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

Constructing influence views from data to support dynamic decision making in medicine.

X Z Qi1, T Y Leong

  • 1Medical Computing Laboratory, Department of Computer Science, School of Computing, National University of Singapore, Singapore. qixz@comp.nus.edu.sg

Studies in Health Technology and Informatics
|October 18, 2001
PubMed
Summary

This study introduces an automated method for building dynamic decision models in medicine using large datasets. The approach efficiently constructs influence views with high accuracy, aiding complex 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 Medical Informatics Program at the National University of Singapore.

Yearbook of medical informatics·2016
Same author

Adaptation of the thylakoid membranes of pea chloroplasts to light intensities. I. Study on the distribution of chlorophyll-protein complexes.

Photosynthesis research·2014
Same author

Adaptation of the thylakoid membranes of pea chloroplasts to light intensities. II. Regulation of electron transport capacities, electron carriers, coupling factor (CF1) activity and rates of photosynthesis.

Photosynthesis research·2014
Same author

Complete mitochondrial genome sequence of the humphead wrasse, Cheilinus undulatus.

Genetics and molecular research : GMR·2013
Same author

The birth and evolution of a discipline devoted to information in biomedicine and health care. As reflected in its longest running journal.

Methods of information in medicine·2011
Same author

Discussion of "biomedical ontologies: toward scientific debate".

Methods of information in medicine·2011

Area of Science:

  • Medical Informatics
  • Computational Medicine
  • Decision Science

Background:

  • Medical decision-making is complex, often involving time and uncertainty.
  • Dynamic decision models can aid this process by explicitly considering these factors.
  • Automating the construction of these models from data is a significant challenge.

Purpose of the Study:

  • To develop an automated approach for constructing dynamic decision models from large medical databases.
  • To represent these models within the DynaMoL (dynamic decision modeling language) framework using influence views.
  • To evaluate the efficiency and fidelity of the proposed construction method.

Main Methods:

  • Learning the structure of influence views using the minimal description length (MDL) principle.

Related Experiment Videos

  • Obtaining model conditional probabilities via Bayesian methods.
  • Utilizing the DynaMoL framework for model representation.

    • Main Results:

    • The developed system can automatically learn influence view structures from medical data.
    • Conditional probabilities are effectively estimated using Bayesian techniques.
    • Experimental results show high-fidelity construction of influence views.

    Conclusions:

    • The proposed method enables efficient and accurate automatic construction of dynamic decision models.
    • This approach facilitates the integration of time and uncertainty into medical decision support systems.
    • The DynaMoL framework provides a robust structure for representing these complex models.