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

Evaluation stages and design steps for knowledge-based systems in medicine.

A Rossi-Mori1, D M Pisanelli, F L Ricci

  • 1Istituto Tecnologie Biomediche CNR, Rome, Italy.

Medical Informatics = Medecine Et Informatique
|July 1, 1990
PubMed
Summary

A new methodology is proposed for designing advanced medical knowledge management systems, shifting focus from prototypes to comprehensive evaluation. This approach considers user environment impact, system efficiency, and expert consensus for atypical cases.

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

The impact of rotary blood pump in conjunction with mechanical ventilation on ventricular energetic parameters - numerical simulation.

Methods of information in medicine·2006
Same author

Clinical guidelines as plans--an ontological theory.

Methods of information in medicine·2006
Same author

Modelling in the study of interaction of Hemopump device and artificial ventilation.

Computers in biology and medicine·2005
Same author

In vivo and simulation study of artificial ventilation effects on energetic variables in cardiosurgical patients.

Methods of information in medicine·2005
Same author

The creation of an ontology of clinical document names.

Studies in health technology and informatics·2001
Same author

Relevance of mandates, notifications and threads in the management of continuity of care.

Studies in health technology and informatics·2001

Area of Science:

  • Medical Informatics
  • Artificial Intelligence in Healthcare
  • Knowledge Management Systems

Background:

  • Early artificial intelligence experiments have paved the way for advanced medical knowledge management systems.
  • The focus in developing these systems is shifting from prototype implementation to rigorous evaluation.

Purpose of the Study:

  • To propose a methodology for designing real-world medical knowledge management systems that integrate with the user's 'knowledge environment'.
  • To re-examine evaluation stages as a framework for defining design goals and criteria.

Main Methods:

  • Adapting field evaluation techniques from similar knowledge management contexts (e.g., drugs, epidemiology).
  • Examining system impact on healthcare provision (cost-benefit, task sharing).

Related Experiment Videos

  • Assessing end-user effectiveness, long-term behavioral effects, and intrinsic system efficiency (knowledge base correctness, reasoning appropriateness).

    • Main Results:

    • The study emphasizes differentiating test samples into obvious, typical, and atypical cases for evaluation and design.
    • It highlights challenges in establishing 'gold standards' for atypical cases due to expert disagreement.
    • Two design approaches, 'standardization mode' and 'brain-storming mode', are proposed to address these challenges.

    Conclusions:

    • A structured evaluation framework is crucial for designing effective medical knowledge management systems.
    • The methodology accounts for the user's operational context and the system's intrinsic qualities.
    • Addressing expert disagreement in atypical cases is vital for robust system design and evaluation.