohols via Addition Reactions
The acid-catalyzed addition of water to the double bond of alkenes is a large-scale industrial method used to synthesize low-molecular-weight alcohols. An acidic atmosphere is required to allow the hydrogen in the water molecule to act as an electrophile and attack the double bond in an alkene. The addition of a proton to the double bond creates a carbocation intermediate. The proton preferentially bonds to the less substituted end of the double bond to create a more stable carbocation...
01:27CNS Depressants: Alcohol and Nicotine
01:30Cognitive Development During Adulthood
02:48Conversion of Alcohols to Alkyl Halides
01:38Preparation of Alcohols via Substitution Reactions
Alcohols can be synthesized from alkyl halides via nucleophilic substitution reactions. The highly polar carbon-halogen bond in the substrate makes halide a good leaving group. The hydroxide ion or water can act as a nucleophile to take the place of halide and form an alcohol. The substitution reactions occur via two different reaction pathways, SN1 or SN2, depending on the nature of carbon attached to the halide.
Primary alcohols are synthesized from primary alkyl halides,...
02:35Acid-Catalyzed Dehydration of Alcohols to Alkenes