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

Are normative expert systems appropriate for diagnostic pathology?

L W Diamond1, V G Mishka, A H Seal

  • 1Pathology Institute, University of Cologne, Germany.

Journal of the American Medical Informatics Association : JAMIA
|March 1, 1995
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

Working memory demands modulate memory brain state engagement.

bioRxiv : the preprint server for biology·2026
Same author

Results from the T2K Experiment on Neutrino Mixing Including a New Far Detector μ-like Sample.

Physical review letters·2026
Same author

Morphological and molecular characterisations of <i>Aphelenchoides vinhphucensis</i> sp. n. associated with rice from Vietnam.

Journal of helminthology·2025
Same author

First Differential Measurement of the Single π^{+} Production Cross Section in Neutrino Neutral-Current Scattering.

Physical review letters·2025
Same author

First Measurement of the Electron-Neutrino Charged-Current Pion Production Cross Section on Carbon with the T2K Near Detector.

Physical review letters·2025
Same author

Trauma-predictive brain network connectivity adaptively responds to mild acute stress.

Proceedings of the National Academy of Sciences of the United States of America·2025

Diagnostic reasoning is a problem-solving task, not decision-making. Probabilistic systems are better for clinical intervention choices than for accurate medical diagnosis, showing limited performance in studies.

Area of Science:

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

Background:

  • Current conceptual models of diagnostic reasoning are reviewed.
  • The appropriateness of probabilistic knowledge-based systems for medical diagnosis is debated.
  • Diagnosis is framed as a problem-solving task, distinct from decision-making.

Purpose of the Study:

  • To critically evaluate the utility of probabilistic knowledge-based systems in medical diagnosis.
  • To contrast diagnostic reasoning with clinical intervention decision-making.
  • To analyze the limitations of Bayesian expert systems in pathology diagnosis.

Main Methods:

  • Review of conceptual models for diagnostic reasoning.
  • Analysis of evidence supporting diagnosis as problem-solving.

Related Experiment Videos

  • Critique of a specific diagnostic Bayesian expert system for lymph node pathology.
  • Examination of empirical study results on Bayesian system performance.

    • Main Results:

    • Evidence suggests diagnosis is fundamentally a problem-solving process.
    • Probabilistic reasoning is deemed more suitable for clinical intervention choices than for diagnosis.
    • Diagnostic Bayesian systems demonstrate limited diagnostic performance, correctly identifying the diagnosis 60-70% of the time.
    • Bayesian systems' architecture does not effectively mirror expert knowledge representation and utilization.

    Conclusions:

    • Probabilistic knowledge-based systems have limitations in medical diagnosis due to their design.
    • Expert diagnostic reasoning differs from the computational approach of Bayesian systems.
    • Alternative models may be more appropriate for capturing the nuances of diagnostic problem-solving.