Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

CXCR4 in colorectal cancer: from prognostic marker to immunotherapy guide?

BMJ oncology·2026

Same author

Web-Based Personalized Machine Learning Recommendations to Enhance Shared Decision-Making in Prostate-Specific Antigen Screening: Randomized Controlled Trial.

JMIR aging·2026

Same author

How vocal timbre impacts word identification and listening effort in traffic-shaped noises.

JASA express letters·2025

Same author

Ginkgolide B increases healthspan and lifespan of female mice.

Nature aging·2025

Same author

Cancer-Associated-Fibroblast-Mediated Paracrine and Autocrine SDF-1/CXCR4 Signaling Promotes Stemness and Aggressiveness of Colorectal Cancers.

Cells·2024

Same author

Artificial Intelligence-Assisted Diagnosis of Anterior Cruciate Ligament Tears From Magnetic Resonance Images: Algorithm Development and Validation Study.

JMIR AI·2024

Search research articles

Related Experiment Video

Updated: Nov 2, 2025

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

Deep Learning Application for Vocal Fold Disease Prediction Through Voice Recognition: Preliminary Development Study.

Hao-Chun Hu^1,2,3, Shyue-Yih Chang⁴, Chuen-Heng Wang⁵

¹Institute of Clinical Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan.

Journal of Medical Internet Research

|June 8, 2021

Summary

Artificial intelligence can now detect vocal fold diseases using voice analysis, improving accessibility in primary care. This AI approach shows promise for screening common voice disorders, aiding telemedicine and reducing the need for immediate invasive examinations.

Keywords:

artificial intelligence convolutional neural network dysphonia pathological voice vocal fold disease voice pathology identification

More Related Videos

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

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

Published on: September 19, 2025

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

Related Experiment Videos

Last Updated: Nov 2, 2025

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

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

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

Published on: September 19, 2025

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

Area of Science:

Otolaryngology
Artificial Intelligence
Machine Learning

Background:

Dysphonia significantly impacts quality of life by hindering communication.
Laryngoscopic examination, crucial for diagnosis, is costly and inaccessible in primary care.
Accurate diagnosis requires experienced laryngologists.

Purpose of the Study:

To develop an artificial intelligence (AI) model for detecting various vocal fold diseases via pathological voice recognition.
To assess the efficacy of AI in distinguishing between normal voices and different voice disorders.

Main Methods:

Collected 741 voice samples: 189 normal and 552 with disorders (vocal atrophy, unilateral vocal paralysis, organic vocal fold lesions, adductor spasmodic dysphonia).
Utilized a convolutional neural network (CNN) approach for model training on 593 samples and testing on 148 samples.
Compared CNN model performance against human specialists (laryngologists and ENT doctors).

Main Results:

The CNN model achieved 66.9% overall accuracy, with 66% sensitivity and 91% specificity.
AI model outperformed human specialists: overall accuracy was 66.9% for AI vs. 60.1%/56.1% for laryngologists and 51.4%/43.2% for ENT doctors.
AI demonstrated strong performance in distinguishing normal voices from various pathological conditions.

Conclusions:

Voice analysis using deep learning (AI) can effectively recognize common vocal fold diseases.
This AI-driven approach is clinically valuable for preliminary screening of voice disorders, especially in primary care and telemedicine settings.
AI can support physicians by identifying potential cases for further, more invasive examinations, optimizing healthcare resource allocation.