Related Experiment Video
Updated: Aug 22, 2026
Asthma Detection Research Based on Voice Signal Processing and Machine Learning
Published on: July 22, 2025
Prediction of laryngeal aspiration using voice analysis
Ju Seok Ryu1, Seo Rin Park, Kyoung Hyo Choi
1Department of Physical Medicine and Rehabilitation, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea.
Objective:
To determine the diagnostic value of voice analysis to screen for patients with high risk of clinically significant aspiration.
Design:
A total of 93 patients referred for a videofluoroscopic swallowing study were included in the study. Voice analyses were performed before and after videofluoroscopic swallowing study, and five acoustic variables were measured, including average fundamental frequency, relative average perturbation, shimmer percentage, noise-to-harmonic ratio, and voice turbulence index. The patients were divided into two groups based on the results of the videofluoroscopic swallowing study: a high-risk group with patients who had the ingested materials on or below the vocal cords and a low-risk group with patients who did not have the ingested materials on or below the vocal cords. The changes of each acoustic variable before and after the videofluoroscopic swallowing study were compared between the two groups.
Results:
Relative average perturbation, shimmer percentage, noise-to-harmonic ratio, and voice turbulence index were significantly increased after videofluoroscopic swallowing study in the high-risk group as compared with the low-risk group (P < 0.05). The change of average fundamental frequency, however, was not significantly different between the two groups (P > 0.05). According to the receiver operating characteristics curve, the sensitivity of these acoustic variables in detecting aspiration or penetration ranged from 68.9% to 91.1% and specificity ranged from 68.8% to 97.9%. Relative average perturbation was the most accurate variable, with a sensitivity of 91.1% and a specificity of 97.9% in predicting aspiration or penetration. The combination of relative average perturbation and noise-to-harmonic ratio increased the sensitivity to 100% but reduced the specificity to 77.1%.
Conclusion:
Voice analysis is a safe, noninvasive, and reliable screening tool for patients with dysphagia and can detect patients at high risk of clinically significant aspiration, thereby augmenting clinical bedside examination.
Related Concept Videos
01:21Larynx
Anatomy of the Larynx
The larynx consists of various components, including cartilage, muscles, and vocal cords. Its structure includes three large unpaired cartilages—the thyroid, cricoid, and epiglottis—and three smaller paired cartilages—the arytenoids, corniculates, and...
01:28Physical Assessment of the Respiratory Tract IV: Auscultation
Breath Sounds
Breath sounds are categorized into vesicular, bronchovesicular, and bronchial.
01:31Respiratory System Abnormal Finding II: Palpation and Auscultation
Palpation Findings
During a respiratory assessment, palpation can reveal several vital abnormalities:
01:30Assessment of Airway, Skin Color, and Use of Accessory Muscles
Introduction
The initial evaluation of a patient's respiratory system...
01:30Cardiopulmonary Resuscitation V: Advanced Airway Management Techniques
01:23Assessment of Respiration
Subjective Assessment: Nurses interview the patient to gather information directly during the subjective assessment. It includes questions about the individual's medical history, medications, and symptoms, focusing on past respiratory conditions like asthma or COPD,...