An automatic measure for speech intelligibility in dysarthrias-validation across multiple languages and neurological disorders

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F24%3A00376338" target="_blank" >RIV/68407700:21230/24:00376338 - isvavai.cz</a>

Result on the web

<a href="https://doi.org/10.3389/fdgth.2024.1440986" target="_blank" >https://doi.org/10.3389/fdgth.2024.1440986</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3389/fdgth.2024.1440986" target="_blank" >10.3389/fdgth.2024.1440986</a>

Result language

angličtina

Original language name

An automatic measure for speech intelligibility in dysarthrias-validation across multiple languages and neurological disorders

Original language description

Introduction: Dysarthria, a motor speech disorder caused by muscle weakness or paralysis, severely impacts speech intelligibility and quality of life. The condition is prevalent in motor speech disorders such as Parkinson's disease (PD), atypical parkinsonism such as progressive supranuclear palsy (PSP), Huntington's disease (HD), and amyotrophic lateral sclerosis (ALS). Improving intelligibility is not only an outcome that matters to patients but can also play a critical role as an endpoint in clinical research and drug development. This study validates a digital measure for speech intelligibility, the ki: SB-M intelligibility score, across various motor speech disorders and languages following the Digital Medicine Society (DiMe) V3 framework. Methods: The study used four datasets: healthy controls (HCs) and patients with PD, HD, PSP, and ALS from Czech, Colombian, and German populations. Participants' speech intelligibility was assessed using the ki: SB-M intelligibility score, which is derived from automatic speech recognition (ASR) systems. Verification with inter-ASR reliability and temporal consistency, analytical validation with correlations to gold standard clinical dysarthria scores in each disease, and clinical validation with group comparisons between HCs and patients were performed. Results: Verification showed good to excellent inter-rater reliability between ASR systems and fair to good consistency. Analytical validation revealed significant correlations between the SB-M intelligibility score and established clinical measures for speech impairments across all patient groups and languages. Clinical validation demonstrated significant differences in intelligibility scores between pathological groups and healthy controls, indicating the measure's discriminative capability. Discussion: The ki: SB-M intelligibility score is a reliable, valid, and clinically relevant tool for assessing speech intelligibility in motor speech disorders. It holds promise for improving clinical trials through automated, objective, and scalable assessments. Future studies should explore its utility in monitoring disease progression and therapeutic efficacy as well as add data from further dysarthrias to the validation.

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

20601 - Medical engineering

Project

Result was created during the realization of more than one project. More information in the Projects tab.

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2024

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Frontiers in Digital Health

ISSN

2673-253X

e-ISSN

2673-253X

Volume of the periodical

6

Issue of the periodical within the volume

July

Country of publishing house

CH - SWITZERLAND

Number of pages

10

Pages from-to

—

UT code for WoS article

001286231000001

EID of the result in the Scopus database

2-s2.0-85200467831