Suitability of Dysphonia Measurements for Telemonitoring of Parkinson's Disease

By Max A. Little, Patrick E. McSharry, Eric J. Hunter, Jennifer L. Spielman, Lorraine O. Ramig. IEEE Transactions on Biomedical Engineering, 2008

1,134 citations recorded by the source corpus.

In this paper, we present an assessment of the practical value of existing traditional and nonstandard measures for discriminating healthy people from people with Parkinson's disease (PD) by detecting dysphonia. We introduce a new measure of dysphonia, pitch period entropy (PPE), which is robust to many uncontrollable confounding effects including noisy acoustic environments and normal, healthy variations in voice frequency. We collected sustained phonations from 31 people, 23 with PD. We then selected ten highly uncorrelated measures, and an exhaustive search of all possible combinations of these measures finds four that in combination lead to overall correct classification performance of 91.4%, using a kernel support vector machine. In conclusion, we find that nonstandard methods in combination with traditional harmonics-to-noise ratios are best able to separate healthy from PD subjects. The selected nonstandard methods are robust to many uncontrollable variations in acoustic environment and individual subjects, and are thus well suited to telemonitoring applications.

Subfields: Physiology, Signal Processing

View Paper: https://www.semanticscholar.org/paper/3945c8c4427323fa096263a00ff7ce121c76fa84

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Physiology

In Signal Processing

Citations in the corpus

Novel Speech Signal Processing Algorithms for High-Accuracy Classification of Parkinson's Disease (2012, methodology): “Sakar and Kursun 2010 [40] SVM, bootstrap with 50 replicates 92.8 ± 1.2 Little et al. 2009 [5] SVM, bootstrap with 50 replicates 91.4 ± 4.4 Psorakis et al. 2010 [41] Non-sparse E-M, 10-fold crossvalidation with 10 repetitions 89.5 ± 6.6 Shahbaba and Neal 2009 [42] dpMNL, 5-fold cross-validation…”
Collection and Analysis of a Parkinson Speech Dataset With Multiple Types of Sound Recordings (2013, methodology): “The main reason behind the popularity of PD diagnosis from speech impairments is that telediagnosis and telemonitoring systems based on speech signals are low in cost and easy to self-use [7], [13].”
New Spanish speech corpus database for the analysis of people suffering from Parkinson’s disease (2014, methodology): “In (Little et al., 2009) different acoustics and nonlinear measurements are used to evaluate sustained phonations of the English vowel /ah/ ut-tered by 23 patients with PD and 8 healthy controls.”
Multi-Objective Parameter Selection for Classifiers (2012, methodology): “In the context of quasi-Monte Carlo integration, Morokoff and Caflisch (1995) showed that Halton sequences generally give better results for up to 6 dimensions, whereas Sobol sequences (and Niederreiter sequences, as they are a generalization of Sobol sequences) perform better for higher dimensions.”
A comparison of multiple classification methods for diagnosis of Parkinson disease (2010, methodology): “In (Little et al., 2008), it is introduced a newmeasure of dysphonia that we dub pitch period entropy (PPE), a robust measure sensitive to observed changes in speech specific to PD for controlling these uncontrollable variations.”
Accurate Telemonitoring of Parkinson's Disease Progression by Noninvasive Speech Tests (2009, methodology): “Both information criteria (AIC and BIC) agree on a subset containing six measures: MDVP: Jitter (Abs), MDVP: Shimmer, NHR, HNR, DFA, and PPE for the CART method.”
Continuous Hyper-parameter Learning for Support Vector Machines (2015, methodology): “We achieve good results using no pre-processing and no filtering of correlated features compared to the original paper [16] where they report a test classification rate of 8.”
Generalizing to Unseen Domains: A Survey on Domain Generalization (2021, positive): “telemonitoring dataset [247] is popular for predicting the clinician’s motor and total UPDRS scoring of Parkinson’s disease symptoms from voice measures.”
Highly comparative time-series analysis: the empirical structure of time series and their methods (2013, methodology): “the ‘jitter’ summary statistic [17]), and we also identified some new techniques (cf.”