Position: Thematic Analysis of Unstructured Clinical Transcripts with Large Language Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yi, Seungjun, Nguyen, Joakim, Lim, Terence, Well, Andrew, Skrovan, Joseph, Beri, Mehak, Lee, YongGeon, Radhakrishnan, Kavita, Leqi, Liu, Markey, Mia, Ding, Ying
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908562632998912
author Yi, Seungjun
Nguyen, Joakim
Lim, Terence
Well, Andrew
Skrovan, Joseph
Beri, Mehak
Lee, YongGeon
Radhakrishnan, Kavita
Leqi, Liu
Markey, Mia
Ding, Ying
author_facet Yi, Seungjun
Nguyen, Joakim
Lim, Terence
Well, Andrew
Skrovan, Joseph
Beri, Mehak
Lee, YongGeon
Radhakrishnan, Kavita
Leqi, Liu
Markey, Mia
Ding, Ying
contents This position paper examines how large language models (LLMs) can support thematic analysis of unstructured clinical transcripts, a widely used but resource-intensive method for uncovering patterns in patient and provider narratives. We conducted a systematic review of recent studies applying LLMs to thematic analysis, complemented by an interview with a practicing clinician. Our findings reveal that current approaches remain fragmented across multiple dimensions including types of thematic analysis, datasets, prompting strategies and models used, most notably in evaluation. Existing evaluation methods vary widely (from qualitative expert review to automatic similarity metrics), hindering progress and preventing meaningful benchmarking across studies. We argue that establishing standardized evaluation practices is critical for advancing the field. To this end, we propose an evaluation framework centered on three dimensions: validity, reliability, and interpretability.
format Preprint
id arxiv_https___arxiv_org_abs_2509_14597
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Position: Thematic Analysis of Unstructured Clinical Transcripts with Large Language Models
Yi, Seungjun
Nguyen, Joakim
Lim, Terence
Well, Andrew
Skrovan, Joseph
Beri, Mehak
Lee, YongGeon
Radhakrishnan, Kavita
Leqi, Liu
Markey, Mia
Ding, Ying
Computation and Language
This position paper examines how large language models (LLMs) can support thematic analysis of unstructured clinical transcripts, a widely used but resource-intensive method for uncovering patterns in patient and provider narratives. We conducted a systematic review of recent studies applying LLMs to thematic analysis, complemented by an interview with a practicing clinician. Our findings reveal that current approaches remain fragmented across multiple dimensions including types of thematic analysis, datasets, prompting strategies and models used, most notably in evaluation. Existing evaluation methods vary widely (from qualitative expert review to automatic similarity metrics), hindering progress and preventing meaningful benchmarking across studies. We argue that establishing standardized evaluation practices is critical for advancing the field. To this end, we propose an evaluation framework centered on three dimensions: validity, reliability, and interpretability.
title Position: Thematic Analysis of Unstructured Clinical Transcripts with Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2509.14597