Leveraging LLMs to Understand Narratives in MAUDE Reports

Authors

• Yuheng Shi
• Yang Gong

Language

English

Publication Date

4-8-2025

Journal

Studies in Health Technology and Informatics

DOI

10.3233/SHTI250076

PMID

40200473

Abstract

Interest in using the MAUDE database to investigate adverse events linked to medical devices has been growing. Yet, the narrative sections of these reports remain largely unexplored, leaving valuable insights unutilized and creating an incomplete understanding of these events. To bridge this gap, we employ large language models (LLMs) to analyze and interpret these narratives. Using OpenAI's GPT-4-turbo model, we focused on MAUDE reports involving endoscopic clips to identify uncoded surgical procedures and uncover additional insights. This approach showcases the potential of LLMs in processing narrative content, offering a more efficient and cost-effective alternative to previous methods and supporting the translation of MAUDE reports into actionable knowledge for clinical practice.

Keywords

Narration, Natural Language Processing, Humans, Electronic Health Records, Surgical Instruments, Data Mining

Published Open-Access

yes

Recommended Citation

Yuheng Shi and Yang Gong, "Leveraging LLMs to Understand Narratives in MAUDE Reports" (2025). Faculty, Staff and Student Publications. 859.
https://digitalcommons.library.tmc.edu/uthshis_docs/859