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 methodology for generating computer-based explanations of decision-theoretic advice.

C P Langlotz1, E H Shortliffe, L M Fagan

  • 1Medical Computer Science, Stanford University School of Medicine, California 94305-5479.

Medical Decision Making : an International Journal of the Society for Medical Decision Making
|October 1, 1988
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

Deep Learning in Neuroradiology.

AJNR. American journal of neuroradiology·2018
Same author

Watson for Oncology and breast cancer treatment recommendations: agreement with an expert multidisciplinary tumor board.

Annals of oncology : official journal of the European Society for Medical Oncology·2018
Same author

The International Academy of Health Sciences Informatics: An Academy of Excellence.

Yearbook of medical informatics·2017
Same author

Medical Informatics Training and Research at Columbia University.

Yearbook of medical informatics·2016
Same author

Medical Informatics Training at Stanford University School of Medicine.

Yearbook of medical informatics·2016
Same author

Commentaries on the IMIA Award of Excellence Lecture by Reinhold Haux.

Yearbook of medical informatics·2014

This study introduces a computer program using symbolic reasoning to generate non-quantitative explanations for clinical decision support. This approach aims to make decision analysis more accessible and persuasive for physicians by avoiding complex mathematical arguments.

Area of Science:

  • Medical Informatics
  • Artificial Intelligence
  • Decision Science

Background:

  • Decision analysis offers valuable clinical decision support but is hindered by the difficulty of generating non-mathematical explanations for computer-based advice.
  • Physicians often find intuitive explanations, such as those derived from decision trees, more acceptable than purely quantitative outputs.

Purpose of the Study:

  • To develop a computer program that generates non-quantitative, symbolic explanations of decision analysis results for clinical decision support systems.
  • To enhance the usability and acceptance of decision-theoretic advice among practicing physicians.

Main Methods:

  • A novel approach combining decision analysis with symbolic reasoning techniques was implemented.
  • The program identifies structural asymmetries and variable inequalities in decision trees to explain differences in expected utility.

Related Experiment Videos

  • Symbolic expressions are generated and converted into plain English text, avoiding mathematical formulas, probabilities, or utility values.

    • Main Results:

    • The developed system successfully generates non-quantitative explanations for decision analysis outcomes.
    • Explanations focus on justifying the preferred choice by highlighting key decision variables and structural factors.
    • The combined approach aims to produce more persuasive and clinically acceptable justifications than either method alone.

    Conclusions:

    • Integrating symbolic processing with decision analysis can create more intuitive and understandable explanations for clinical decision support.
    • This method has the potential to increase the adoption and effectiveness of decision-theoretic tools in medical practice.
    • Non-mathematical explanations are crucial for bridging the gap between complex analytical models and clinical physician acceptance.