Exploring digital speech biomarkers of hypokinetic dysarthria
in a multilingual cohort

J 2024

Exploring digital speech biomarkers of hypokinetic dysarthria in a multilingual cohort

KOVÁČ, Daniel, Jiří MEKYSKA, Vered AHARONSON, Pavol HARAR, Zoltan GALAZ et. al.

Basic information

Original name

Exploring digital speech biomarkers of hypokinetic dysarthria in a multilingual cohort

Authors

KOVÁČ, Daniel (203 Czech Republic), Jiří MEKYSKA (203 Czech Republic), Vered AHARONSON, Pavol HARAR, Zoltan GALAZ, Steven RAPCSAK, Juan Rafael OROZCO-ARROYAVE, Luboš BRABENEC (203 Czech Republic, belonging to the institution) and Irena REKTOROVÁ (203 Czech Republic, guarantor, belonging to the institution)

Edition

Biomedical Signal Processing and Control, OXFORD, ELSEVIER SCI LTD, 2024, 1746-8094

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

30401 Health-related biotechnology

Country of publisher

United Kingdom of Great Britain and Northern Ireland

Confidentiality degree

není předmětem státního či obchodního tajemství

References:

URL

Impact factor

Impact factor: 5.100 in 2022

Organization unit

Central European Institute of Technology

DOI

http://dx.doi.org/10.1016/j.bspc.2023.105667

UT WoS

001108281100001

Keywords in English

Hypokinetic dysarthria; Parkinson's disease; Multilingual study; Acoustic speech features; Statistical analysis; Machine learning

Abstract

V originále

Hypokinetic dysarthria, a motor speech disorder characterized by reduced movement and control in the speech -related muscles, is mostly associated with Parkinson's disease. Acoustic speech features thus offer the potential for early digital biomarkers to diagnose and monitor the progression of this disease. However, the influence of language on the successful classification of healthy and dysarthric speech remains crucial. This paper explores the analysis of acoustic speech features, both established and newly proposed, in a multilingual context to support the diagnosis of PD. The study aims to identify language-independent and highly discriminative digital speech biomarkers using statistical analysis and machine learning techniques. The study analyzes thirty-three acoustic features extracted from Czech, American, Israeli, Columbian, and Italian PD patients, as well as healthy controls. The analysis employs correlation and statistical tests, descriptive statistics, and the XGBoost classifier. Feature importances and Shapley values are used to provide explanations for the classification results. The study reveals that the most discriminative features, with reduced language dependence, are those measuring the prominence of the second formant, monopitch, and the frequency of pauses during text reading. Classification accuracies range from 67% to 85%, depending on the language. This paper introduces the concept of language robustness as a desirable quality in digital speech biomarkers, ensuring consistent behaviour across languages. By leveraging this concept and employing additional metrics, the study proposes several language-independent digital speech biomarkers with high discrimination power for diagnosing PD.

Links

LX22NPO5107, research and development project

Name: Národní ústav pro neurologický výzkum

Investor: Ministry of Education, Youth and Sports of the CR, 5.1 EXCELES

NU20-04-00294, research and development project

Name: Diagnostika onemocnění s Lewyho tělísky v prodromálním stadiu založená na analýze multimodálních dat

Investor: Ministry of Health of the CR, Diagnostics of Lewy body diseases in prodromal stage based on multimodal data analysis

734718, interní kód MU

Name: Novel Network-Based Approaches for Studying Cognitive Dysfunction in Behavioral Neurology (Acronym: CoBeN)

Investor: European Union, MSCA Marie Skłodowska-Curie Actions (Excellent Science)

Citovat

KOVÁČ, Daniel, Jiří MEKYSKA, Vered AHARONSON, Pavol HARAR, Zoltan GALAZ, Steven RAPCSAK, Juan Rafael OROZCO-ARROYAVE, Luboš BRABENEC and Irena REKTOROVÁ. Exploring digital speech biomarkers of hypokinetic dysarthria in a multilingual cohort. Biomedical Signal Processing and Control. OXFORD: ELSEVIER SCI LTD, 2024, vol. 88, B, p. 1-11. ISSN 1746-8094. Available from: https://dx.doi.org/10.1016/j.bspc.2023.105667.

