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

Classifying coronary dysfunction using neural networks through cardiovascular auscultation.

R Folland1, E L Hines, P Boilot

  • 1Electrical and Electronic Engineering Division, School of Engineering, University of Warwick, Coventry, UK. r.s.folland@warwick.ac.uk

Medical & Biological Engineering & Computing
|August 28, 2002
PubMed
Summary

Artificial neural networks (ANNs) effectively classify heart sound abnormalities using auscultation data. Radial basis function networks achieved 88% accuracy, showing promise for improved diagnostics.

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

Role of molecular driver mutations in recurrence of early-stage laryngeal cancer following narrow field definitive radiotherapy.

Oral oncology reports·2026
Same author

Accelerating domain-aware electron microscopy analysis using deep learning models with synthetic data and image-wide confidence scoring.

npj computational materials·2025
Same author

Therapeutic Treatment With OLX-07010 Inhibited Tau Aggregation and Ameliorated Motor Deficits in an Aged Mouse Model of Tauopathy.

Journal of neurochemistry·2025
Same author

Great ape surveys and the implications of long-term monitoring in the Djéké Triangle, Republic of Congo.

Primates; journal of primatology·2024
Same author

Understanding Global Access to Topical Onychomycosis Therapy: A Systematic Review and Meta-Analysis.

Mycoses·2024
Same author

Immune biomarker evaluation of sequential tyrosine kinase inhibitor and nivolumab monotherapies in renal cell carcinoma: the phase I TRIBE trial.

Immuno-oncology technology·2024

Area of Science:

  • Cardiology
  • Biomedical Engineering
  • Artificial Intelligence

Background:

  • Heart sound auscultation is a fundamental diagnostic tool.
  • Distinguishing between various heart sound abnormalities can be challenging.
  • Automated analysis of auscultation data can enhance diagnostic accuracy and efficiency.

Purpose of the Study:

  • To apply artificial neural networks (ANNs) for the classification of heart sound abnormalities.
  • To develop and compare the performance of Multi-layer Perceptron (MLP) and Radial Basis Function (RBF) neural networks for this task.
  • To explore the potential for a combined cardio-respiratory analysis system.

Main Methods:

  • Collection of audio auscultation samples from 16 different coronary abnormalities.

Related Experiment Videos

  • Data pre-processing including down-sampling, Fast Fourier Transform (FFT), and Levinson-Durbin autoregression for feature extraction.
  • Training of MLP and RBF neural networks using the processed auscultation data.

    • Main Results:

    • The MLP neural network achieved a classification accuracy of 84%.
    • The RBF neural network achieved a higher classification accuracy of 88%.
    • Both networks demonstrated capability in distinguishing between different heart sound abnormalities.

    Conclusions:

    • ANNs, particularly RBF networks, show significant potential for accurate automated analysis of heart sound abnormalities.
    • This approach could lead to faster and more efficient diagnostic processes.
    • Future work could integrate respiratory auscultation analysis for a comprehensive cardio-respiratory diagnostic system.