• AutoQUEST: A Chain-of-Thought...

*Result*: AutoQUEST: A Chain-of-Thought Pipeline for Automated Question Generation and Validation in MAUDE Research.

Title:
AutoQUEST: A Chain-of-Thought Pipeline for Automated Question Generation and Validation in MAUDE Research.
Authors:
Hua L; Xinzhou Teachers University, Shanxi, China., Gong Y; University of Texas Health Science Center at Houston, Texas, USA.
Source:
Studies in health technology and informatics [Stud Health Technol Inform] 2025 Aug 07; Vol. 329, pp. 421-425.
Publication Type:
Journal Article
Language:
English
Journal Info:
Publisher: IOS Press Country of Publication: Netherlands NLM ID: 9214582 Publication Model: Print Cited Medium: Internet ISSN: 1879-8365 (Electronic) Linking ISSN: 09269630 NLM ISO Abbreviation: Stud Health Technol Inform Subsets: MEDLINE
Imprint Name(s):
Original Publication: Amsterdam ; Washington, DC : IOS Press, 1991-
MeSH Terms:
Data Mining*/methods , Databases, Factual* , Software* , Natural Language Processing*, Programming Languages ; Humans
Contributed Indexing:
Keywords: Chain-of-Thought; MAUDE database; SQL optimization; automation; large language models; prompt engineering
Entry Date(s):
Date Created: 20250808 Date Completed: 20250808 Latest Revision: 20250808
Update Code:
20260130
DOI:
10.3233/SHTI250874
PMID:
40775892
Database:
MEDLINE

*Further Information*

*The process of formulating research questions using the Manufacturer and User Facility Device Experience (MAUDE) database is often complicated by the challenges of data preprocessing and analysis. To meet the challenges, AutoQUEST, a Python-based prompt pipeline that capitalizes on large language models (LLMs) and Chain-of-Thought (CoT) has been proposed to facilitate the automation of question formulation. In five distinct test cases, AutoQUEST yielded an accuracy rate of 100% in generating valid research questions and attained query execution success rates ranging from 75% to 100%. This innovative CoT pipeline facilitates the research question formulating process, reduces technical barriers in data extraction and transformation, and enhances the efficacy of patient safety research concerning medical devices.*