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 Video

Updated: Mar 5, 2026

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections
06:22

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Published on: September 19, 2025

594

Application of semi-supervised deep learning to lung sound analysis.

Daniel Chamberlain, Rahul Kodgule, Daniela Ganelin

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
    |March 23, 2017
    PubMed
    Summary

    Automated lung sound classification for pulmonary disease diagnosis is challenging. This study introduces a semi-supervised deep learning algorithm that successfully classifies wheeze and crackle lung sounds using a large dataset and minimal labeling.

    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 systematic review of the prevalence of ADHD and autism among those experiencing gambling harm.

    Addictive behaviors·2026
    Same author

    Adapting and Validating Tools to Assess the Usability and Acceptability of mHealth Tools Among Community Health Workers in Rural Settings: Development and Usability Study.

    JMIR mHealth and uHealth·2026
    Same author

    Africa's Digital Health Revolution: The Digital Fit-Viability Model to Move From Innovation to Scaled Implementation.

    Journal of medical Internet research·2026
    Same author

    Community health workers' usability and acceptability of an mHealth tool for post-cesarean assessments: A mixed-methods study in rural Rwanda.

    BMC pregnancy and childbirth·2025
    Same author

    Bioequivalence and Safety of Bilastine 20 mg Administered in Three Eight-Hourly Dose Versus a Single Daily Dose: A Randomized Two-Treatment, Two-Period, Cross-Over Comparative Study.

    European journal of drug metabolism and pharmacokinetics·2025
    Same author

    New Advanced Placement course designed to broaden access promotes participation and demographic diversity in computer science education.

    Proceedings of the National Academy of Sciences of the United States of America·2025

    Area of Science:

    • Pulmonary Medicine
    • Artificial Intelligence
    • Medical Diagnostics

    Background:

    • Lung sound analysis via auscultation is crucial for diagnosing pulmonary diseases and telemedicine.
    • Automated lung sound classification has faced limitations due to small patient cohorts and extensive data labeling requirements.
    • Previous studies typically involved fewer than 20 patients and limited lung sound types.

    Purpose of the Study:

    • To develop a semi-supervised deep learning algorithm for automated classification of lung sounds.
    • To address the challenge of limited labeled data in lung sound analysis.
    • To improve the accuracy and scalability of pulmonary diagnostic tools.

    Main Methods:

    • Developed a semi-supervised deep learning algorithm for lung sound classification.

    More Related Videos

    Asthma Detection Research Based on Voice Signal Processing and Machine Learning
    04:04

    Asthma Detection Research Based on Voice Signal Processing and Machine Learning

    Published on: July 22, 2025

    1.1K

    Related Experiment Videos

    Last Updated: Mar 5, 2026

    Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections
    06:22

    Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

    Published on: September 19, 2025

    594
    Asthma Detection Research Based on Voice Signal Processing and Machine Learning
    04:04

    Asthma Detection Research Based on Voice Signal Processing and Machine Learning

    Published on: July 22, 2025

    1.1K
  • Utilized a dataset of 11,627 lung sound files from 284 patients with pulmonary disease.
  • Collected data using a mobile app and a low-cost electronic stethoscope.
  • Focused on classifying two common lung sounds: wheeze and crackle.

    • Main Results:

    • Achieved an Area Under the Curve (AUC) of 0.86 for wheeze classification.
    • Achieved an AUC of 0.74 for crackle classification.
    • Demonstrated the effectiveness of semi-supervised deep learning with a large dataset (890 labeled files).

    Conclusions:

    • Semi-supervised deep learning offers a viable solution for large-scale lung sound analysis.
    • The developed algorithm can classify common pulmonary lung sounds with significant accuracy.
    • This approach reduces the need for extensive manual data labeling, making automated diagnostics more feasible.