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

Multiply sectioned Bayesian networks for neuromuscular diagnosis

Y Xiang1, B Pant, A Eisen

  • 1Department of Computer Science, University of Regina, Sask., Canada.

Artificial Intelligence in Medicine
|August 1, 1993
PubMed
Summary

A new system, PAINULIM, uses Bayesian networks to diagnose painful or impaired upper limbs. Preliminary tests show good clinical performance in identifying neuromuscular conditions.

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

Revisiting the timing of intervention in necrotising pancreatitis.

Intensive care medicine·2025
Same author

Prone position for acute respiratory distress syndrome and the hazards of meta-analysis.

Pulmonology·2023
Same author

Overall survival in the OlympiA phase III trial of adjuvant olaparib in patients with germline pathogenic variants in BRCA1/2 and high-risk, early breast cancer.

Annals of oncology : official journal of the European Society for Medical Oncology·2022
Same author

Study into the spread of heat from thermo-optic silicon photonic elements.

Optics express·2021
Same author

Digital Subtraction Angiography a Door Opener for Neurosurgical Residents who want to Perform Neurointerventional Procedures.

Kathmandu University medical journal (KUMJ)·2021
Same author

Supercomputer-Based Ensemble Docking Drug Discovery Pipeline with Application to Covid-19.

Journal of chemical information and modeling·2020

Area of Science:

  • Neurology
  • Biomedical Engineering
  • Artificial Intelligence in Medicine

Background:

  • Developing accurate diagnostic tools for neuromuscular disorders is crucial for effective patient treatment.
  • Existing diagnostic systems may face computational challenges in complex application domains.
  • User interface design is important for focusing on specific areas of interest in diagnostics.

Purpose of the Study:

  • To present the knowledge representation challenges encountered during the development of a neuromuscular diagnostic system.
  • To introduce a prototype system, PAINULIM, for diagnosing painful or impaired upper limbs.
  • To describe the use of multiply sectioned Bayesian networks to address computational overhead and enhance user interface focus.

Main Methods:

  • Development of a prototype neuromuscular diagnostic system named PAINULIM.

Related Experiment Videos

  • Application of Bayesian networks for knowledge representation and diagnostic reasoning.
  • Implementation of multiply sectioned Bayesian networks to manage complexity and provide focused displays.

    • Main Results:

    • Successful development of the PAINULIM prototype.
    • Identification and nonmathematical presentation of key knowledge representation issues.
    • Preliminary evaluation with 76 patients indicated good clinical performance.

    Conclusions:

    • The PAINULIM system, utilizing multiply sectioned Bayesian networks, shows promise for diagnosing upper limb neuromuscular conditions.
    • Addressing knowledge representation challenges is vital for developing efficient and user-friendly diagnostic AI.
    • The system's preliminary clinical performance suggests its potential utility in medical diagnostics.