A Novel Approach for Mixed-Methods Research Using Large Language Models: A Report Using Patients' Perspectives on Barriers to Arthroplasty.

Abstract

Mixed-methods research is valuable in health care to gain insights into patient perceptions. However, analyzing textual data from interviews can be time-consuming and require multiple analysts for investigator triangulation. This study aims to explore a novel approach to investigator triangulation in mixed-methods research by employing a large language model (LLM) for analyzing data from patient interviews. This study compared the thematic analysis and survey generation performed by human investigators and ChatGPT-4, which uses GPT-4 as its backbone model, using data from an existing study that explored patient perceptions of barriers to arthroplasty. The human- and ChatGPT-4-generated themes and surveys were compared and evaluated based on their representation of salient themes from a predetermined topic guide. ChatGPT-4 generated analogous dominant themes and a comprehensive corresponding survey as the human investigators but in significantly less time. The survey questions generated by ChatGPT-4 were less precise than those developed by human investigators. The mixed-methods flowchart proposes integrating LLMs and human investigators as a supplementary tool for the preliminary thematic analysis of qualitative data and survey generation. By utilizing a combination of LLMs and human investigators through investigator triangulation, researchers may be able to conduct more efficient mixed-methods research to better understand patient perspectives. Ethical and qualitative implications of using LLMs should be considered.