Accurate telemonitoring of Parkinson’s disease progression by non-invasive speech tests

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

doi:10.1038/npre.2009.3920.1

Cited by 105 publications

(115 citation statements)

References 10 publications

(17 reference statements)

Supporting

Mentioning

111

Contrasting

Unclassified

Order By: Relevance

“…We next apply model (2) to a data set containing information from 5,875 voice recordings on 42 patients with earlystage Parkinson's disease [17,32]. This data set is publicly available at {http://archive.ics.uci.edu/ml/datasets/Parkinsons+ Telemonitoring}.…”

Section: Parkinson's Telemonitoring Case Studymentioning

confidence: 99%

“…Moreover, there has been little emphasis on derivative estimation. The present paper is partly motivated by -and will use model (2) with a vector covariate x and derivative estimation to address -the question of how Parkinson's disease symptoms progress in relation to the vocal characteristics of patients, which constitute a sort of diagnostic test [17,32]. Section 4 provides a fuller description of the publicly available Parkinson's telemonitoring data set, including definitions of the response variable and covariates.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Nonparametric and semiparametric compound estimation in multiple covariates

Charnigo

Feng

Srinivasan

2015

Journal of Multivariate Analysis

View full text Add to dashboard Cite

a b s t r a c tWe consider the problem of simultaneously estimating a mean response function and its partial derivatives, when the mean response function depends nonparametrically on two or more covariates. To address this problem, we propose a ''compound estimation'' approach, in which differentiation and estimation are interchangeable: an estimated partial derivative is exactly equal to the corresponding partial derivative of the estimated mean response function. Compound estimation yields essentially optimal convergence rates and may exhibit substantially smaller squared error in finite samples compared to local regression. We also explain how to employ compound estimation under more general circumstances, when the mean response function depends parametrically on some additional covariates and the observations are not statistically independent. In a case study, we apply compound estimation to examine how the progression of Parkinson's disease may relate to a subject's age and the signal fractal scaling exponent of the subject's recorded voice. Especially among those intermediate in age, an abnormal signal fractal scaling exponent may portend greater symptom progression.

show abstract

Section: Parkinson's Telemonitoring Case Studymentioning

confidence: 99%

mentioning

confidence: 99%

Nonparametric and semiparametric compound estimation in multiple covariates

Charnigo

Feng

Srinivasan

2015

Journal of Multivariate Analysis

View full text Add to dashboard Cite

show abstract

“…The results demonstrate that these new dysphonia measures can outperform existing results, reaching almost 99% overall classification accuracy using only ten dysphonia features. The use of four different FS to find only 10 features from the original 132 features has led to an informative feature subset for the binary classification task of this study, which may also tentatively suggest the most detectable characteristics of voice impairment in PD [21,[22][23][24].…”

Section: Range( G-lp )(°)mentioning

confidence: 99%

Objective assessment of Parkinson's disease symptoms severity: A review

Oung

Hariharan

Lee

et al. 2015

2015 2nd International Conference on Biomedical Engineering (ICoBE)

View full text Add to dashboard Cite

Parkinson's disease (PD) is placed as second supreme neurodegenerative sicknesses after Alzheimer's. It is characterized by dopaminergic deficiencies in the mid brain that impair motor function. Due to rise in proportion of elderly people the number of patients with Parkinson (PWP) are expected to increase for the coming 25 years. Until now, there are still no solutions towards PD, although medication and surgical intervention can temporarily hold back the progression of the symptom. Therefore, early diagnosis is critical in order in improving PWP disease quality of life and prolong longevity, where many of them will be substantially dependent on clinical intervention. The investigators begin exploring motor disorders and the likelihood of applying various types of sensor to measure the significance of clinical involvements on the quality of movement observed while PWP accomplished different tasks. The focus of this review is to provide a discussion of the capabilities of wearable technology and audio sensors in the assessment of PD symptoms severity. Index Terms-Parkinson's Disease (PD), wearable sensors, speech signal, patients with Parkinson(PWP), Unified Parkinson Disease Rating Scale (UPDRS)

show abstract

“…Cmejla et al [24] proposed a Bayesian autoregressive change point detector (BACD) for the evaluation of speech disfluency and articulation impairment. Tsanas et al [25] used the AHTD (At Home Testing Device by Intel Corp. [26]) for telemonitoring PD patients, in order to track the disease progression at home. However, the audio processing (concerning sustained vowels only) is made offline, as the voice records are sent to a server located in the medical centre.…”

Section: Introductionmentioning

confidence: 99%