EUVIMEDEUVIMED entdecken
Open Access

Harnessing ChatGPT for Thematic Analysis: Are We Ready?

V Vien Lee iD, Stephanie C C van der Lubbe iD, Lay Hoon Goh iD, Jose Maria Valderas iD

Journal of Medical Internet Research · 31.05.2024 · 26 · e54974

DOI: 10.2196/54974 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Medical Internet Research, online erschienen am 31.05.2024. Verfasst von V Vien Lee und 3 weiteren Autor:innen. Beteiligte Einrichtung: Division of Family Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore. Hauptthemen laut MEDLINE: Natural Language Processing. Die Arbeit wurde bisher 139-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

ChatGPT (OpenAI) is an advanced natural language processing tool with growing applications across various disciplines in medical research. Thematic analysis, a qualitative research method to identify and interpret patterns in data, is one application that stands to benefit from this technology. This viewpoint explores the use of ChatGPT in three core phases of thematic analysis within a medical context: (1) direct coding of transcripts, (2) generating themes from a predefined list of codes, and (3) preprocessing quotes for manuscript inclusion. Additionally, we explore the potential of ChatGPT to generate interview transcripts, which may be used for training purposes. We assess the strengths and limitations of using ChatGPT in these roles, highlighting areas where human intervention remains necessary. Overall, we argue that ChatGPT can function as a valuable tool during analysis, enhancing the efficiency of the thematic analysis and offering additional insights into the qualitative data. While ChatGPT may not adequately capture the full context of each participant, it can serve as an additional member of the analysis team, contributing to researcher triangulation through knowledge building and sensemaking.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Natural Language ProcessingHumansQualitative Research

Stichwörter der Autor:innen

ChatGPTNLPefficiencymedical researchnatural language processingqualitative dataqualitative researchtechnologythematic analysisviewpoint

Autor:innen und Institutionen

  • Division of Family Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore.
  • Department of Family Medicine, National University Health System, Singapore, Singapore.
  • Centre for Research in Health Systems Performance, National University of Singapore, Singapore, Singapore.

ORCID-Profile: V Vien Lee, Stephanie C C van der Lubbe, Lay Hoon Goh, Jose Maria Valderas

Zitieren

APA

Lee, V. V., van der Lubbe, S. C. C., Goh, L. H., & Valderas, J. M. (2024). Harnessing ChatGPT for Thematic Analysis: Are We Ready?. Journal of Medical Internet Research, 26, e54974. https://doi.org/10.2196/54974

Vancouver

Lee VV, van der Lubbe SCC, Goh LH, Valderas JM. Harnessing ChatGPT for Thematic Analysis: Are We Ready?. Journal of Medical Internet Research. 2024;26:e54974. doi:10.2196/54974

BibTeX
@article{Lee2024,
  author = {Lee, V Vien and van der Lubbe, Stephanie C C and Goh, Lay Hoon and Valderas, Jose Maria},
  title = {Harnessing ChatGPT for Thematic Analysis: Are We Ready?},
  journal = {Journal of Medical Internet Research},
  year = {2024},
  volume = {26},
  pages = {e54974},
  doi = {10.2196/54974}
}
Kostenlos starten →