@Article{info:doi/10.2196/64447,
author="Castellanos, Arturo
and Jiang, Haoqiang
and Gomes, Paulo
and Vander Meer, Debra
and Castillo, Alfred",
title="Large Language Models for Thematic Summarization in Qualitative Health Care Research: Comparative Analysis of Model and Human Performance",
journal="JMIR AI",
year="2025",
month="Apr",
day="4",
volume="4",
pages="e64447",
keywords="artificial intelligence; generative AI; large language models; ChatGPT; machine learning; health care",
abstract="Background: The application of large language models (LLMs) in analyzing expert textual online data is a topic of growing importance in computational linguistics and qualitative research within health care settings. Objective: The objective of this study was to understand how LLMs can help analyze expert textual data. Topic modeling enables scaling the thematic analysis of content of a large corpus of data, but it still requires interpretation. We investigate the use of LLMs to help researchers scale this interpretation. Methods: The primary methodological phases of this project were (1) collecting data representing posts to an online nurse forum, as well as cleaning and preprocessing the data; (2) using latent Dirichlet allocation (LDA) to derive topics; (3) using human categorization for topic modeling; and (4) using LLMs to complement and scale the interpretation of thematic analysis. The purpose is to compare the outcomes of human interpretation with those derived from LLMs. Results: There is substantial agreement (247/310, 80{\%}) between LLM and human interpretation. For two-thirds of the topics, human evaluation and LLMs agree on alignment and convergence of themes. Furthermore, LLM subthemes offer depth of analysis within LDA topics, providing detailed explanations that align with and build upon established human themes. Nonetheless, LLMs identify coherence and complementarity where human evaluation does not. Conclusions: LLMs enable the automation of the interpretation task in qualitative research. There are challenges in the use of LLMs for evaluation of the resulting themes. ",
issn="2817-1705",
doi="10.2196/64447",
url="https://ai.jmir.org/2025/1/e64447",
url="https://doi.org/10.2196/64447"
}