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 probabilistic rule-based expert system

B S Todd1, R Stamper, P Macpherson

  • 1Programming Research Group, Oxford University Computing Laboratory, UK.

International Journal of Bio-Medical Computing
|September 1, 1993
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 natural experiment during lockdown and on-going care-home COVID-19 outbreaks showed a single dose of vaccine reduced hospitalisation and deaths of care-home residents in North West England.

Public health·2024
Same author

Community-level variation in TB testing history in Blantyre, Malawi.

The international journal of tuberculosis and lung disease : the official journal of the International Union against Tuberculosis and Lung Disease·2024
Same author

Missed opportunities for diagnosis and treatment in patients with TB symptoms: a systematic review.

Public health action·2022
Same author

Does tuberculosis screening improve individual outcomes? A systematic review.

EClinicalMedicine·2021
Same author

Determining the value of TB active case-finding: current evidence and methodological considerations.

The international journal of tuberculosis and lung disease : the official journal of the International Union against Tuberculosis and Lung Disease·2021
Same author

Psychosocial and pharmacologic interventions for methamphetamine addiction: protocol for a scoping review of the literature.

Systematic reviews·2020
Same journal

Nonlinear eye movement detection method for drowsiness studies.

International journal of bio-medical computing·1996
Same journal

Segmentation of auditory brainstem response signals.

International journal of bio-medical computing·1996
Same journal

A comparison of neural network and Bayes recognition approaches in the evaluation of the brainstem trigeminal evoked potentials in multiple sclerosis.

International journal of bio-medical computing·1996
Same journal

Methodology for using the UMLS as a background knowledge for the description of surgical procedures.

International journal of bio-medical computing·1996
Same journal

An MLP-based model for identifying qEEG in depression.

International journal of bio-medical computing·1996
Same journal

Guidelines for cost-effective implementation of Picture Archiving and Communication Systems. An approach building on practical experiences in three European hospitals.

International journal of bio-medical computing·1996
See all related articles

This study introduces a medical expert system using Bayesian networks and weighted inference rules for diagnosis. The system achieves comparable accuracy to traditional Bayesian methods, even with fewer parameters, making it suitable for small datasets.

Area of Science:

  • Medical Informatics
  • Artificial Intelligence in Medicine
  • Computational Statistics

Background:

  • Expert systems are crucial for medical diagnosis.
  • Traditional Bayesian methods often assume symptom independence, which may not hold true.
  • Estimating numerous parameters in Bayesian networks can be challenging with limited data.

Purpose of the Study:

  • To develop and evaluate a novel medical expert system.
  • To integrate Bayesian network modeling with weighted inference rules.
  • To improve diagnostic accuracy and parameter estimation efficiency.

Main Methods:

  • Combining Bayesian network modeling with weighted inference rules.
  • Objectively estimating rule weights from training data.

Related Experiment Videos

  • Utilizing Monte Carlo simulation for conditional probability estimation.

    • Main Results:

    • The developed medical expert system demonstrated diagnostic accuracy comparable to standard Bayesian classifiers.
    • The system achieved similar accuracy despite having significantly fewer numerical parameters (over 70 times less).
    • The proposed method shows promise for scenarios with small training datasets.

    Conclusions:

    • The novel expert system offers an efficient alternative for medical diagnosis.
    • This approach is particularly advantageous when dealing with limited case data.
    • Weighted inference rules combined with Bayesian networks provide a robust diagnostic tool.