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

Diabetes expert systems: planning for long term use.

P Compton1, R Jansen

  • 1Garvan Institute of Medical Research, St. Vincent's Hospital, Sydney, Australia.

Hormone and Metabolic Research. Supplement Series
|January 1, 1990
PubMed
Summary

Expert systems can aid diabetes management but are hard to maintain. Problems arise because expert knowledge is context-dependent, making it difficult to extract and use in expert 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

Low-noise φ-OTDR employing nonlinear optical preamplification for distributed acoustic sensing.

Applied optics·2023
Same author

Activated Carbon Modifications for Heterogeneous Fenton-Like Catalysis.

Journal of chemical engineering and catalysis·2023
Same author

Waveguide-based absorption measurement system for visible wavelength applications.

Biomedical optics express·2021
Same author

The prevalence of mental health problems in sub-Saharan adolescents living with HIV: a systematic review.

Global mental health (Cambridge, England)·2021
Same author

Paediatric Posttraumatic Cyst-Like Lesions: A Report of Two Cases and Review of the Literature.

Case reports in orthopedics·2020
Same author

Global longitudinal strain to predict left ventricular dysfunction in asymptomatic patients with severe mitral valve regurgitation: literature review.

Netherlands heart journal : monthly journal of the Netherlands Society of Cardiology and the Netherlands Heart Foundation·2019

Area of Science:

  • Artificial Intelligence
  • Medical Informatics
  • Diabetes Management

Background:

  • Expert systems show promise for assisting diabetes control.
  • Current expert systems face significant challenges in long-term maintenance and usability.
  • The difficulty in maintaining expert systems stems from how expert knowledge is represented.

Purpose of the Study:

  • To investigate the challenges in maintaining expert systems for diabetes management.
  • To identify the root causes of difficulties in expert system maintenance.
  • To propose improved strategies for capturing and utilizing expert knowledge in context.

Main Methods:

  • Analysis of maintenance issues in the GARVAN-ES1 expert system.
  • Examination of expert knowledge representation and justification processes.
  • Exploration of context-dependent knowledge acquisition.

Main Results:

  • Expert knowledge is often justified post-hoc and is highly context-specific.
  • Extracting knowledge out of its original context leads to maintenance problems.
  • Existing methods struggle to capture the contextual nature of expert decision-making.

Conclusions:

  • Future expert systems must capture knowledge in context to be maintainable.
  • Flexible tools are needed to adapt expert system knowledge bases to different contexts.
  • Strategies like 'ripple down rules' and 'knowledge dictionaries' offer potential solutions.

Related Experiment Videos