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

Feature and classifier fusion for 12-lead ECG classification.

C D Nugent1, J A Webb, N D Black

  • 1The Northern Ireland BioEngineering Centre, Newtownabbey. cd.nugent@ulst.ac.uk

Medical Informatics and the Internet in Medicine
|November 22, 2000
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

Reactive oxygen species alter dopaminergic and purinergic signaling and microglia physiology in the nucleus accumbens.

bioRxiv : the preprint server for biology·2026
Same author

The effects of COVID-19 on hip fracture management and mortality in a regional trauma centre.

Anaesthesia·2020
Same author

Characterisation of spatial variability in water quality in the Great Barrier Reef catchments using multivariate statistical analysis.

Marine pollution bulletin·2018
Same author

Detection of workplace sedentary behavior using thermal sensors.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2017
Same author

Sensor-based activity recognition using extended belief rule-based inference methodology.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2015
Same author

The creation of simulated activity datasets using a graphical intelligent environment simulation tool.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2015

This study explores two methods for classifying 12-lead electrocardiograms (ECGs). Feature and classifier fusion techniques significantly improved diagnostic accuracy, offering a viable solution for ECG analysis.

Area of Science:

  • Biomedical Engineering
  • Artificial Intelligence in Medicine
  • Cardiology

Background:

  • Computerized classification of 12-lead electrocardiogram (ECG) recordings is crucial for diagnosing cardiac conditions.
  • Existing methods face challenges in effectively fusing information from multiple classifiers and features.

Purpose of the Study:

  • To investigate two novel methodologies for computerized 12-lead ECG classification: feature fusion and classifier fusion.
  • To address the issue of unresolved conflict during the fusion of classifiers.

Main Methods:

  • Subdividing the classification problem into smaller bi-dimensional problems using bi-group Neural Network classifiers.
  • Employing a novel Specificity Matrix approach to fuse a Neural Network classifier and a decision tree, resolving conflicts.

Related Experiment Videos

Main Results:

  • The bi-group classifier framework enhanced overall performance by 12.0% compared to conventional approaches.
  • The Specificity Matrix fusion method achieved an 81.3% performance level, outperforming individual classifiers.
  • Both methodologies demonstrated effectiveness in improving 12-lead ECG classification accuracy.

Conclusions:

  • Feature and classifier fusion techniques offer viable solutions for improving computerized 12-lead ECG classification.
  • The Specificity Matrix provides a robust method for classifier fusion, mitigating conflict issues.
  • These approaches are scalable and can be extended to more complex diagnostic scenarios.