Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Non-equilibrium in the Cell01:16

Non-equilibrium in the Cell

4.3K
An important concept in studying metabolism and energy is that of chemical equilibrium. Most chemical reactions are reversible. They can proceed in both directions, releasing energy into their environment in one direction, and absorbing it from the environment in the other direction. The same is true for the chemical reactions involved in cell metabolism, such as the breaking down and building up of proteins into and from individual amino acids, respectively. Reactants within a closed system...
4.3K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Digital health and consumer health informatics: past and future.

Medical research archives·2026
Same author

The gut microbial metabolite phenylacetylglutamine exacerbates severe acute pancreatitis by promoting ferroptosis and TLR4/NF-κB signaling pathways.

International immunopharmacology·2026
Same author

Hootation: A GUI and API library for ontology validation and verbalization.

Proceedings. IEEE International Conference on Semantic Computing·2026
Same author

Interactive Visualization of Patient Safety Events in MAUDE.

Studies in health technology and informatics·2026
Same author

A Maturity Model for REDCap-Based Patient-Facing Technologies: A Roadmap Toward Patient-Centered Intelligence.

Studies in health technology and informatics·2026
Same author

An Automated Synchronization Strategy for MAUDE Literature Dashboard.

Studies in health technology and informatics·2026
Same journal

The Essential Components and Critical Conditions for Success in a Learning Health System in Oncology.

Studies in health technology and informatics·2026
Same journal

Use of Artificial Intelligence in Screening for Adolescent Idiopathic Scoliosis: A Scoping Review.

Studies in health technology and informatics·2026
Same journal

Movement Related Biomechanics in Adolescent Idiopathic Scoliosis: A Review of Reviews.

Studies in health technology and informatics·2026
Same journal

The Impact of Surgical Correction of Adolescent Idiopathic Scoliosis Using Posterior Spinal Fusion on Selected Radiological Parameters and Respiratory Function.

Studies in health technology and informatics·2026
Same journal

Acute Effect of Physio-logic® Exercises on Muscle Tone and Stiffness in Adolescent Idiopathic Scoliosis Patients: A Preliminary Study.

Studies in health technology and informatics·2026
Same journal

Effects of Integrated Music and Occupational Therapy on Motor and Autonomic Function in Children with Neurogenic Scoliosis.

Studies in health technology and informatics·2026
See all related articles

Related Experiment Video

Updated: Jun 15, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

525

Developing a Generative AI-Powered Chatbot for Analyzing MAUDE Database.

Yue Yu1, Yuheng Shi1, Yubo Feng2

  • 1University of Texas Health Science Center at Houston, Houston, Texas, USA.

Studies in Health Technology and Informatics
|August 23, 2024
PubMed
Summary
This summary is machine-generated.

This AI-powered chatbot simplifies accessing medical device adverse event reports from the MAUDE database. It uses generative AI to interpret queries, retrieve data, and summarize findings for researchers.

Keywords:
Patient safetydata extractionincident reportsinformation retrieval

More Related Videos

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

991
Depletion of Mouse Cells from Human Tumor Xenografts Significantly Improves Downstream Analysis of Target Cells
07:10

Depletion of Mouse Cells from Human Tumor Xenografts Significantly Improves Downstream Analysis of Target Cells

Published on: July 29, 2016

12.6K

Related Experiment Videos

Last Updated: Jun 15, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

525
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

991
Depletion of Mouse Cells from Human Tumor Xenografts Significantly Improves Downstream Analysis of Target Cells
07:10

Depletion of Mouse Cells from Human Tumor Xenografts Significantly Improves Downstream Analysis of Target Cells

Published on: July 29, 2016

12.6K

Area of Science:

  • Medical Informatics
  • Artificial Intelligence in Healthcare
  • Regulatory Science

Background:

  • The MAUDE database contains critical open-access records of medical device adverse events.
  • Accessing and analyzing this data can be complex and time-consuming for researchers.
  • There is a need for tools to streamline the retrieval and understanding of this patient safety information.

Purpose of the Study:

  • To develop and evaluate a generative AI-powered chatbot for accessing and understanding MAUDE database records.
  • To enable natural language querying and summarization of medical device adverse event reports.
  • To improve the accessibility and usability of patient safety data for a wider research community.

Main Methods:

  • Utilized generative AI (GPT-4) and the openFDA API to build the chatbot.
  • Implemented natural language processing to interpret user queries and generate API calls.
  • Employed few-shot learning with query-URL pairs to enhance API call accuracy.
  • Conducted human expert ratings to evaluate the quality of generated summaries.

Main Results:

  • The chatbot successfully interprets natural language queries for MAUDE database searches.
  • Generative AI accurately generates API calls to retrieve adverse event data.
  • Content-based summaries of adverse event reports were evaluated positively by human experts.
  • A downloadable link to original reports enhances data accessibility.

Conclusions:

  • The developed chatbot significantly simplifies access to and understanding of medical device adverse event data.
  • This AI-driven approach enhances data replicability and manageability for researchers.
  • The initiative represents a key advancement in making patient safety data more accessible.