Assessing progress of Parkinson's disease using acoustic analysis of phonation
- Resource Type
- Conference
- Authors
- Mekyska, Jiri; Galaz, Zoltan; Mzourek, Zdenek; Smekal, Zdenek; Rektorova, Irena; Eliasova, Ilona; Kostalova, Milena; Mrackova, Martina; Berankova, Dagmar; Faundez-Zanuy, Marcos; Lopez-de-Ipina, Karmele; Alonso-Hernandez, Jesus B.
- Source
- 2015 4th International Work Conference on Bioinspired Intelligence (IWOBI) Bioinspired Intelligence (IWOBI), 2015 4th International Work Conference on. :111-118 Jun, 2015
- Subject
- Bioengineering
Computing and Processing
Signal Processing and Analysis
Parkinson's disease
Speech
Feature extraction
Correlation
Indexes
Light emitting diodes
Estimation
- Language
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.