A Study on Building a Voice Cohort for the Development of a Non-face-to-face Machine Learning Diagnostic and Monitoring Platform Using Voice Analysis and Various Sensors in Patients With Dysphagia.

Collection of basic data for real-time analysis and monitoring by measuring what changes in voice occur according to the state of dysphagia using voice analysis and various sensors.

Study Overview

• Status: Completed
• Conditions: Deglutition Disorders
• Intervention / Treatment: Diagnostic test: Voice recording and sensor-based data collection

Detailed Description

• Design : Prospective cohort study
• Setting : Hospital rehabilitation department
• Inclusion criteria of the patient group : Patients scheduled for VFSS examination

• Intervention

  • This study will be conducted after collecting basic information such as age, gender, and disease of patients who met the inclusion criteria among patients scheduled to undergo a video fluoroscopic swallowing test (VFSS test) for the diagnosis of dysphagia, and after obtaining guidance and consent through the study description will do.
  • Before the subject's VFSS test, "Ah for 5 seconds", after clearing the throat, "Ah for 5 seconds", and briefly cut with a slightly high sound, "Ah. oh Ah.", shut lips lightly and read "Ummm~~~~", read a short sentence.
  • While the subject makes the above sound, voice is recorded, video is taken, and integrated sensors such as a microphone (sound detection) sensor is attached to measure changes in each sensor.
  • After the VFSS test, participants will repeat the above sound and record the same twice. (As before the test, imaging of the patient's swallowing is also performed.)
  • Using voice analysis, various sensor values, and image information, a voice indicator that can predict the amount of suction and residue on the VFSS test is found.

• Study Type: Observational
• Enrollment (Actual): 259

Contacts and Locations

Study Locations

• South Korea
  • Gyeonggi-do
    • Seongnam-si, Gyeonggi-do, South Korea, 463-707
      • Department of Rehabilitation Medicine, Seoul National University Bundang Hospital, Seoul National University College of Medicine

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 19 years and older (Adult, Older Adult)
• Accepts Healthy Volunteers: Yes

• Sampling Method: Probability Sample

Study Population

Patients scheduled for VFSS examination due to dysphagia

Description

Inclusion Criteria:

• Those who are 19 years of age or older and do not fall under the exclusion criteria
• Patients scheduled for VFSS test
• Patients who can record voices such as "Ah.", "Ummm~~~", short sentences
• Patients who can attach sensor on their throat
• Those who voluntarily consent to the clinical trial

Exclusion Criteria:

• Those who do not agree to participate in this study
• Patients who can not follow Step 1 instructions
• Patients who can not vocalize or follow to speak
• Patients who cannot apply the sensor due to skin allergy or hypersensitivity to sensor attachment
• Other who have comorbidities (e.g., maligant tumors, blood clotting abnormalities, etc.) that are inappropriate for clinical trial participation by the judgment of the researcher 6) Other who are judged by the researcher to be unsuitable for this clinical trial.

Study Plan

How is the study designed?

Design Details

• Observational Models: Cohort
• Time Perspectives: Prospective

Number of groups / cohorts

3

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Normal Group; Healthy volunteers and VFSS patients with PAS 1. Voice recorded before and after swallowing.	Diagnostic test: Voice recording and sensor-based data collection; Pre- and post-swallowing voice recordings (sustained phonation "ah" for 5 seconds, short phonation, humming, and sentence reading) were collected using a microphone (AKG C 411L) attached to suprahyoid muscles. For VFSS patients, recordings were performed before and after VFSS examination. For healthy controls, recordings were performed before and after yogurt intake. No therapeutic intervention was performed.
Low-Risk Dysphagia Group (Penetration/Residue); VFSS patients with PAS 2-4. Voice recorded before and after VFSS examination.	Diagnostic test: Voice recording and sensor-based data collection; Pre- and post-swallowing voice recordings (sustained phonation "ah" for 5 seconds, short phonation, humming, and sentence reading) were collected using a microphone (AKG C 411L) attached to suprahyoid muscles. For VFSS patients, recordings were performed before and after VFSS examination. For healthy controls, recordings were performed before and after yogurt intake. No therapeutic intervention was performed.
High-Risk Dysphagia Group (Aspiration); VFSS patients with PAS 5-8. Voice recorded before and after VFSS examination.	Diagnostic test: Voice recording and sensor-based data collection; Pre- and post-swallowing voice recordings (sustained phonation "ah" for 5 seconds, short phonation, humming, and sentence reading) were collected using a microphone (AKG C 411L) attached to suprahyoid muscles. For VFSS patients, recordings were performed before and after VFSS examination. For healthy controls, recordings were performed before and after yogurt intake. No therapeutic intervention was performed.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Voice analysis before and after meals, the results are compared with VFSS to verify significant indicators (residue, aspiration, etc.) by Paired t-test analysis.	By comparing the VFSS swallow test result with the analysis value through voice analysis, the accuracy of the case classified as aspiration in the voice test is used as the primary indicator.	Baseline/ Change from baseline when swallowing

Collaborators and Investigators

• Sponsor: Seoul National University Hospital
• Investigators: Study Director: Juseok Ryu, M.D, PhD, Seoul National University Bundang Hospital

Study record dates

Study Major Dates

• Study Start (Actual): April 7, 2023
• Primary Completion (Actual): December 18, 2024
• Study Completion (Actual): December 18, 2024

Study Registration Dates

• First Submitted: June 16, 2022
• First Submitted That Met QC Criteria: June 26, 2022
• First Posted (Actual): June 30, 2022

Study Record Updates

• Last Update Posted (Actual): February 25, 2026
• Last Update Submitted That Met QC Criteria: February 23, 2026
• Last Verified: February 1, 2026

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Digestive System Diseases; Gastrointestinal Diseases; Esophageal Diseases; Otorhinolaryngologic Diseases; Pharyngeal Diseases; Deglutition Disorders
• Other Study ID Numbers: B-2206-761-302

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: Individual participant data contain voice recordings which are personally identifiable. Sharing is restricted under Korean Personal Information Protection Act and institutional policy.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No