Large Language Models for Thematic Summarization in Qualitative Health Care Research: Comparative Analysis of Model and Human Performance

Abstract BackgroundThe 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. ObjectiveThe objective of this study was t...

Full description

Saved in:
Bibliographic Details
Main Authors: Arturo Castellanos, Haoqiang Jiang, Paulo Gomes, Debra Vander Meer, Alfred Castillo
Format: Article
Language:English
Published: JMIR Publications 2025-04-01
Series:JMIR AI
Online Access:https://ai.jmir.org/2025/1/e64447
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Abstract BackgroundThe 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. ObjectiveThe 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. MethodsThe 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. ResultsThere 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. ConclusionsLLMs 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