Detail publikace

Assessing progress of Parkinson's disease using acoustic analysis of phonation

Originální název

Assessing progress of Parkinson's disease using acoustic analysis of phonation

Anglický název

Assessing progress of Parkinson's disease using acoustic analysis of phonation

Jazyk

en

Originální abstrakt

This paper deals with a complex acoustic analysis of phonation in patients with Parkinson's disease (PD) with a special focus on estimation of disease progress that is described by 7 different clinical scales (e. g. Unified Parkinson's disease rating scale or Beck depression inventory). The analysis is based on parametrization of 5 Czech vowels pronounced by 84 PD patients. Using classification and regression trees we estimated all clinical scores with maximal error lower or equal to 13 %. Best estimation was observed in the case of Mini-mental state examination (MAE = 0.77, estimation error 5.50 %). Finally, we proposed a binary classification based on random forests that is able to identify Parkinson's disease with sensitivity SEN = 92.86% (SPE = 85.71 %). The parametrization process was based on extraction of 107 speech features quantifying different clinical signs of hypokinetic dysarthria present in PD.

Anglický abstrakt

This paper deals with a complex acoustic analysis of phonation in patients with Parkinson's disease (PD) with a special focus on estimation of disease progress that is described by 7 different clinical scales (e. g. Unified Parkinson's disease rating scale or Beck depression inventory). The analysis is based on parametrization of 5 Czech vowels pronounced by 84 PD patients. Using classification and regression trees we estimated all clinical scores with maximal error lower or equal to 13 %. Best estimation was observed in the case of Mini-mental state examination (MAE = 0.77, estimation error 5.50 %). Finally, we proposed a binary classification based on random forests that is able to identify Parkinson's disease with sensitivity SEN = 92.86% (SPE = 85.71 %). The parametrization process was based on extraction of 107 speech features quantifying different clinical signs of hypokinetic dysarthria present in PD.

BibTex


@inproceedings{BUT115864,
  author="Jiří {Mekyska} and Zoltán {Galáž} and Zdeněk {Mžourek} and Zdeněk {Smékal} and Irena {Rektorová} and Ilona {Eliášová} and Milena {Košťálová} and Martina {Mračková} and Dagmar {Berankova} and Marcos {Faúndez Zanuy} and Karmele {Lopez-de-Ipina} and Jesus {Alonso-Hernandez}",
  title="Assessing progress of Parkinson's disease using acoustic analysis of phonation",
  annote="This paper deals with a complex acoustic analysis of phonation in patients with Parkinson's disease (PD) with a special focus on estimation of disease progress that is described by 7 different clinical scales (e. g. Unified Parkinson's disease rating scale or Beck depression inventory). The analysis is based on parametrization of 5 Czech vowels pronounced by 84 PD patients. Using classification and regression trees we estimated all clinical scores with maximal error lower or equal to 13 %. Best estimation was observed in the case of Mini-mental state examination (MAE = 0.77, estimation error 5.50 %). Finally, we proposed a binary classification based on random forests that is able to identify Parkinson's disease with sensitivity SEN = 92.86% (SPE = 85.71 %). The parametrization process was based on extraction of 107 speech features quantifying different clinical signs of hypokinetic dysarthria present in PD.",
  booktitle="2015 4th International Work Conference on Bioinspired Intelligence (IWOBI)",
  chapter="115864",
  doi="10.1109/IWOBI.2015.7160153",
  howpublished="print",
  year="2015",
  month="june",
  pages="111--118",
  type="conference paper"
}