Automated Analysis of MAUDE Database Based on Chain-of-Thought Reasoning

Corresponding author: HUA Lei, leihua@xztu.edu.cn

DOI: 10.12201/bmr.202506.00070

•  

  Abstract: Purpose/Significance: To address the challenges of high technical complexity and low efficiency in MAUDE database analysis, this study designed and implemented the AutoQUEST automated analysis framework. By integrating large language model and chain-of-thought reasoning techniques, the framework reduces the complexity of database analysis and accelerates research output. Methods/Process: The AutoQUEST framework employs a dual-chain structure combining think and do chains, equipped with capabilities for automatic generation of research questions, structured SQL query formulation, and data analysis. Five distinct cases were used to evaluate the framework in terms of query success rates, execution duration, and report quality. Results/Conclusions: In the best case, the framework achieved a 100% query success rate, an execution time of 158 seconds, and an overall quality score of 4.74 out of 5. By effectively automating high-quality analysis of the MAUDE database, the framework provides convenient and reliable data analysis support to healthcare institutions, manufacturers, and regulatory authorities.

  Key words: medical device adverse event, MAUDE database; large language model; chain-of-thought reasoning

  Submit time: 24 June 2025

  Copyright: The copyright holder for this preprint is the author/funder, who has granted biomedRxiv a license to display the preprint in perpetuity.
• html

• 图表

• wangyaoguo, tangshishi, liuhongze, anyuting, zhouyi. Research on optimization of osteoporosis disease database construction process based on local large model. 2024. doi: 10.12201/bmr.202410.00002

  long si zhe, zhang wu jun. Data Governance-based Practice for Constructing Specialized Disease Database. 2022. doi: 10.12201/bmr.202207.00012

  WU Hong, HU Jun, CHEN Erzhen, DONG Chenjie, LI Jianhua, YE Qi. Construction of a Medical Quality Control Application System Based on Large Language Models. 2025. doi: 10.12201/bmr.202503.00004

  Lianwanmin. Construction practice of cerebrovascular disease database based on Data Governance. 2022. doi: 10.12201/bmr.202210.00011

  niuyuxiang, geshanshan, wanglihua. Exploration and research of electronic medical record generation technology from traditional NLP to large language model. 2024. doi: 10.12201/bmr.202412.00080

  ZHANG YANAN. Exploration and Practice of Constructing Structured Specialized Disease Database based on NLP for Medical Records. 2024. doi: 10.12201/bmr.202406.00007

  Guo Shaoyou, Liang Hanxiao, Li Xufei, Wen Taohong. Payment Sharing of Medical Knowledge Chain Based on Blockchain. 2021. doi: 10.12201/bmr.202111.00005

  Zhao Hanqing. Knowledge reasoning and intelligent recommendation based on knowledge map of Chinese patent medicine. 2024. doi: 10.12201/bmr.202404.00018

  LIU Mi-mi, DU Guo-xia, ZHOU Yi, WU Bin, WU Xiao-ying. Construction and preliminary application of liver cirrhosis special disease database. 2021. doi: 10.12201/bmr.202104.00014

  zhangbaiping. Constructing patient diagnosis and treatment knowledge graph from relational database of EMR systemZHANG. 2021. doi: 10.12201/bmr.202110.00031

• ID	Submit time	Number	Download
  1	2025-03-21	10.12201/bmr.202506.00070V1	Download

• Public  Anonymous  To author only Submit Comments