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

A PC based neural network algorithm for measurement of heart rate variability

T T Foo1, S S Hull, J Y Cheung

  • 1School of Electrical Engineering, University of Oklahoma, Norman 73019, USA.

Biomedical Sciences Instrumentation
|January 1, 1995
PubMed
Summary

Heart Rate Variability (HRV) can predict sudden cardiac death. This study uses a neural network to accurately classify QRS complexes, achieving a 99% detection rate for improved cardiac risk assessment.

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

Response to "clarification of enrolled subjects in tolvaptan HF trials".

Clinical pharmacology and therapeutics·2014
Same author

Vasopressin antagonists for patients with acute heart failure: interpreting new clinical and translational data.

Clinical pharmacology and therapeutics·2013
Same author

The Hong-Ou-Mandel interferometer: a new procedure for alignment.

The Review of scientific instruments·2009
Same author

Graeco-Latin squares design for line detection in the presence of correlated noise.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008
Same author

Stress induced in heart and other tissues by rat dermal exposure to JP-8 fuel.

Cell biology and toxicology·2005
Same author

Overexpression of Na+/Ca2+ exchanger alters contractility and SR Ca2+ content in adult rat myocytes.

American journal of physiology. Heart and circulatory physiology·2001

Area of Science:

  • Cardiology
  • Biomedical Engineering
  • Artificial Intelligence in Medicine

Background:

  • Heart Rate Variability (HRV) is an emerging biomarker for predicting sudden cardiac death.
  • Accurate analysis of electrocardiogram (ECG) signals, specifically QRS complexes, is crucial for cardiac health assessment.

Purpose of the Study:

  • To evaluate the efficacy of a neural network technique for classifying QRS complexes.
  • To determine if QRS complex classification can aid in predicting cardiac events.

Main Methods:

  • Utilized a single-layer perceptron neural network for QRS pattern learning and classification.
  • Applied the algorithm to real-world cardiac data for validation.

Main Results:

Related Experiment Videos

  • Achieved a 99% correct QRS detection rate using the neural network algorithm.
  • Demonstrated the potential of the neural network for accurate QRS complex analysis.

    • Conclusions:

    • Neural network classification of QRS complexes is a highly accurate method.
    • This technique shows promise for enhancing the prediction of sudden cardiac death using HRV.