Large Language Models for Large-Scale, Rigorous Qualitative Analysis in Applied Health Services Research

TL;DR

This paper presents a flexible framework for integrating large language models into qualitative health research, demonstrating improved efficiency and rigor in analyzing large-scale multi-site data.

Contribution

It introduces a model- and task-agnostic framework for human-LLM qualitative analysis, applied to real-world health services research to enhance data synthesis and coding.

Findings

LLMs enabled timely feedback to practitioners.

Large-scale qualitative data informed theory and practice.

Framework supports diverse analytic aims in health research.

Abstract

Large language models (LLMs) show promise for improving the efficiency of qualitative analysis in large, multi-site health-services research. Yet methodological guidance for LLM integration into qualitative analysis and evidence of their impact on real-world research methods and outcomes remain limited. We developed a model- and task-agnostic framework for designing human-LLM qualitative analysis methods to support diverse analytic aims. Within a multi-site study of diabetes care at Federally Qualified Health Centers (FQHCs), we leveraged the framework to implement human-LLM methods for (1) qualitative synthesis of researcher-generated summaries to produce comparative feedback reports and (2) deductive coding of 167 interview transcripts to refine a practice-transformation intervention. LLM assistance enabled timely feedback to practitioners and the incorporation of large-scale qualitative data to inform theory and practice changes. This work demonstrates how LLMs can be integrated into applied health-services research to enhance efficiency while preserving rigor, offering guidance for continued innovation with LLMs in qualitative research.