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 Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Expanding Horizons: The Vanderbilt Plastic Surgery Annual Lecture Series.

Annals of plastic surgery·2026
Same author

Foreword.

Annals of plastic surgery·2026
Same author

Augmentation, Mastopexy, and Augmentation-Mastopexy: Navigating Surgical Decision-Making and Optimizing Outcomes.

Annals of plastic surgery·2026
Same author

Tracking Scholarly Productivity in Academic Plastic Surgery: A Departmental Scholarly Index Analysis.

Annals of plastic surgery·2026
Same author

Preventing GLP-1-Associated Facial Aging: An Anatomy-Driven Risk Stratification Model and Prevention Algorithm in the "Ozempic Face" Era.

Aesthetic plastic surgery·2026
Same author

Leonard T. Furlow-Reflections From the Archive-Innovation at the Intersection of Surgery and Imagination.

Annals of plastic surgery·2026

Related Experiment Video

Updated: Jun 27, 2025

Minimally Invasive Murine Laryngoscopy for Close-Up Imaging of Laryngeal Motion During Breathing and Swallowing
07:22

Minimally Invasive Murine Laryngoscopy for Close-Up Imaging of Laryngeal Motion During Breathing and Swallowing

Published on: December 1, 2023

482

Machine Learning for Automatic Detection of Velopharyngeal Dysfunction: A Preliminary Report.

Claiborne Lucas1, Ricardo Torres-Guzman2, Andrew J James2

  • 1Department of General Surgery, Prisma Health Greenville, Greenville, SC.

The Journal of Craniofacial Surgery
|May 6, 2024
PubMed
Summary

A new machine-learning model can detect velopharyngeal dysfunction (VPD) using only audio samples. This technology could significantly improve diagnostic access for individuals with VPD, especially in low-resource settings.

Keywords:
Artificial intelligencecleft palatemachine learningvelopharyngeal dysfunctionvelopharyngeal insufficiency

More Related Videos

Ultrasound Images of the Tongue: A Tutorial for Assessment and Remediation of Speech Sound Errors
08:32

Ultrasound Images of the Tongue: A Tutorial for Assessment and Remediation of Speech Sound Errors

Published on: January 3, 2017

21.8K
A Protocol for Comprehensive Assessment of Bulbar Dysfunction in Amyotrophic Lateral Sclerosis ALS
12:43

A Protocol for Comprehensive Assessment of Bulbar Dysfunction in Amyotrophic Lateral Sclerosis ALS

Published on: February 21, 2011

34.8K

Related Experiment Videos

Last Updated: Jun 27, 2025

Minimally Invasive Murine Laryngoscopy for Close-Up Imaging of Laryngeal Motion During Breathing and Swallowing
07:22

Minimally Invasive Murine Laryngoscopy for Close-Up Imaging of Laryngeal Motion During Breathing and Swallowing

Published on: December 1, 2023

482
Ultrasound Images of the Tongue: A Tutorial for Assessment and Remediation of Speech Sound Errors
08:32

Ultrasound Images of the Tongue: A Tutorial for Assessment and Remediation of Speech Sound Errors

Published on: January 3, 2017

21.8K
A Protocol for Comprehensive Assessment of Bulbar Dysfunction in Amyotrophic Lateral Sclerosis ALS
12:43

A Protocol for Comprehensive Assessment of Bulbar Dysfunction in Amyotrophic Lateral Sclerosis ALS

Published on: February 21, 2011

34.8K

Area of Science:

  • Speech-language pathology
  • Artificial intelligence in healthcare
  • Medical diagnostics

Background:

  • Velopharyngeal dysfunction (VPD) affects up to 30% of patients post-palatoplasty, with estimates primarily from high-income countries.
  • The prevalence and impact of VPD in low- and middle-income countries (LMICs) remain largely unknown.
  • Current diagnostic and therapeutic access for VPD is limited in LMICs due to resource constraints.

Purpose of the Study:

  • To develop and validate a machine-learning model for detecting VPD using audio samples.
  • To assess the model's performance in identifying VPD in a diverse patient population.

Main Methods:

  • Audio samples from patients with and without VPD were collected from various sources.
  • A machine-learning model was developed and trained using Python.
  • The model's precision, sensitivity, and specificity were evaluated using both training and prospective datasets.

Main Results:

  • The model achieved 100% precision in initial testing.
  • Sensitivity was 92.73% and specificity was 98.18% on the training set.
  • On a prospective dataset, the model maintained 100% precision with 88.89% sensitivity and 66% specificity.

Conclusions:

  • A phone-based, machine-learning screening tool for VPD shows promising accuracy.
  • This technology has the potential to significantly expand access to VPD diagnosis and treatment globally.
  • Addressing the unknown burden of VPD in LMICs is crucial for improving patient outcomes and reducing psychosocial morbidity.