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

Personal computer system for ECG ST-segment recognition based on neural networks.

Y Suzuki1, K Ono

  • 1Department of Computer Science and Systems Engineering, Muroran Institute of Technology, Japan.

Medical & Biological Engineering & Computing
|January 1, 1992
PubMed
Summary

This study introduces a novel personal computer system for electrocardiogram (ECG) ST-segment recognition using adaptive resonance theory (ART) neural networks. The system accurately identifies ST-segment features, offering robust and patient-specific ECG analysis.

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

Histochemical study of the lumbar colonic nerve supply to the internal anal sphincter and its physiological role in dogs.

Brain research·1992
Same author

[Analysis of pedestrian injuries in traffic accidents: impact point, injury portion, and injury severity].

Nihon hoigaku zasshi = The Japanese journal of legal medicine·1992
Same author

Immunolocalization of alkaline phosphatase in osteoblasts and matrix vesicles of human fetal bone.

Bone and mineral·1992
Same author

Changes of splenic lymphocyte subpopulation in mice inoculated with Babesia microti and Babesia rodhaini.

The Journal of veterinary medical science·1992
Same author

Magnocellular neurosecretory neurons with ferritin-like immunoreactivity in the hypothalamic supraoptic and paraventricular nuclei of the rat.

Brain research·1992
Same author

Gradient expression of neural cell adhesion molecule (NCAM) in the pontine migratory stream of fetal rats.

Neuroscience research·1992

Area of Science:

  • Biomedical Engineering
  • Computational Neuroscience
  • Medical Informatics

Background:

  • Accurate electrocardiogram (ECG) ST-segment analysis is crucial for diagnosing cardiac conditions.
  • Traditional methods for ST-segment recognition can be sensitive to noise and patient variability.
  • Automated systems are needed to improve the efficiency and accuracy of ECG interpretation.

Purpose of the Study:

  • To develop and evaluate a personal computer system for automated ECG ST-segment recognition.
  • To leverage adaptive resonance theory (ART) neural networks for robust and self-organizing ECG pattern analysis.
  • To accurately identify the J point and T-wave onset (T(on)) for precise ST-segment delineation.

Main Methods:

  • A system comprising a preprocessor, ART neural networks, and a recognizer was developed.

Related Experiment Videos

  • The preprocessor identifies R points and segments ECG into cardiac cycles.
  • ART neural networks self-organize to detect approximate J and T(on) points, with a recognizer refining their exact locations.

    • Main Results:

    • The developed system successfully recognizes the ST-segment by identifying the J and T(on) points.
    • The use of ART neural networks provides robustness against noise through competitive and co-operative neuronal interactions.
    • The system self-organizes and learns patient-specific ECG characteristics over time.

    Conclusions:

    • The developed personal computer system offers an effective approach for automated ECG ST-segment recognition.
    • ART neural networks demonstrate significant potential for creating noise-robust and adaptive ECG analysis tools.
    • This system facilitates accurate ST-segment analysis, adaptable to individual patient ECG patterns.