By using this site, you agree to the Privacy Policy and Terms of Use.
Accept
MedsparkMedsparkMedspark
  • Home
  • News & Alerts
    News & AlertsShow More
    Ion Based Memristors Create Hardware Neurons That Mirror Brain Function
    By
    msadmin
    July 6, 2026
    Deep learning pipeline pinpoints anatomical source of snoring from audio alone
    By
    msadmin
    July 5, 2026
    AI Model Generates Future Knee X-Rays to Predict Osteoarthritis Progression
    By
    msadmin
    July 1, 2026
    Baptist Health Deploys AI Platform to Close Gaps in Incidental Finding Follow-Up
    By
    msadmin
    June 30, 2026
    Google’s AMIE AI Advances from Diagnosis to Long-Term Disease Management in New Nature Study
    By
    msadmin
    June 30, 2026
  • Spotlight
    SpotlightShow More
    Strategic healthcare AI governance framework abstract illustration
    Building a Resilient Healthcare AI Strategy: Insights from Industry Leaders
    By
    msadmin
    May 15, 2026
    Pharma AI Alliance Expands: Owkin and AstraZeneca Deploy New Drug Discovery Models
    By
    msadmin
    May 14, 2026
    7 Must-Attend MedTech Events in South Africa for 2025
    By
    Jostel Owusu
    August 9, 2025
    EY Expert Urges Healthcare Leaders to Double Down on AI Amid Economic Uncertainty
    By
    Yu Chi Huang
    July 11, 2025
    Medow Health AI Launches Real-Time AI Scribe in Singapore to Boost Clinical Efficiency
    By
    Yu Chi Huang
    July 4, 2025
  • Articles
    ArticlesShow More
    AI in Surgical Research: How Large Language Models Are Accelerating Medical Discovery at the Medical College of Wisconsin
    By
    msadmin
    June 30, 2026
    Why Radiologists Reject Standalone AI: The Case for Seamless Workflow Integration
    By
    msadmin
    June 30, 2026
    Bridging the Gap: Translating AI Innovations into Neurological Practice
    By
    msadmin
    June 30, 2026
    Stress Tests Reveal Critical Gaps in AI Medical Reasoning Despite Top Benchmark Scores
    By
    msadmin
    June 30, 2026
    Designing Healthcare AI for Real World Clinical Flow
    By
    msadmin
    June 30, 2026
  • Events
    EventsShow More
    Stanford Health AI Week Highlights AI’s Growing Role in Medical Education, Patient Empowerment, and Life Sciences
    By
    msadmin
    June 19, 2026
    HIMSS APAC 2026: Re-engineering APAC Health Systems in the AI Era
    By
    msadmin
    June 9, 2026
    AIMed 2026: Bridging the Gap Between AI Promise and Clinical Reality in Kraków
    By
    msadmin
    April 30, 2026
    7 Must-Attend MedTech Events in South Africa for 2025
    By
    Jostel Owusu
    August 9, 2025
    Cleveland Clinic’s First AI Summit Signals Bold Future for Healthcare
    By
    msadmin
    July 19, 2025
  • About
    • Mission
    • Services
    • Contact
Font ResizerAa
MedsparkMedspark
Font ResizerAa
  • Home
  • News & Alerts
  • Spotlight
  • Articles
  • Events
  • About
  • Quick Links
    • Home
    • News & Alerts
    • Spotlight
    • Articles
    • Events
  • About MedSpark
    • Our Purpose & Vision
    • Services
    • Contact
Follow US
News & Alerts

Deep learning pipeline pinpoints anatomical source of snoring from audio alone

MSAdmin
By
msadmin
MSAdmin
Bymsadmin
MedTech AI & Cybersecurity News
Follow:
Published: July 5, 2026
Share
2 Min Read
SHARE

AI Driven Snore Source Localization

Researchers have developed a heterogeneous deep learning framework that can classify the anatomical origin of snoring by analyzing audio signals alone. Snoring is a hallmark of obstructive sleep apnea, where vibration or obstruction occurs in structures such as the soft palate, tongue base, epiglottis, or lateral oropharyngeal walls. Currently, identifying the specific site of obstruction often requires invasive procedures. The proposed model uses short-time Fourier transform (STFT) to convert snore sounds into spectrograms, preserving both time and frequency information. A pretrained convolutional neural network (VGG19 or AlexNet) then extracts high-level features, which are classified by a support vector machine (SVM) into four categories corresponding to different upper airway structures.

Contents
AI Driven Snore Source LocalizationPerformance and Clinical Implications

Performance and Clinical Implications

Tested on the Munich-Passau Snore Sound Corpus (MPSSC), the pipeline achieved an unweighted average recall of 67.1% on the test set, outperforming conventional methods such as MFCC+SVM, end to end CNNs, and advanced audio models like wav2vec 2.0 and audio spectrogram transformers. Ablation studies showed that removing any module (STFT, pretrained CNN, or SVM) reduced performance by 7.5 to 21.3 percentage points, confirming the complementary role of each component. While the results are promising, the model requires independent validation on external clinical datasets before it can be applied in routine sleep medicine. If confirmed, this AI approach could enable noninvasive, low cost triage of snoring patients and guide personalized treatments such as targeted surgery or continuous positive airway pressure therapy.

Source: News-Medical

TAGGED:audio classificationClinical AIcomputer visiondeep learningsleep apneasnoring
Share This Article
Facebook Copy Link Print
MSAdmin
Bymsadmin
Follow:
MedTech AI & Cybersecurity News
banner-medspark-horiz

You Might Also Like

News & Alerts

New AI model detects brain tumors with 99% accuracy—no scalpel needed

By
msadmin
June 23, 2025
News & Alerts

AMD’s £2 Billion UK Investment Pledges to Transform Healthcare AI and Scientific Discovery

By
msadmin
June 8, 2026
News & Alerts

Pennsylvania Targets AI Chatbots That Pose as Licensed Doctors

By
msadmin
May 5, 2026
News & Alerts

 UK Becomes First Pioneer in Global AI Health Regulation Network

By
Yu Chi Huang
June 25, 2025
Facebook Twitter Youtube Linkedin
Quick Links
  • News & Alerts
  • Articles
  • Spotlight
  • Events
About Medspark
  • Mission
  • Services
  • Contact

© Copyright 2026 MedSpark. All rights reserved.

Privacy Policy | Legal