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

A knowledge-based model construction approach to medical decision making

L Ngo1, P Haddawy

  • 1Department of Electrical Engineering and Computer Science University of Wisconsin-Milwaukee 53201, USA. liem@cs.uwm.edu

Proceedings : a Conference of the American Medical Informatics Association. AMIA Fall Symposium
|January 1, 1996
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

[Vasectomy under local anesthesia, retrospective evaluation of patient satisfaction in CH Annecy Genevois].

Progres en urologie : journal de l'Association francaise d'urologie et de la Societe francaise d'urologie·2023
Same author

Spontaneous eyelid and subconjunctival socket bleeding related to vitamin C deficiency: First case report.

Journal francais d'ophtalmologie·2020
Same author

Memory advancement by intranasal insulin in type 2 diabetes (MemAID) randomized controlled clinical trial: Design, methods and rationale.

Contemporary clinical trials·2020
Same author

Effectiveness of the Multilayered Caries Model and Visuo-tactile Virtual Reality Simulator for Minimally Invasive Caries Removal: A Randomized Controlled Trial.

Operative dentistry·2018
Same author

Post-mortem prediction of primal and selected retail cut weights of New Zealand lamb from carcass and animal characteristics.

Meat science·2015
Same author

Comparison of clinical and cone beam computed tomography measurements to diagnose furcation involvement.

International journal of dental hygiene·2014
Same journal

Identification of findings suspicious for breast cancer based on natural language processing of mammogram reports.

Proceedings : a conference of the American Medical Informatics Association. AMIA Fall Symposium·1997
Same journal

Searching for information on the Internet using the UMLS and Medical World Search.

Proceedings : a conference of the American Medical Informatics Association. AMIA Fall Symposium·1997
Same journal

Text structures in medical text processing: empirical evidence and a text understanding prototype.

Proceedings : a conference of the American Medical Informatics Association. AMIA Fall Symposium·1997
Same journal

A natural language parsing system for encoding admitting diagnoses.

Proceedings : a conference of the American Medical Informatics Association. AMIA Fall Symposium·1997
Same journal

Meeting clinician information needs by integrating access to the medical record and knowledge resources via the Web.

Proceedings : a conference of the American Medical Informatics Association. AMIA Fall Symposium·1997
Same journal

Electronic forms: benefits drawbacks of a World Wide Web-based approach to data entry.

Proceedings : a conference of the American Medical Informatics Association. AMIA Fall Symposium·1997
See all related articles

This study introduces a framework for probabilistic treatment plans using Bayesian networks (BNs). An algorithm generates BN-graphs to project plans and find optimal strategies, enhancing decision-making in complex scenarios.

Area of Science:

  • Artificial Intelligence
  • Decision Theory
  • Probabilistic Graphical Models

Background:

  • Representing probabilistic effects of actions and contingent treatment plans is crucial for complex decision-making.
  • Existing methods may lack a structured approach for projecting and optimizing treatment plans under uncertainty.

Purpose of the Study:

  • To present a novel framework for representing probabilistic effects of actions and contingent treatment plans.
  • To develop an algorithm (BNG) for generating Bayesian networks (BNs) to compute posterior probabilities.
  • To address the projection and optimal generation of contingent treatment plans using a BN-graph structure.

Main Methods:

  • Developed a language with declarative semantics for probabilistic representations.
  • Implemented the BNG algorithm to generate Bayesian networks.

Related Experiment Videos

  • Constructed a BN-graph, a structure of interrelated BNs, for plan projection.
  • Utilized propagation procedures on BN-graphs for plan analysis.
  • Introduced a programming-like language to describe plan spaces for optimal plan generation.

    • Main Results:

    • The framework enables the representation of probabilistic effects of actions and contingent treatment plans.
    • The BNG algorithm successfully generates Bayesian networks for query probability computation.
    • The BN-graph structure facilitates the projection of contingent treatment plans.
    • Procedures for finding optimal plans from structured plan spaces were presented.

    Conclusions:

    • The proposed framework offers a robust method for probabilistic reasoning in treatment planning.
    • The BN-graph approach provides an effective mechanism for projecting and optimizing complex treatment plans.
    • The developed language and algorithms enhance automated decision support in uncertain environments.