Using a Large Language Model to Support Thematic Analysis of Patient Experiences in Chronic Illness Management: Comparative Qualitative Study

Clinical Snapshot

Key Findings

• P Value: Not applicable — qualitative study design

• Effect Size: Not applicable — qualitative comparative study; no quantitative effect size reported

• Primary Outcome: Both manual and LLM-assisted thematic analysis identified overlapping core themes: healthcare navigation and challenges, support systems and family dynamics, and emotional challenges and coping. Manual analysis produced more contextually rich and nuanced interpretations. LLM analysis generated a greater number of subthemes and demonstrated superior efficiency in processing large transcript volumes.

• Nnt Or Sensitivity: Not applicable — methodological comparative qualitative study. Method-specific unique themes: Manual analysis uniquely identified faith, caregiving roles, and proactive mindset; LLM uniquely identified future planning and multiple health conditions as distinct themes.

• Confidence Interval: Not applicable — qualitative study design

Clinical Application

LLM-assisted thematic analysis is technically feasible and potentially scalable for research teams with access to commercial LLM platforms. However, implementation requires careful attention to prompt design, data de-identification protocols, and human oversight of outputs. The hybrid approach proposed — combining LLM efficiency with human interpretive depth — is practically achievable but requires methodological standardisation before widespread adoption. Cost and institutional access to LLM APIs vary across research settings. In the Australian context, the use of commercial LLMs to process patient health narratives raises specific obligations under the Privacy Act 1988 (Cth) and the Australian Privacy Principles, particularly APP 8 regarding cross-border data disclosure when using US-based LLM providers. The NHMRC National Statement on Ethical Conduct in Human Research requires ethics committee review for such data processing arrangements. The RACGP supports patient-centred care for multimorbidity management, and qualitative research informing this area is directly relevant to general practice. Australian researchers considering LLM-assisted qualitative analysis should consult their institutional Human Research Ethics Committee (HREC) regarding data sovereignty and de-identification requirements before processing patient transcripts through third-party AI platforms. The AIHW's chronic disease surveillance priorities align with the multimorbidity focus of this study. Researchers and clinicians conducting qualitative health research with patients living with multimorbidity or other chronic conditions; applicable to any clinical context requiring large-scale analysis of patient narrative data including patient-reported outcomes, clinical interview data, and health service evaluations

Abstract

BACKGROUND: Qualitative health research often focuses on how patients experience and manage chronic illnesses, a topic that has been extensively studied in the literature. With the emergence of large language models (LLMs), such as Claude (Anthropic PBC) and ChatGPT (OpenAI), new opportunities are arising to support and scale the thematic analysis of narrative health data. However, their role and added value compared to traditional human-led approaches remain underexplored, particularly in complex clinical contexts such as multimorbidity. OBJECTIVE: We aim to evaluate the methodological contribution of LLM-assisted analysis by examining its ability to replicate and extend established qualitative insights, in comparison with traditional thematic analysis. METHODS: Semistructured interviews were conducted with 30 individuals living with two or more chronic illnesses. Transcripts were analyzed using both manual thematic coding and Claude 3.5 Sonnet. A structured comparison was conducted to identify shared and unique themes across the two approaches. The analysis examined thematic overlap, differences in subtheme identification, and variation in the level of detail between the methods. RESULTS: Both approaches identified similar core themes related to the patient experience, including health care navigation and challenges, support systems and family dynamics, and emotional challenges and coping. Manual analysis produced more contextually detailed interpretations, while the LLM approach identified a larger number of subthemes. Each method also revealed distinct themes: the manual analysis included themes such as faith, caregiving roles, and a proactive mindset, whereas the LLM identified themes such as future planning and multiple health conditions. The findings show both similarities and differences between the two approaches. The LLM analysis also demonstrated efficiency in processing large volumes of qualitative data. CONCLUSIONS: A hybrid approach that integrates artificial intelligence-assisted and human-led thematic analysis can enhance both analytical depth and scalability. These findings support the use of LLMs as a complementary tool in qualitative research, while highlighting the importance of combining automated pattern detection with human interpretation.

References

1. 1.Kivity, S., Barilan, Y. M., Noham, R., & Saban, M. (2026). Using a large language model to support thematic analysis of patient experiences in chronic illness management: Comparative qualitative study. Journal of Medical Internet Research. https://doi.org/10.2196/88677