Artificial Intelligence in Diagnosing Dysphagia Patients

The Catholic University of Korea

Status: Completed

Conditions: Respiration Disorders; Stroke; Aspiration; Liquids; Swallowing Disorder; Aspiration Pneumonia; Phonation Disorder

Treatments: Other: Acoustic features (from signals obtained during phonation)

Study type: Observational

Funder types: Other

Identifiers

NCT05098808

HC19EESE0060

Details and patient eligibility

About

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.

Full 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.

Enrollment: 449 patients

Sex: All

Ages: 19 to 90 years old

Volunteers: No Healthy Volunteers

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

Trial design

449 participants in 2 patient groups

Dysphagia mild

Description:

Able to start oral feeding after assessment

Treatment:

Other: Acoustic features (from signals obtained during phonation)

Dysphagia severe

Description:

Non oral feeding and high risk of aspiration

Treatment:

Other: Acoustic features (from signals obtained during phonation)