Robust parsimonious selection of dysphonia measures for telemonitoring of parkinson's disease symptom severity

Athanasios Tsanas*, Max A. Little, Patrick E. McSharry, Lorraine O. Ramig

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Parkinson's disease (PD) symptom severity is typically quantified using the standard clinical metric Unified Parkinson's Disease Rating Scale (UPDRS) which spans the range 0-176 (0 denotes healthy). This assessment requires the patient's physical presence in the clinic, is time consuming, and relies on the clinical rater's subjective evaluation and experience; practice has shown that expert clinicians might differ by as much as 4-5 UPDRS points in their evaluations. We had previously developed a statistical machine learning framework which enables accurate and objective quantification of average PD symptom severity using exclusively speech signals. for this purpose, we evaluated 132 speech signal processing algorithms (dysphonia measures), which attempt to capture distinctive characteristics in PD subjects' voice. on a very large database of about 6,000 phonations, we could replicate the clinical experts' assessments within less than two UPDRS points' error. in this paper, we focus on identifying the most successful of the original 132 dysphonia measures in estimating UPDRS using five robust feature selection techniques. We demonstrate that we can improve on our previous findings using only 15 dysphonia measures, where the selected measures also tentatively indicate the most representative pathophysiological characteristics in male and female PD voices.

Original languageEnglish
Title of host publicationModels and Analysis of Vocal Emissions for Biomedical Applications - 7th International Workshop, MAVEBA 2011
EditorsClaudia Manfredi
PublisherFirenze University Press
Pages169-172
Number of pages4
ISBN (Electronic)9788866550099
Publication statusPublished - 1 Jan 2011
Event7th International Workshop on Models and Analysis of Vocal Emissions for Biomedical Applications, MAVEBA 2011 - Firenze, Italy
Duration: 25 Aug 201127 Aug 2011

Publication series

NameModels and Analysis of Vocal Emissions for Biomedical Applications - 7th International Workshop, MAVEBA 2011

Conference

Conference7th International Workshop on Models and Analysis of Vocal Emissions for Biomedical Applications, MAVEBA 2011
Country/TerritoryItaly
CityFirenze
Period25/08/1127/08/11

Keywords / Materials (for Non-textual outputs)

  • Feature selection
  • Parkinson's disease
  • Telemedicine
  • Unified parkinson's disease rating scale

Fingerprint

Dive into the research topics of 'Robust parsimonious selection of dysphonia measures for telemonitoring of parkinson's disease symptom severity'. Together they form a unique fingerprint.

Cite this