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

Augmented transition networks as a representation for knowledge-based history-taking systems.

A D Poon1, K B Johnson, L M Fagan

  • 1Section on Medical Informatics, Stanford University School of Medicine, CA 94305-5479.

Proceedings. Symposium on Computer Applications in Medical Care
|January 1, 1992
PubMed
Summary

Automated medical history-taking systems lack a standard for representing interviewing knowledge. This study proposes using augmented transition networks (ATNs) as a flexible and generalizable solution for knowledge representation in these systems.

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

Opportunities and challenges for biomarker discovery using electronic health record data.

Trends in molecular medicine·2023
Same author

REDCap on FHIR: Clinical Data Interoperability Services.

Journal of biomedical informatics·2021
Same author

Floral Colonization Dynamics and Specificity of <i>Aureobasidium pullulans</i> Strains Used to Suppress Fire Blight of Pome Fruit.

Plant disease·2019
Same author

Effect of Epiphytic Fungi on Brown Rot Blossom Blight and Latent Infections in Sweet Cherry.

Plant disease·2019
Same author

Analysis of Resistance to Eastern Filbert Blight in Corylus avellana.

Plant disease·2019
Same author

Secondary Colonization of Pear Blossoms by Two Bacterial Antagonists of the Fire Blight Pathogen.

Plant disease·2019

Area of Science:

  • Artificial Intelligence in Medicine
  • Natural Language Processing
  • Knowledge Representation

Background:

  • Automated medical history-taking systems aim to streamline patient data collection.
  • Existing systems exhibit variability in control, input/output modalities, and question strategies.
  • A lack of standardized knowledge representation hinders interoperability and development.

Purpose of the Study:

  • To introduce augmented transition networks (ATNs) as a standardized method for representing interviewing knowledge in automated history-taking systems.
  • To demonstrate the applicability of ATNs using the Q-MED speech-driven system.
  • To highlight the generalizability of ATNs for diverse knowledge-based interviewing systems.

Main Methods:

  • Utilized augmented transition networks (ATNs) to model the expert knowledge required for medical interviews.

Related Experiment Videos

  • Developed the Q-MED program, a speech-driven automated history-taking system, employing ATNs for knowledge representation.
  • Analyzed the structural and functional characteristics of ATNs relevant to interviewing systems.

    • Main Results:

    • Augmented transition networks (ATNs) provide an explicit and hierarchical structure for representing interviewing knowledge.
    • The Q-MED system successfully demonstrated the practical application of ATNs in a speech-driven context.
    • ATNs offer generality, making them suitable for a wide range of knowledge-based interviewing applications.

    Conclusions:

    • Augmented transition networks (ATNs) offer a standardized, explicit, and hierarchical approach to knowledge representation in automated medical history-taking.
    • The ATN framework enhances the development and potential of intelligent interviewing systems.
    • This representation method facilitates the creation of more robust and adaptable medical AI.