Original title:
Digital Biomarkers for Assessing Respiratory Disorders in Parkinson’s Disease
Authors:
Kováč, Daniel ; Cvetler, Dominik Document type: Papers
Language:
eng Publisher:
Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií Abstract:
Respiratory disorders are a significant part of hypokineticdysarthria (HD) that affects patients with Parkinson’sdisease (PD). Still, their potential role in the objective assessmentof HD has not yet been fully explored, which is the primary goalof this study. Several respiratory features were designed andextracted from acoustic signals recorded during text reading.Based on these features, the XGBoost model was able to predictclinical test scores of phonorespiration with an estimated errorrate of 12.54%. Statistical analysis revealed that measuring respirationrate and quantifying signal fluctuations during inspirationhave great potential in the objective assessment of respiratorydisorders in patients with PD.
Keywords:
digital biomarkers; hypokineticdysarthria; machine learning; Parkinson’s disease; respiration; statistics Host item entry: Proceedings II of the 29st Conference STUDENT EEICT 2023: Selected papers, ISBN 978-80-214-6154-3, ISSN 2788-1334
Institution: Brno University of Technology
(web)
Document availability information: Fulltext is available in the Brno University of Technology Digital Library. Original record: http://hdl.handle.net/11012/210697