Detail publikace

Digital Biomarkers for Assessing Respiratory Disorders in Parkinson’s Disease

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

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"
}