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

Diagnostic ECG classification based on neural networks

G Bortolan1, J L Willems

  • 1Ladseb-CNR, Padova, Italy.

Journal of Electrocardiology
|January 1, 1993
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

Preface.

Yearbook of medical informatics·2016
Same author

T-wave alternans detection by a combined method of principal component analysis and T-wave amplitude.

Physiological measurement·2012
Same author

Probabilistic approach to polychlorinated biphenyl (PCB) exposure through eel consumption in recreational fishermen vs. the general population.

Food additives and contaminants·2007
Same author

Simulated impact of a fish based shift in the population n--3 fatty acids intake on exposure to dioxins and dioxin-like compounds.

Food and chemical toxicology : an international journal published for the British Industrial Biological Research Association·2007
Same author

Assessment and comparison of different methods for heartbeat classification.

Medical engineering & physics·2007
Same author

Premature ventricular contraction classification by the Kth nearest-neighbours rule.

Physiological measurement·2005
Same journal

The need to measure electrical synchrony - Assessment of electrical synchrony and its utility. Synchromax in real life.

Journal of electrocardiology·2026
Same journal

An assessment of intern doctors' experiences of undergraduate education in electrocardiogram interpretation.

Journal of electrocardiology·2026
Same journal

Feasibility and efficacy of left bundle branch area pacing guided by modified chest lead 1.

Journal of electrocardiology·2026
Same journal

Spatial proximity or vector orientation? Re-evaluating ECG interpretation in anterior myocardial infarction using cardiac magnetic resonance.

Journal of electrocardiology·2026
Same journal

Pacing spikes without visible QRS complexes: Failure to capture?

Journal of electrocardiology·2026
Same journal

Rethinking prediction of sudden cardiac arrest: The role of electrocardiography in forecasting low-incidence, high-consequence events.

Journal of electrocardiology·2026
See all related articles

This study demonstrates how neural networks can effectively classify resting 12-lead electrocardiograms for diagnosing heart conditions like hypertrophy and myocardial infarction. The connectionist approach shows strong performance compared to traditional statistical methods.

Area of Science:

  • Cardiology
  • Artificial Intelligence
  • Medical Diagnostics

Background:

  • Resting 12-lead electrocardiograms (ECG) are crucial for diagnosing cardiac conditions.
  • Accurate ECG interpretation is vital for patient management and treatment.
  • Traditional diagnostic methods can be limited in complex cases.

Purpose of the Study:

  • To evaluate the efficacy of a neural network approach for diagnostic classification of resting 12-lead ECGs.
  • To compare the performance of neural networks against classical statistical methodologies.
  • To explore variations in neural network architectures and training strategies.

Main Methods:

  • Utilized the CORDA database comprising 3,253 ECG signals with single diseases.
  • Employed a feed-forward neural network with the backpropagation algorithm for training.

Related Experiment Videos

  • Compared neural network performance against linear discriminant analysis and logistic discriminant analysis.

    • Main Results:

    • Neural networks demonstrated strong potential and good performance in classifying ECGs.
    • The connectionist approach achieved competitive accuracy compared to statistical models.
    • Optimized network architectures and training strategies further enhanced diagnostic capabilities.

    Conclusions:

    • Neural networks offer a promising and effective tool for automated ECG diagnostic classification.
    • This approach can complement or potentially surpass traditional diagnostic methods.
    • Further research into advanced neural network models could improve diagnostic accuracy in cardiology.