User and Provider Experiences With Health Education Chatbots: Qualitative Systematic Review
JMIR Human Factors · 13.06.2025 · 12 · e60205-e60205
DOI: 10.2196/60205 ↗Kurz gefasst
Systematische Übersicht in der Zeitschrift JMIR Human Factors, online erschienen am 13.06.2025. Verfasst von Кyung-Eun Anna Choi und 1 weiteren Autor:innen. Beteiligte Einrichtung: Health Services Research Group, Medical Images Analysis and Artificial Intelligence, Danube Private University, Steiner Landstraße 124, Krems an der …. Hauptthemen laut MEDLINE: Health Education, Health Personnel. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
Chatbots, as dialog-based platforms, have the potential to transform health education and behavior-change interventions. Despite the growing use of chatbots, qualitative insights into user and provider experiences remain underexplored, particularly with respect to experiences and perceptions, adoption factors, and the role of theoretical frameworks in design.
Objective
This systematic review of qualitative evidence aims to address three key research questions (RQs): (RQ1) user and provider experiences; (RQ2) facilitators and barriers to adoption; and (RQ3) role of theoretical frameworks.
Methods
We systematically searched PubMed, the Cochrane Library, and ScienceDirect from January 1, 2018, to October 1, 2023, for English- or German-language, peer-reviewed qualitative or mixed methods studies. Studies were included if they examined users’ or providers’ experiences with chatbots in health education or behavior-change contexts. Two reviewers independently screened titles, abstracts, and full texts (Cohen κ=0.82). We used the Joanna Briggs Institute Critical Appraisal Checklist for quality assessment and conducted a reflexive thematic analysis following Braun and Clarke’s framework.
Results
Among the 1754 records identified, 27 studies from 10 countries met the inclusion criteria, encompassing 241 qualitative-only participants and 10,802 mixed method participants (657 contributing qualitative data). For RQ1, users emphasized empathy and emotional connection. For RQ2, accessibility and ease of use emerged as facilitators, whereas trust deficits, technical glitches, and cultural misalignment were key barriers. For RQ3, the integration of behavior-change theories emerged as underutilized despite their potential to increase motivation.
Conclusions
Chatbots demonstrate strong potential for health education and behavior-change interventions but must address privacy and trust issues, embed robust theoretical underpinnings, and overcome adoption barriers to fully realize their impact. Future directions should include evaluations of cultural adaptability and rigorous ethical considerations in chatbot design.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Health Services Research Group, Medical Images Analysis and Artificial Intelligence, Danube Private University, Steiner Landstraße 124, Krems an der Donau, 3500, Austria, 43 0734102289.
- Center for Health Services Research, Brandenburg Medical University, Neuruppin, Germany.
- Evidence-Based Practice in Brandenburg-A JBI Affiliated Group, Hochstraße 29, Brandenburg an der Havel, 14770, Germany.
ORCID-Profile: Кyung-Eun Anna Choi, Sebastian Fitzek
Zitieren
APA
Choi, К. A., & Fitzek, S. (2025). User and Provider Experiences With Health Education Chatbots: Qualitative Systematic Review. JMIR Human Factors, 12, e60205-e60205. https://doi.org/10.2196/60205
Vancouver
Choi КA, Fitzek S. User and Provider Experiences With Health Education Chatbots: Qualitative Systematic Review. JMIR Human Factors. 2025;12:e60205-e60205. doi:10.2196/60205
BibTeX
@article{Choi2025,
author = {Choi, Кyung-Eun Anna and Fitzek, Sebastian},
title = {User and Provider Experiences With Health Education Chatbots: Qualitative Systematic Review},
journal = {JMIR Human Factors},
year = {2025},
volume = {12},
pages = {e60205--e60205},
doi = {10.2196/60205}
}
EUVIMED