Publication detail

Digital Biomarkers for Assessing Respiratory Disorders in Parkinson’s Disease

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

ISBN

2788-1334

Periodical

Proceedings II of the Conference STUDENT EEICT

State

Czech Republic

Pages from

232

Pages to

236

Pages count

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"
}