Generative AI for thematic analysis in a maternal health study: coding semistructured interviews using large language models
Applied Psychology: Health and Well-Being · 2025-06 · 17 (3)
DOI: 10.1111/aphw.70038 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Psychology: Health and Well-Being, online erschienen am 16.05.2025. Verfasst von Shan Qiao und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Health Promotion, Education, and Behavior, Arnold School of Public Health, University of South Carolina, Columbia, South Carolina, USA. Hauptthemen laut MEDLINE: Qualitative Research, Artificial Intelligence, Maternal Health, Interviews as Topic. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: NIAID NIH HHS, NIH HHS, Population Research Center Seed Grant.
Abstract (Originalsprache)
Study Objectives : The coding of semistructured interview transcripts is a critical step for thematic analysis of qualitative data. However, the coding process is often labor‐intensive and time‐consuming. The emergence of generative artificial intelligence (GenAI) presents new opportunities to enhance the efficiency of qualitative coding. This study proposed a computational pipeline using GenAI to automatically extract themes from interview transcripts.
Methods
Using transcripts from interviews conducted with maternity care providers in South Carolina, we leveraged ChatGPT for inductive coding to generate codes from interview transcripts without a predetermined coding scheme. Structured prompts were designed to instruct ChatGPT to generate and summarize codes. The performance of GenAI was evaluated by comparing the AI‐generated codes with those generated manually.
Results
GenAI demonstrated promise in detecting and summarizing codes from interview transcripts. ChatGPT exhibited an overall accuracy exceeding 80% in inductive coding. More impressively, GenAI reduced the time required for coding by 81%.
Discussion
GenAI models are capable of efficiently processing language datasets and performing multi‐level semantic identification. However, challenges such as inaccuracy, systematic biases, and privacy concerns must be acknowledged and addressed. Future research should focus on refining these models to enhance reliability and address inherent limitations associated with their application in qualitative research.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Health Promotion, Education, and Behavior, Arnold School of Public Health, University of South Carolina, Columbia, South Carolina, USA.
- South Carolina SmartState Center for Heatlhcare Quality (CHQ), University of South Carolina, Columbia, South Carolina, USA.
- GISense Lab, Department of Geography and the Environment, The University of Texas at Austin, Austin, Texas, USA.
- Department of Geography, University of South Carolina, Columbia, South Carolina, USA.
- School of Civil, Environmental and Geomatic Engineering, University College London, London, UK.
- Department of Geography and Sustainability, University of Tennessee, Knoxville, Tennessee, USA.
ORCID-Profile: Shan Qiao, Yuhao Kang
Förderung
- NIAID NIH HHS
- NIH HHS
- Population Research Center Seed Grant
Zitieren
APA
Qiao, S., Fang, X., Wang, J., Zhang, R., Li, X., & Kang, Y. (2025). Generative AI for thematic analysis in a maternal health study: coding semistructured interviews using large language models. Applied Psychology: Health and Well-Being, 17(3). https://doi.org/10.1111/aphw.70038
Vancouver
Qiao S, Fang X, Wang J, Zhang R, Li X, Kang Y. Generative AI for thematic analysis in a maternal health study: coding semistructured interviews using large language models. Applied Psychology: Health and Well-Being. 2025;17(3). doi:10.1111/aphw.70038
BibTeX
@article{Qiao2025,
author = {Qiao, Shan and Fang, Xingyu and Wang, Junbo and Zhang, Ran and Li, Xiaoming and Kang, Yuhao},
title = {Generative AI for thematic analysis in a maternal health study: coding semistructured interviews using large language models},
journal = {Applied Psychology: Health and Well-Being},
year = {2025},
volume = {17},
number = {3},
doi = {10.1111/aphw.70038}
}
EUVIMED