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

Medical expert systems based on causal probabilistic networks.

S Andreassen1, F V Jensen, K G Olesen

  • 1Aalborg University, Institute of Electronic Systems, Denmark.

International Journal of Bio-Medical Computing
|May 1, 1991
PubMed
Summary

Causal probabilistic networks (CPNs) provide a unified framework for medical expert systems, offering an attractive alternative to traditional methods. These networks enable robust reasoning under uncertainty and facilitate knowledge acquisition for improved medical decision-making.

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 Education in Medical Informatics.

Yearbook of medical informatics·2016
Same author

Image and Signal Processing.

Yearbook of medical informatics·2016
Same author

Quantifying the associations between antibiotic exposure and resistance - a step towards personalised antibiograms.

European journal of clinical microbiology & infectious diseases : official publication of the European Society of Clinical Microbiology·2016
Same author

Modelling and control in biomedical systems.

Computer methods and programs in biomedicine·2011
Same author

Symposium on Modelling and Control in Biomedical Systems, Aalborg, Denmark, 2009. Introduction.

Computer methods and programs in biomedicine·2011
Same author

EMG-torque dynamics at different contraction levels in human ankle muscles.

Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology·2010

Area of Science:

  • Artificial Intelligence
  • Medical Informatics
  • Probabilistic Reasoning

Background:

  • Traditional medical expert systems often struggle with diverse reasoning types.
  • Causal probabilistic networks (CPNs) offer a uniform conceptual framework for medical reasoning.
  • CPNs present an attractive alternative to existing methods based on prototype systems.

Purpose of the Study:

  • To introduce causal probabilistic networks (CPNs) as a powerful tool for building advanced medical expert systems.
  • To highlight the advantages of CPNs in handling uncertainty and diverse medical reasoning.
  • To explore the potential of CPNs in decision support for test and therapy planning.

Main Methods:

  • Utilizing Causal Probabilistic Networks (CPNs) as an intensional model of medical domains.

Related Experiment Videos

  • Employing recent advancements in Bayesian inference for computationally efficient methods.
  • Integrating decision theory for rational test and therapy planning.

    • Main Results:

    • CPNs provide a sound framework for causal, diagnostic, deductive, and abductive reasoning under uncertainty.
    • The representation in CPNs facilitates the incorporation of 'deep knowledge,' such as physiological models.
    • Learning facilities in CPNs enable a smooth transition from expert opinion to data-driven statistics.

    Conclusions:

    • Causal probabilistic networks (CPNs) offer a unified and effective approach to medical expert systems.
    • CPNs support robust reasoning under uncertainty and facilitate knowledge representation and learning.
    • The integration of CPNs with decision theory holds promise for optimizing medical planning and decision-making.