Artificial Intelligence in Diagnosing Dysphagia Patients

Completed

• Conditions: Stroke; Respiration Disorders; Aspiration; Liquids; Swallowing Disorder; Phonation Disorder; Aspiration Pneumonia
• Interventions: Other: Acoustic features (from signals obtained during phonation)

• Registration Number: NCT05098808
• Lead Sponsor: The Catholic University of Korea

Brief Summary

In this prospective study we extracted acoustic parameters using PRAAT from patient's attempt to phonate during the clinical evaluation using a digital smart device. From these parameters we attempted (1) to define which of the PRAAT acoustic features best help to discriminate patients with dysphagia (2) to develop algorithms using sophisticated ML techniques that best classify those i) with dysphagia and those ii ) at high risk of respiratory complications due to poor cough force.

Detailed Description

This study was prospective study, and patients who visited the department of rehabilitation medicine in a single university-affiliated tertiary hospital with dysphagic symptoms from September 2019 to March 2021 were included.Voice recording was performed at the enrollment with blinded assessment, where the participants first visited the rehabilitation department with chief complaints of dysphagia. The cough sounds were recorded with an iPad (Apple, Cupertino, CA, USA) through an embedded microphone.

From the acoustic files we extracted fourteen voice parameters that include the average value and standard deviation of the fundamental frequency (f0), harmonic-to-noise ratio (HNR), the jitter that refers to frequency instability, and the shimmer that represents the amplitude instability of the sound signal.

Machine learning algorithms and sophisticated deep neural network analysis will be performed.

Study Timeline

• Study Start: 2019-09-01
• Primary Completion: 2021-09-01
• Status Verified: 2021-10
• Study Completion: 2021-10-01
• Study First Submitted: 2021-10-01
• Study First Submitted QC: 2021-10-18
• Last Update Submitted: 2021-10-18
• Study First Posted: 2021-10-28
• Last Update Posted: 2021-10-28

Recruitment & Eligibility

• Status: COMPLETED
• Sex: All
• Target Recruitment: 449

Inclusion Criteria

• Inclusion criteria

1. Suspected swallowing disorder who were referred for swallowing assessment
2. Dysphagia attributable to brain lesion including stroke

Exclusion Criteria

1. Participants who were unable to perform phonation
2. Participants who had no VFSS or standardized swallowing assessment results
3. Participants with no spirometric measurements

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Arm && Interventions

Group	Intervention	Description
Dysphagia severe	Acoustic features (from signals obtained during phonation)	Non oral feeding and high risk of aspiration
Dysphagia mild	Acoustic features (from signals obtained during phonation)	Able to start oral feeding after assessment

Primary Outcome Measures

Name	Time	Method
Functional Oral Intake Scale	during the intervention	Dysphagia severity as measured by the the Functional Oral Intake Scale obtained from standardized swallowing tests
Cough strength	during the intervention	Spirometry values : cough strength as measured by the spirometric values during voluntary cough

Trial Locations

Locations (1)

Department of Rehabilitation Medicine Bucheon St Mary's Hospital, Catholic University of Korea, College of Medicine; 🇰🇷 Bucheon, Kyounggido, Korea, Republic of