Abstract
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.
Topics

No keywords indexed for this article. Browse by subject →

References
26
[1]
Using thematic analysis in psychology

Virginia Braun, Victoria Clarke

Qualitative Research in Psychology 10.1191/1478088706qp063oa
[2]
Reflecting on reflexive thematic analysis

Virginia Braun, Victoria Clarke

Qualitative Research in Sport, Exercise and Health 10.1080/2159676x.2019.1628806
[4]
Evaluation and accurate diagnoses of pediatric diseases using artificial intelligence

Huiying Liang, Brian Y. Tsui, Hao Ni et al.

Nature Medicine 10.1038/s41591-018-0335-9
[7]
AILYZE20232024-04-02https://www.ailyze.com/
[8]
MonkeyLearn20232024-04-02https://monkeylearn.com/
[9]
ChatGPTOpenAI20232024-04-02https://chat.openai.com/
[10]
What are tokens and how to count them?OpenAI20232024-04-02https://help.openai.com/en/articles/4936856-what-are-tokens-and-how-to-count-them
[12]
Utility of ChatGPT in Clinical Practice

Jialin Liu, Changyu Wang, Siru Liu

Journal of Medical Internet Research 10.2196/48568
[20]
HarleyAPersonas make users memorable for product team membersNielsen Norman Group20152024-04-02https://www.nngroup.com/articles/persona/
[21]
Understanding and Evaluating Qualitative Research

Ellie Fossey, Carol Harvey, Fiona McDermott et al.

Australian & New Zealand Journal of Psychiatry 10.1046/j.1440-1614.2002.01100.x
[22]
Diabetes discussions: living with diabetesDiabetes UK20232023-06-21https://www.diabetes.org.uk/guide-to-diabetes/podcasts/living-with-diabetes
[24]
Privacy policyOpenAI20232024-04-02https://openai.com/policies/privacy-policy
[25]
ChatGPT: A comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope

Partha Pratim Ray

Internet of Things and Cyber-Physical Systems 10.1016/j.iotcps.2023.04.003
[26]
March 20 ChatGPT outage: here's what happenedOpenAI20232023-04-02https://openai.com/index/march-20-chatgpt-outage
Metrics
95
Citations
26
References
Details
Published
May 31, 2024
Vol/Issue
26
Pages
e54974
Cite This Article
V Vien Lee, Stephanie C C van der Lubbe, Lay Hoon Goh, et al. (2024). Harnessing ChatGPT for Thematic Analysis: Are We Ready?. Journal of Medical Internet Research, 26, e54974. https://doi.org/10.2196/54974