Abstract
Recent studies have demonstrated that analysis of laboratory-quality voice recordings can be used to accurately differentiate people diagnosed with Parkinson's disease (PD) from healthy controls (HCs). These findings could help facilitate the development of remote screening and monitoring tools for PD. In this study, 2759 telephone-quality voice recordings from 1483 PD and 15 321 recordings from 8300 HC participants were analyzed. To account for variations in phonetic backgrounds, data were acquired from seven countries. A statistical framework for analyzing voice was developed, whereby 307 dysphonia measures that quantify different properties of voice impairment, such as breathiness, roughness, monopitch, hoarse voice quality, and exaggerated vocal tremor, were computed. Feature selection algorithms were used to identify robust parsimonious feature subsets, which were used in combination with a random forests (RFs) classifier to accurately distinguish PD from HC. The best tenfold cross-validation performance was obtained using Gram-Schmidt orthogonalization and RF, leading to mean sensitivity of 64.90% (standard deviation, SD, 2.90%) and mean specificity of 67.96% (SD 2.90%). This large scale study is a step forward toward assessing the development of a reliable, cost-effective, and practical clinical decision support tool for screening the population at large for PD using telephone-quality voice.
Highlights
Institute, University of Oxford, Oxford, OX2 6GG, United Kingdom.solely on voice samples collected over the standard telephone network, facilitating its widespread use as a population screening tool.Vocal performance degradation is met in the vast majority of people diagnosed with PD, and may be one of the earliest indicators of disease onset (Harel et al, 2004)
This study investigated the potential of using telephonequality voice recordings for discriminating PD participants from control participants
We remark that previous studies in the research literature were considerably more limited in the number of participants; they relied on high-quality data typically recorded under highly controlled conditions and used expert clinical diagnosis as the ground truth
Summary
University of Oxford, Oxford, OX2 6GG, United Kingdom.solely on voice samples collected over the standard telephone network, facilitating its widespread use as a population screening tool.Vocal performance degradation is met in the vast majority of people diagnosed with PD, and may be one of the earliest indicators of disease onset (Harel et al, 2004). Using high-quality voice recordings, recent studies have developed technologies to (1) discriminate PD from controls (Little et al, 2009; Das, 2010; Astr€om and Koker, 2011; Luukka, 2011; Tsanas et al, 2012; Chen et al, 2013; Naranjo et al, 2016; Orozco-Arroyave et al, 2016; Godino-Llorente et al, 2017; Parisi et al, 2019), (2) telemonitor PD symptom severity (Tsanas et al, 2011; Eskidere et al, 2012), and (3) monitor voice rehabilitation in PD (Tsanas et al, 2014b). Recent studies have investigated the feasibility and efficacy of using smartphone technology, which extended the use of voice data to include four additional tests for gait, postural sway, dexterity, and reaction times, to support clinical diagnosis for PD. A major limitation of that pilot study, was that it was conducted with a very small cohort size
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
