Přístupnostní navigace
E-application
Search Search Close
Publication detail
KOVÁČ, D. CVETLER, D.
Original Title
Digital Biomarkers for Assessing Respiratory Disorders in Parkinson’s Disease
Type
conference paper
Language
English
Original Abstract
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.
Keywords
respiration, digital biomarkers, hypokineticdysarthria, Parkinson’s disease, statistics, machine learning
Authors
KOVÁČ, D.; CVETLER, D.
Released
25. 4. 2023
Publisher
Brno University of Technology, Faculty of Elektronic Engineering and Communication
Location
Brno
ISBN
978-80-214-6154-3
Book
Proceedings II of the 29st Conference STUDENT EEICT 2023: Selected papers
Edition
1
2788-1334
Periodical
Proceedings II of the Conference STUDENT EEICT
State
Czech Republic
Pages from
232
Pages to
236
Pages count
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" }