@article{2371788,
   author = {Kováč, Daniel and Mekyska, Jiří and Aharonson, Vered and Harar, Pavol and Galaz, Zoltan and Rapcsak, Steven and OrozcoandArroyave, Juan Rafael and Brabenec, Luboš and Rektorová, Irena},
   article_location = {OXFORD},
   article_number = {B},
   doi = {http://dx.doi.org/10.1016/j.bspc.2023.105667},
   keywords = {Hypokinetic dysarthria; Parkinson's disease; Multilingual study; Acoustic speech features; Statistical analysis; Machine learning},
   language = {eng},
   issn = {1746-8094},
   journal = {Biomedical Signal Processing and Control},
   title = {Exploring digital speech biomarkers of hypokinetic dysarthria in a multilingual cohort},
   url = {https://www.sciencedirect.com/science/article/pii/S174680942301100X?via%3Dihub},
   volume = {88},
   year = {2024}
}

TY  - JOUR
ID  - 2371788
AU  - Kováč, Daniel - Mekyska, Jiří - Aharonson, Vered - Harar, Pavol - Galaz, Zoltan - Rapcsak, Steven - Orozco-Arroyave, Juan Rafael - Brabenec, Luboš - Rektorová, Irena
PY  - 2024
TI  - Exploring digital speech biomarkers of hypokinetic dysarthria in a multilingual cohort
JF  - Biomedical Signal Processing and Control
VL  - 88
IS  - B
SP  - 1-11
EP  - 1-11
PB  - ELSEVIER SCI LTD
SN  - 17468094
KW  - Hypokinetic dysarthria
KW  - Parkinson's disease
KW  - Multilingual study
KW  - Acoustic speech features
KW  - Statistical analysis
KW  - Machine learning
UR  - https://www.sciencedirect.com/science/article/pii/S174680942301100X?via%3Dihub
N2  - Hypokinetic dysarthria, a motor speech disorder characterized by reduced movement and control in the speech -related muscles, is mostly associated with Parkinson's disease. Acoustic speech features thus offer the potential for early digital biomarkers to diagnose and monitor the progression of this disease. However, the influence of language on the successful classification of healthy and dysarthric speech remains crucial. This paper explores the analysis of acoustic speech features, both established and newly proposed, in a multilingual context to support the diagnosis of PD. The study aims to identify language-independent and highly discriminative digital speech biomarkers using statistical analysis and machine learning techniques. The study analyzes thirty-three acoustic features extracted from Czech, American, Israeli, Columbian, and Italian PD patients, as well as healthy controls. The analysis employs correlation and statistical tests, descriptive statistics, and the XGBoost classifier. Feature importances and Shapley values are used to provide explanations for the classification results. The study reveals that the most discriminative features, with reduced language dependence, are those measuring the prominence of the second formant, monopitch, and the frequency of pauses during text reading. Classification accuracies range from 67% to 85%, depending on the language. This paper introduces the concept of language robustness as a desirable quality in digital speech biomarkers, ensuring consistent behaviour across languages. By leveraging this concept and employing additional metrics, the study proposes several language-independent digital speech biomarkers with high discrimination power for diagnosing PD.
ER  -

KOVÁČ, Daniel, Jiří MEKYSKA, Vered AHARONSON, Pavol HARAR, Zoltan GALAZ, Steven RAPCSAK, Juan Rafael OROZCO-ARROYAVE, Luboš BRABENEC and Irena REKTOROVÁ. Exploring digital speech biomarkers of hypokinetic dysarthria in a multilingual cohort. \textit{Biomedical Signal Processing and Control}. OXFORD: ELSEVIER SCI LTD, 2024, vol.~88, B, p.~1-11. ISSN~1746-8094. Available from: https://dx.doi.org/10.1016/j.bspc.2023.105667.

Detailed Information on Publication Record