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

ECG processing techniques based on neural networks and bidirectional associative memories

N Maglaveras1, T Stamkopoulos, C Pappas

  • 1Aristotelian University, Laboratory of Medical Informatics, Medical School, Thessaloniki, Macedonia, Greece.

Journal of Medical Engineering & Technology
|July 17, 1998
PubMed
Summary

This study presents two neural network (NN) techniques for electrocardiogram (ECG) analysis. These methods effectively classify heartbeats, including identifying premature ventricular contractions (PVCs) and detecting ischaemic beats.

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

Nonlinear optical vector processing using linear silicon photonic circuits for 50 Gb/s memory and string similarity functions.

Nature communications·2025
Same author

Time-space-wavelength multiplexed photonic tensor core using WDM SiGe EAM array chiplets.

Optics express·2025
Same author

Wearable pulmonary monitoring system with integrated functional lung imaging and chest sound recording: a clinical investigation in healthy subjects.

Physiological measurement·2023
Same author

Field-induced vortex-like textures as a probe of the critical line in reentrant spin glasses.

Scientific reports·2021
Same author

Identification and analysis of stable breathing periods in electrical impedance tomography recordings.

Physiological measurement·2021
Same author

Furnace for in situ and simultaneous studies of nano-precipitates and phase transformations in steels by SANS and neutron diffraction.

The Review of scientific instruments·2020

Area of Science:

  • Biomedical Engineering
  • Cardiology
  • Artificial Intelligence in Medicine

Background:

  • Accurate electrocardiogram (ECG) analysis is crucial for diagnosing cardiac conditions.
  • Distinguishing between normal, abnormal (like premature ventricular contractions - PVCs), and ischaemic heartbeats requires sophisticated processing.
  • Neural networks (NNs) offer potential for advanced ECG signal classification.

Purpose of the Study:

  • To introduce and evaluate two novel NN-based ECG processing techniques.
  • To assess the efficacy of these techniques in classifying various types of heartbeats, including QRS complexes, PVCs, and ischaemic beats.
  • To develop reliable algorithms for automated cardiac rhythm analysis.

Main Methods:

  • Nonlinear ECG mapping preprocessing followed by a shrinking algorithm based on NNs for QRS/PVC classification.

Related Experiment Videos

  • Utilizing Bidirectional Associative Memory (BAM) NN, treating ECG beats as digitized images transformed into bipolar vectors for normal vs. ischaemic beat discrimination.
  • Calibration of the BAM NN for optimized performance.

    • Main Results:

    • The first NN technique demonstrated good results in classifying QRS complexes and PVCs.
    • The BAM NN technique showed potential for fast and reliable ischaemic beat detection when properly calibrated.
    • Both techniques leverage NN technology for enhanced ECG interpretation.

    Conclusions:

    • NN-based approaches provide effective solutions for complex ECG beat classification.
    • The BAM NN method offers a promising avenue for rapid and accurate ischaemic beat detection.
    • Further calibration and validation can lead to robust clinical applications in cardiac monitoring.