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

Toward normative expert systems: Part II. Probability-based representations for efficient knowledge acquisition and

D E Heckerman1, B N Nathwani

  • 1Department of Computer Science, University of California, Los Angeles.

Methods of Information in Medicine
|June 1, 1992
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

A meta-analysis of Hodgkin lymphoma reveals 19p13.3 TCF3 as a novel susceptibility locus.

Nature communications·2014
Same author

Eliciting cytotoxic T-lymphocyte responses from synthetic vectors containing one or two epitopes in a C57BL/6 mouse model using peptide-containing biodegradable microspheres and adjuvants.

Vaccine·2014
Same author

Fecal microbiota diversity in survivors of adolescent/young adult Hodgkin lymphoma: a study of twins.

British journal of cancer·2013
Same author

Diffuse large B-cell lymphoma: a clinicopathologic analysis of 444 cases classified according to the updated Kiel classification.

Leukemia & lymphoma·2002
Same author

Peripheral T-cell lymphoma (excluding anaplastic large-cell lymphoma): results from the Non-Hodgkin's Lymphoma Classification Project.

Annals of oncology : official journal of the European Society for Medical Oncology·2002
Same author

Hyperplasia of mantle/marginal zone B cells with clear cytoplasm in peripheral lymph nodes. A clinicopathologic study of 35 cases.

American journal of clinical pathology·2001

This study introduces novel methods for building diagnostic expert systems, like Pathfinder, which aids pathologists in diagnosing lymph-node diseases by efficiently handling complex evidence dependencies using belief networks.

Area of Science:

  • Medical Informatics
  • Artificial Intelligence in Medicine
  • Pathology

Background:

  • Expert systems offer decision-theoretic approaches to medical diagnosis.
  • Pathological diagnosis, particularly for lymph-node diseases, involves complex evidence evaluation.
  • Existing methods for representing dependencies among diagnostic evidence can be challenging to implement.

Purpose of the Study:

  • To address practical challenges in constructing and utilizing normative expert systems for diagnosis.
  • To enhance the efficiency of diagnostic processes in surgical pathology.
  • To introduce novel representations for building complex belief networks.

Main Methods:

  • Examined the Pathfinder expert system for lymph-node disease diagnosis.
  • Described belief networks as graphical representations of probabilistic dependencies.

Related Experiment Videos

  • Introduced similarity networks for constructing large belief networks from independent subnetworks.
  • Introduced partitions for facilitating probability assessment in belief networks.
  • Main Results:

    • Pathfinder efficiently constructs differential diagnoses using belief networks, even with dependent evidence.
    • Similarity networks enable the construction of complex belief networks by modularizing domain knowledge.
    • Partitions simplify the assessment of probabilities required for belief network construction.
    • The developed representations made the practical construction of Pathfinder feasible.

    Conclusions:

    • Similarity networks and partitions are effective tools for building complex, decision-theoretic diagnostic expert systems.
    • These methods improve the practical application of belief networks in medical diagnosis.
    • The Pathfinder system demonstrates the utility of these advanced representations in surgical pathology.