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

Classification of endocardial electrograms using adapted wavelet packets and neural networks.

D Strauss1, J Jung, A Rieder

  • 1Applied Mathematics and Computer Science, University of Mannheim, Germany. strauss@keynumerics.com

Annals of Biomedical Engineering
|July 19, 2001
PubMed
Summary

Distinguishing ventricular tachycardias from sinus tachycardia is difficult for implantable cardioverter defibrillators. This study introduces a novel wavelet-packet decomposition and neural network method for accurate atrial activation pattern classification.

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

Extreme storm events drive beach connectivity through headland bypassing.

The Science of the total environment·2025
Same author

Long-term complete remissions of refractory severe idiopathic immune thrombocytopenia treated with daratumumab: A case series.

British journal of haematology·2024
Same author

Sensory over-responsivity and atypical neural responses to socially relevant stimuli in autism.

Autism research : official journal of the International Society for Autism Research·2024
Same author

Photoproduction of K^{+}K^{-} Pairs in Ultraperipheral Collisions.

Physical review letters·2024
Same author

Emergence of Long-Range Angular Correlations in Low-Multiplicity Proton-Proton Collisions.

Physical review letters·2024
Same author

First Measurement of the |t| Dependence of Incoherent J/ψ Photonuclear Production.

Physical review letters·2024

Area of Science:

  • Biomedical Engineering
  • Cardiology
  • Signal Processing

Background:

  • Differentiating ventricular tachycardia (VT) with 1:1 retrograde conduction from sinus tachycardia (ST) poses a challenge for rate-based algorithms in dual-chamber implantable cardioverter defibrillators (ICDs).
  • Morphology-based analysis of atrial activation patterns offers a potential solution, but time-domain template matching of endocardial electrograms is suboptimal due to high dimensionality and irrelevant features.

Purpose of the Study:

  • To develop an enhanced morphological analysis tool for classifying antegrade and retrograde atrial activation patterns.
  • To improve the accuracy of tachycardia discrimination in cardiac implantable electronic devices.

Main Methods:

  • Utilized an adapted wavelet-packet decomposition to extract discriminating features from endocardial electrograms representing antegrade and retrograde atrial activation.

Related Experiment Videos

  • Employed a feed-forward neural network for classification based on the extracted wavelet-packet features.
  • Developed a hybrid approach combining transform-domain signal processing with machine learning.

    • Main Results:

    • The proposed hybrid method achieved accurate classification of antegrade and retrograde atrial activation patterns.
    • No false classifications were observed between physiological (sinus rhythm) and pathological (ventricular tachycardia) cardiac states.
    • The transform-domain representation significantly improved feature extraction compared to time-domain methods.

    Conclusions:

    • The developed classification scheme, utilizing wavelet-packet decomposition and neural networks, is highly efficient for distinguishing atrial activation patterns.
    • This approach offers a promising solution for enhancing the diagnostic capabilities of implantable cardioverter defibrillators in tachycardia detection.