AI-Enabled Personalized Smoking Cessation Intervention With the Aipaca Chatbot: Mixed Methods Feasibility Study
JMIR Formative Research · 11.12.2025 · 9 · e73319
DOI: 10.2196/73319 ↗Kurz gefasst
Beobachtungsstudie in der Zeitschrift JMIR Formative Research, online erschienen am 11.12.2025. Verfasst von Yunlong Liu und 8 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, University of Oklahoma, Norman, OK, United States. Hauptthemen laut MEDLINE: Smoking Cessation, Counseling, Artificial Intelligence. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Office of the Director, NIH Common Fund.
Abstract (Originalsprache)
Background
Tobacco use remains the leading cause of preventable mortality in the United States; yet, evidence-based cessation services remain underused due to staffing constraints, limited access to counseling, and competing clinical priorities. Generative artificial intelligence (GenAI) chatbots may address these barriers by delivering personalized, guideline-aligned counseling through naturalistic dialogue. However, little is known about how GenAI chatbots support smoking cessation at both outcome and communication process levels.
Objective
This feasibility study evaluated the implementation of an evidence-based smoking cessation counseling session delivered by a GenAI-powered chatbot, Aipaca. We examined (1) pre-post changes in cessation preparedness, (2) communication dynamics during counseling sessions, and (3) user perceptions of the chatbot’s value, limitations, and design needs.
Methods
We conducted an observational, single-arm, mixed methods study with 29 adult smokers. Participants completed pre-post surveys measuring knowledge of smoking-related health risks and cessation methods, self-efficacy, and readiness to quit. Each engaged in a 30-minute text-based counseling session with Aipaca, powered by GPT-4 and structured using the 5A’s framework (Ask, Advise, Assess, Assist, Arrange). Sessions were transcribed for microsequential conversation analysis. Twenty-five participants completed semistructured interviews exploring perceived value, challenges, and design suggestions. Quantitative data were analyzed with paired-samples t tests, qualitative data were thematically analyzed, and transcripts were analyzed for interactional practices. The methodological strength of this study lies in its triangulated approach, which combines quantitative measurement of intervention effectiveness, qualitative analysis of user interviews, and conversational analysis of counseling transcripts to generate a comprehensive understanding of both outcomes and underlying mechanisms.
Results
Participants demonstrated significant improvements in all preparedness indicators: knowledge of health risks, knowledge of cessation methods, self-efficacy, and readiness to quit. Conversation analysis identified three recurrent patterns enabling counseling-relevant dynamics: (1) contextual referencing and continuity, (2) formulations with elaboration prompts, and (3) narrative progression toward collaborative planning. Interview themes underscored Aipaca’s perceived value as an accessible, nonjudgmental, and motivating resource, capable of delivering personalized and interactive support. Criticisms included limited accountability, reduced cultural resonance, and overly goal-directed style. Participants emphasized design needs such as proactive engagement, gamified progress tracking, empathetic or anthropomorphic personas, and safeguards for accuracy.
Conclusions
This mixed methods feasibility study demonstrates that GenAI can deliver evidence-based smoking cessation counseling with measurable short-term gains in cessation preparedness and process-level communication patterns consistent with motivational interviewing. Users valued Aipaca’s accessibility, empathy, and personalization, while also articulating expectations for richer social roles and long-term accountability. Findings highlight both the promise and challenges of integrating GenAI into digital health: pairing adaptive language generation with human-centered design, embedding accuracy safeguards, and ensuring integration into multilevel cessation infrastructures will be essential for future clinical deployment.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Computer Science, University of Oklahoma, Norman, OK, United States.
- Department of Community Health and Family Medicine, College of Medicine, University of Florida, Gainesville, FL, United States.
- Department of Family and Preventive Medicine, College of Medicine, University of Oklahoma Health Sciences Center, Oklahoma City, OK, United States.
- College of Nursing, Florida State University, Tallahassee, FL, United States.
- College of Communication and Information, Florida State University, Tallahassee, FL, United States.
ORCID-Profile: Yunlong Liu, Paul Calle, Mariah Vadakekut, Daniel Rubin, Zsolt Nagykaldi, Mark Doescher, Lisa Hightow-Weidman, Chongle Pan, Ruosi Shao
Förderung
- Office of the Director, NIH Common Fund
Zitieren
APA
Liu, Y., Calle, P., Vadakekut, M., Rubin, D., Nagykaldi, Z., Doescher, M., Hightow-Weidman, L., Pan, C., & Shao, R. (2025). AI-Enabled Personalized Smoking Cessation Intervention With the Aipaca Chatbot: Mixed Methods Feasibility Study. JMIR Formative Research, 9, e73319. https://doi.org/10.2196/73319
Vancouver
Liu Y, Calle P, Vadakekut M, Rubin D, Nagykaldi Z, Doescher M, et al. AI-Enabled Personalized Smoking Cessation Intervention With the Aipaca Chatbot: Mixed Methods Feasibility Study. JMIR Formative Research. 2025;9:e73319. doi:10.2196/73319
BibTeX
@article{Liu2025,
author = {Liu, Yunlong and Calle, Paul and Vadakekut, Mariah and Rubin, Daniel and Nagykaldi, Zsolt and Doescher, Mark and Hightow-Weidman, Lisa and Pan, Chongle and Shao, Ruosi},
title = {AI-Enabled Personalized Smoking Cessation Intervention With the Aipaca Chatbot: Mixed Methods Feasibility Study},
journal = {JMIR Formative Research},
year = {2025},
volume = {9},
pages = {e73319},
doi = {10.2196/73319}
}
EUVIMED