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 new ECG classifier based on linear prediction techniques.

J P Marques de Sá, C Abreu-Lima

    Computers and Biomedical Research, an International Journal
    |June 1, 1986
    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

    A novel dry active electrode for EEG recording.

    IEEE transactions on bio-medical engineering·2007
    Same author

    Hemodynamic, autonomic and neurohormonal behaviour of familial amyloidotic polyneuropathy and neurally mediated syncope patients during supine and orthostatic stress.

    International journal of cardiology·2006
    Same author

    Population based study on the prevalence of the stages of heart failure.

    Heart (British Cardiac Society)·2006
    Same author

    Determinants of in-hospital mortality in women with acute myocardial infarction who underwent primary coronary angioplasty.

    Revista portuguesa de cardiologia : orgao oficial da Sociedade Portuguesa de Cardiologia = Portuguese journal of cardiology : an official journal of the Portuguese Society of Cardiology·2001
    Same author

    Automatic classifiers for the interpretation of electrocardiograms.

    Revista portuguesa de cardiologia : orgao oficial da Sociedade Portuguesa de Cardiologia = Portuguese journal of cardiology : an official journal of the Portuguese Society of Cardiology·1998
    Same author

    The diagnostic performance of computer programs for the interpretation of electrocardiograms.

    The New England journal of medicine·1991
    Same journal

    Wavelet domain nonlinear filtering for evoked potential signal enhancement.

    Computers and biomedical research, an international journal·2001
    Same journal

    Time-frequency analysis of the RT and RR variability to stratify hypertrophic cardiomyopathy patients.

    Computers and biomedical research, an international journal·2001
    Same journal

    Controlled auxotonic twitch in papillary muscle: a new computer-based control approach.

    Computers and biomedical research, an international journal·2001
    Same journal

    Controlling for chance agreement in the validation of medical expert systems with no gold standard: PNEUMON-IA and RENOIR revisited.

    Computers and biomedical research, an international journal·2001
    Same journal

    Artificial neural networks compared to factor analysis for low-dimensional classification of high-dimensional body fat topography data of healthy and diabetic subjects.

    Computers and biomedical research, an international journal·2000
    Same journal

    On the parallelization of linkmap from the LINKAGE/FASTLINK package.

    Computers and biomedical research, an international journal·2000
    See all related articles

    This study introduces linear prediction coefficients for statistical electrocardiogram (ECG) classification, offering a noise-insensitive alternative to conventional ECG features. This novel method significantly reduces classification errors in diagnosing conditions like myocardial infarction and hypertrophies.

    Area of Science:

    • Biomedical Engineering
    • Signal Processing
    • Medical Informatics

    Background:

    • Traditional automatic electrocardiogram (ECG) classification relies on conventional waveform features like amplitude and duration.
    • These conventional features can be sensitive to high-frequency noise, potentially impacting classification accuracy.
    • A need exists for more robust and noise-insensitive ECG feature extraction methods.

    Purpose of the Study:

    • To present and evaluate an alternative statistical ECG classification approach using linear prediction coefficients (LPCs).
    • To assess the effectiveness of LPCs as "abstract" features that capture whole-signal dependency and exhibit noise insensitivity.
    • To compare the classification performance of LPCs against conventional features in a clinical dataset.

    Main Methods:

    Related Experiment Videos

    • Employed linear prediction coefficients as "abstract" features for statistical ECG classification.
    • Utilized a dataset of 400 ECGs categorized into four clinical groups: normal, myocardial infarction, right hypertrophy, and left hypertrophy.
    • Evaluated classification error rates and cluster separability for the proposed LPC method and conventional features.

    Main Results:

    • The linear prediction coefficient method demonstrated a significantly lower classification error rate compared to conventional features when applied to the 400 ECGs.
    • Results showed promising classification and cluster separability, indicating the potential of LPCs.
    • The method proved to be relatively insensitive to high-frequency noise, a common issue with conventional ECG analysis.

    Conclusions:

    • Linear prediction coefficients offer a viable and potentially superior alternative for statistical ECG classification.
    • The LPC-based method shows significant promise for clinical environments due to its robustness and improved accuracy.
    • This approach advances automatic ECG analysis by providing a more reliable feature set for pattern discrimination.