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 method for sleep apnea classification using wavelets and feedforward neural networks.

Oscar Fontenla-Romero1, Bertha Guijarro-Berdiñas, Amparo Alonso-Betanzos

  • 1Department of Computer Science, Faculty of Informatics, University of A Coruña, Campus de Elviña s/n, 15071 A Coruña, Spain. oscarfon@udc.es

Artificial Intelligence in Medicine
|May 12, 2005
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

Shallow Learning Techniques for Early Detection and Classification of Cyberattacks over MQTT IoT Networks.

Sensors (Basel, Switzerland)·2026
Same author

Beyond RMSE and MAE: Introducing EAUC to Unmask Hidden Bias and Unfairness in Dyadic Regression Models.

IEEE transactions on neural networks and learning systems·2025
Same author

"Play by play": A dataset of handball and basketball game situations in a standardized space.

Data in brief·2025
Same author

Positive-Unlabelled learning for identifying new candidate Dietary Restriction-related genes among ageing-related genes.

Computers in biology and medicine·2024
Same author

E2E-FS: An End-to-End Feature Selection Method for Neural Networks.

IEEE transactions on pattern analysis and machine intelligence·2023
Same author

Low-precision feature selection on microarray data: an information theoretic approach.

Medical & biological engineering & computing·2022

This study introduces a new method for classifying sleep apnea types (obstructive, central, mixed) using neural networks. The developed classifier achieved 83.78% accuracy, outperforming previous methods.

Area of Science:

  • Biomedical Engineering
  • Machine Learning in Healthcare
  • Sleep Medicine Research

Background:

  • Sleep apnea is a common disorder with multiple subtypes.
  • Accurate classification of sleep apnea types is crucial for effective treatment.
  • Current classification methods may have limitations in accuracy and efficiency.

Purpose of the Study:

  • To develop and evaluate a novel approach for classifying obstructive, central, and mixed sleep apnea.
  • To utilize discrete wavelet transformation and neural networks for sleep apnea classification.
  • To compare the performance of different supervised learning methods for this task.

Main Methods:

  • Employed three supervised learning methods based on neural networks.
  • Utilized level-5-detail coefficients from discrete wavelet transformation of thoracic effort signals as input.

Related Experiment Videos

  • Trained and tested models using 120 events from six patients, with 10-fold cross-validation and 100 simulations.

    • Main Results:

    • A feedforward neural network trained with a Bayesian framework and cross-entropy error function was selected.
    • The final model achieved a mean classification accuracy of 83.78% ± 1.90% on the test set.
    • The performance was validated through extensive simulations and statistical comparison.

    Conclusions:

    • The proposed sleep apnea classification system demonstrates superior performance compared to existing methods.
    • The novel approach offers a promising tool for objective sleep apnea diagnosis.
    • A framework for ongoing system maintenance and improvement in clinical settings is suggested.