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 new paradigm for explaining and linking knowledge in diagnostic problem solving.

P W Jamieson1

  • 1University of Kansas Medical Center, Kansas City.

Journal of Clinical Engineering
|September 1, 1990
PubMed
Summary
This summary is machine-generated.

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

Automating clinical practice guidelines: a corporate-academic partnership.

Clinical laboratory management review : official publication of the Clinical Laboratory Management Association·1996
Same author

Idiopathic generalized myokymia.

Muscle & nerve·1994
Same author

Lambert-Eaton myasthenic syndrome associated with an ameloblastoma of the tibia.

Muscle & nerve·1993
Same author

Neurology research: a journal survey, 1980-1990.

Annals of neurology·1992
Same author

A computational model of levodopa pharmacodynamics in Parkinson's disease.

Clinical neuropharmacology·1991
Same author

A model for diagnosing and explaining multiple disorders.

Computers and biomedical research, an international journal·1991
Same journal

US Food and Drug Administration Seeks Input From Healthcare Technology Management Community on Medical Device Supply Disruption During COVID-19 Pandemic.

Journal of clinical engineering·2021
Same journal

Observations on COVID-19.

Journal of clinical engineering·2021
Same journal

Medical computing over the World Wide Web: use of forms and CGI scripts for constructing medical algorithm Web pages.

Journal of clinical engineering·1999
Same journal

Utilization of the Internet to deliver educational materials to healthcare professionals.

Journal of clinical engineering·1999
Same journal

Computer-aided learning--a solution for the training needs of users & maintainers of medical equipment.

Journal of clinical engineering·1999
Same journal

A study on the current situation in the biomedical technology and clinical engineering sector in Bulgaria--advances, trends and needs.

Journal of clinical engineering·1999
See all related articles

HyperExplain offers a novel method for generating patient-specific explanatory models in medical expert systems. This approach enhances understanding of diagnostic decisions without increasing computational costs.

Area of Science:

  • Medical Informatics
  • Artificial Intelligence in Medicine
  • Clinical Decision Support

Background:

  • Medical expert systems often rely on causal models for diagnostic reasoning.
  • A key challenge is providing computationally inexpensive yet informative explanations.
  • Users need to understand expert system decisions and access further details.

Purpose of the Study:

  • To introduce HyperExplain, a new method for linking explanations with conclusions in causal reasoning systems.
  • To develop patient-specific explanatory (PSE) models for enhanced medical expert system decision support.
  • To enable flexible explanation focusing based on clinical context and patient data.

Main Methods:

  • Developed HyperExplain to flexibly link explanations to conclusions from causal reasoning.

Related Experiment Videos

  • Created patient-specific explanatory (PSE) models tailored to individual cases.
  • Implemented a program demonstrating HyperExplain's capabilities in neurophysiology diagnostics.

    • Main Results:

    • HyperExplain successfully generates patient-specific explanatory models.
    • The method allows for dynamic adjustment of explanation focus.
    • Demonstrated utility in providing diagnostic assistance in neurophysiology.

    Conclusions:

    • HyperExplain addresses the challenge of computationally expensive explanations in medical expert systems.
    • The PSE model approach offers versatile decision support.
    • This method improves user comprehension and interaction with diagnostic systems.