Přístupnostní navigace
E-přihláška
Vyhledávání Vyhledat Zavřít
Detail publikace
KOVÁČ, D. CVETLER, D.
Originální název
Digital Biomarkers for Assessing Respiratory Disorders in Parkinson’s Disease
Typ
článek ve sborníku ve WoS nebo Scopus
Jazyk
angličtina
Originální abstrakt
Respiratory disorders are a significant part of hypokinetic dysarthria (HD) that affects patients with Parkinson’s disease (PD). Still, their potential role in the objective assessment of HD has not yet been fully explored, which is the primary goal of this study. Several respiratory features were designed and extracted from acoustic signals recorded during text reading. Based on these features, the XGBoost model was able to predict clinical test scores of phonorespiration with an estimated error rate of 12.54%. Statistical analysis revealed that measuring respiration rate and quantifying signal fluctuations during inspiration have great potential in the objective assessment of respiratory disorders in patients with PD.
Klíčová slova
respiration, digital biomarkers, hypokineticdysarthria, Parkinson’s disease, statistics, machine learning
Autoři
KOVÁČ, D.; CVETLER, D.
Vydáno
25. 4. 2023
Nakladatel
Brno University of Technology, Faculty of Elektronic Engineering and Communication
Místo
Brno
ISBN
978-80-214-6154-3
Kniha
Proceedings II of the 29st Conference STUDENT EEICT 2023: Selected papers
Edice
1
ISSN
2788-1334
Periodikum
Proceedings II of the Conference STUDENT EEICT
Stát
Česká republika
Strany od
232
Strany do
236
Strany počet
5
URL
https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2023_sbornik_2_v2.pdf
BibTex
@inproceedings{BUT184102, author="Daniel {Kováč} and Dominik {Cvetler}", title="Digital Biomarkers for Assessing Respiratory Disorders in Parkinson’s Disease", booktitle="Proceedings II of the 29st Conference STUDENT EEICT 2023: Selected papers", year="2023", series="1", journal="Proceedings II of the Conference STUDENT EEICT", pages="232--236", publisher="Brno University of Technology, Faculty of Elektronic Engineering and Communication", address="Brno", doi="10.13164/eeict.2023.232", isbn="978-80-214-6154-3", issn="2788-1334", url="https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2023_sbornik_2_v2.pdf" }