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

Ranking of pattern recognition parameters for premature ventricular contractions classification by neural networks.

I Christov1, G Bortolan

  • 1Centre of Biomedical Engineering, Bulgarian Academy of Sciences, Sofia, Bulgaria. Ivaylo.Christov@clbme.bas.bg

Physiological Measurement
|November 13, 2004
PubMed
Summary

This study introduces a quantitative analysis using 26 parameters and neural networks to classify normal heartbeats and premature ventricular contractions (PVCs) from ECG data. The method achieved high accuracy, improving detection with two ECG leads.

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

DOES THE PATTERN OF CLONAL EVOLUTION IN THE KARYOTYPE OF PATIENTS WITH ACUTE MYELOID LEUKEMIA AND MYELODYSPLASTIC SYNDROMES DEPEND ON THE TYPE OF THE PRIMARY CHROMOSOMAL ABERRATIONS?

TSitologiia i genetika·2015
Same author

IS THE AMPLIFICATION OF c-MYC, MLL AND RUNX1 GENES IN AML AND MDS PATIENTS WITH TRISOMY 8, 11 AND 21 A FACTOR FOR A CLONAL EVOLUTION IN THEIR KARYOTYPE?

TSitologiia i genetika·2015
Same author

Extraction of the fetal ECG in noninvasive recordings by signal decompositions.

Physiological measurement·2014
Same author

Amplification of c-MYC and MLL Genes as a Marker of Clonal Cell Progression in Patients with Myeloid Malignancy and Trisomy of Chromosomes 8 or 11.

Balkan journal of medical genetics : BJMG·2013
Same author

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

Physiological measurement·2012
Same author

Quasi-phase matching of high-harmonics and attosecond pulses in modulated waveguides.

Optics express·2009

Area of Science:

  • Biomedical Engineering
  • Cardiology
  • Artificial Intelligence in Medicine

Background:

  • Accurate detection and classification of ventricular complexes are crucial for patient monitoring in critical care settings.
  • Beat-to-beat analysis enables tracking heart rhythm evolution and identifying arrhythmias like premature ventricular contractions (PVCs).
  • Existing methods may benefit from advanced quantitative analysis for improved accuracy.

Purpose of the Study:

  • To propose a quantitative analysis of pattern recognition parameters for classifying normal QRS complexes and PVCs.
  • To evaluate the effectiveness of neural networks in analyzing a large set of ECG parameters.
  • To compare the accuracy of single-lead versus dual-lead ECG analysis for arrhythmia detection.

Main Methods:

Related Experiment Videos

  • Defined 26 quantitative parameters including QRS width, vectorcardiogram features, and ECG lead measurements (amplitudes, areas, intervals, slopes, vector angles).
  • Utilized the MIT-BIH arrhythmia database, analyzing QRS complexes annotated as 'normals' and 'PVCs'.
  • Employed neural networks for parameter analysis and performed separate and group rankings of parameters.

    • Main Results:

    • Neural networks proved effective for analyzing extensive parameter sets.
    • Parameter groups for PVC clustering were ranked as amplitude, slope, and interval; for normal beats, they were vector, amplitude, and area.
    • Achieved 99.7% accuracy for normal QRS detection and 98.5% for PVC detection using the full parameter set.
    • Simultaneous analysis of two ECG leads improved PVC classification accuracy by 4.5% compared to a single lead.

    Conclusions:

    • The proposed quantitative analysis and neural network approach effectively classifies normal QRS complexes and PVCs.
    • Dual-lead ECG analysis offers superior accuracy for PVC detection compared to single-lead analysis.
    • This method holds significant potential for enhancing patient monitoring in critical care environments.