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 Experiment Videos

A multiagent architecture for developing medical information retrieval agents.

Steven Walczak1

  • 1Health Administration and Information Systems Programs, The Business School, University of Colorado at Denver, Campus Box 165, PO Box 173364, Denver, Colorado 80217-3364, USA. swalczak@carbon.cudenver.edu

Journal of Medical Systems
|October 31, 2003
PubMed
Summary

Physicians can now better manage medical information overload. A new multi-agent system filters the web, significantly increasing relevant information for patient care.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Artificial Intelligence in Surgical Research: Accomplishments and Future Directions.

American journal of surgery·2023
Same author

A neural network analysis of the effect of high and low frailty index indicators on predicting elective surgery discharge destinations.

PloS one·2023
Same author

Predicting Elective Surgical Patient Outcome Destination Based on the Preoperative Modified Frailty Index and Laboratory Values.

The Journal of surgical research·2022
Same author

Predicting Crime and Other Uses of Neural Networks in Police Decision Making.

Frontiers in psychology·2021
Same author

Artificial neural networks in surgical research.

American journal of surgery·2020
Same author

Prediction of perioperative transfusions using an artificial neural network.

PloS one·2020

Area of Science:

  • Medical Informatics
  • Artificial Intelligence
  • Information Retrieval

Background:

  • The exponential growth of online information presents a significant challenge for physicians.
  • Access to up-to-date medical information is crucial for delivering quality patient care.
  • Existing search tools often fail to adequately filter the vast amount of available data.

Purpose of the Study:

  • To develop and describe a multiple agent architecture for efficient information retrieval from the World Wide Web (WWW).
  • To enable physicians to filter information and retrieve only data relevant to current patient treatments.
  • To address domain-specific constraints in medical agent-based information retrieval.

Main Methods:

  • Development of a novel multiple agent architecture.

Related Experiment Videos

  • Integration of the World Wide Web (WWW) and other explicit information resources.
  • Simulation-based evaluation of the proposed architecture.

    • Main Results:

    • A 97% decrease in information overload was observed compared to existing meta-search tools.
    • An 85% increase in information relevancy was achieved over existing meta-search tools.
    • Substantial improvements in information retrieval efficiency were demonstrated over standard search engines.

    Conclusions:

    • The proposed multiple agent architecture effectively reduces information overload for physicians.
    • The system significantly enhances the relevancy of retrieved medical information.
    • Agent-based information retrieval offers a promising solution for navigating complex medical data landscapes.