Source and Vocal Tract Cues for Speech-Based Classification of Patients with Parkinson’s Disease and Healthy Subjects

2021 ◽  
Author(s):  
Tanuka Bhattacharjee ◽  
Jhansi Mallela ◽  
Yamini Belur ◽  
Nalini Atchayaram ◽  
Ravi Yadav ◽  
...  
Keyword(s):  
Healthy Subjects ◽  
Vocal Tract

scholarly journals Real-time classification of hand movements as a basis for intuitive control of grasp neuroprostheses

2020 ◽  
Vol 6 (2) ◽  
Author(s):  
Dmitry Amelin ◽  
Ivan Potapov ◽  
Josep Cardona Audí ◽  
Andreas Kogut ◽  
Rüdiger Rupp ◽  
...  
Keyword(s):  
Neural Networks ◽  
Standard Deviation ◽  
Real Time ◽  
Convolutional Neural Networks ◽  
Recurrent Neural Networks ◽  
Healthy Subjects ◽  
Hand Movements ◽  
Cord Injury ◽  
Field Programmable

AbstractThis paper reports on the evaluation of recurrent and convolutional neural networks as real-time grasp phase classifiers for future control of neuroprostheses for people with high spinal cord injury. A field-programmable gate array has been chosen as an implementation platform due to its form factor and ability to perform parallel computations, which are specific for the selected neural networks. Three different phases of two grasp patterns and the additional open hand pattern were predicted by means of surface Electromyography (EMG) signals (i.e. Seven classes in total). Across seven healthy subjects, CNN (Convolutional Neural Networks) and RNN (Recurrent Neural Networks) had a mean accuracy of 85.23% with a standard deviation of 4.77% and 112 µs per prediction and 83.30% with a standard deviation of 4.36% and 40 µs per prediction, respectively.

scholarly journals Classification of speech under stress based on modeling of the vocal folds and vocal tract

2013 ◽  
Vol 2013 (1) ◽  
Author(s):  
Xiao Yao ◽  
Takatoshi Jitsuhiro ◽  
Chiyomi Miyajima ◽  
Norihide Kitaoka ◽  
Kazuya Takeda
Keyword(s):  
Vocal Tract ◽  
Vocal Folds

Advanced classification of Alzheimer's disease and healthy subjects based on EEG markers

2015 ◽  
Author(s):  
Vitoantonio Bevilacqua ◽  
Angelo Antonio Salatino ◽  
Carlo Di Leo ◽  
Giacomo Tattoli ◽  
Domenico Buongiorno ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Healthy Subjects

CLASSIFICATION OF RESPIRATORY SOUNDS BY USING AN ARTIFICIAL NEURAL NETWORK

2003 ◽  
Vol 17 (04) ◽  
pp. 567-580 ◽  
Author(s):  
ZÜMRAY DOKUR ◽  
TAMER ÖLMEZ
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Dynamic Programming ◽  
Wavelet Transform ◽  
Healthy Subjects ◽  
Respiratory Sounds ◽  
Multi Layer Perceptron ◽  
Wavelet Coefficients ◽  
Kohonen Network

In this paper, a classification method for respiratory sounds (RSs) in patients with asthma and in healthy subjects is presented. Wavelet transform is applied to a window containing 256 samples. Elements of the feature vectors are obtained from the wavelet coefficients. The best feature elements are selected by using dynamic programming. Grow and Learn (GAL) neural network, Kohonen network and multi-layer perceptron (MLP) are used for the classification. It is observed that RSs of patients (with asthma) and healthy subjects are successfully classified by the GAL network.

scholarly journals Serum PTH reference values established by an automated third-generation assay in vitamin D-replete subjects with normal renal function: consequences of diagnosing primary hyperparathyroidism and the classification of dialysis patients

2016 ◽  
Vol 174 (3) ◽  
pp. 315-323 ◽  
Author(s):  
Jean-Claude Souberbielle ◽  
Catherine Massart ◽  
Sylvie Brailly-Tabard ◽  
Catherine Cormier ◽  
Etienne Cavalier ◽  
...  
Keyword(s):  
Vitamin D ◽  
Renal Function ◽  
Primary Hyperparathyroidism ◽  
Reference Values ◽  
Healthy Subjects ◽  
Target Range ◽  
Entire Group ◽  
Third Generation ◽  
Dialysis Patients

ObjectiveTo determine parathyroid hormone (PTH) reference values in French healthy adults, taking into account serum 25-hydroxyvitamin D (25OHD), renal function, age, gender, and BMI.Participants and main biological measurementsWe studied 898 healthy subjects (432 women) aged 18–89 years with a normal BMI and estimated glomerular filtration rate (eGFR), 81 patients with surgically proven primary hyperparathyroidism (PHPT), and 264 dialysis patients. 25OHD and third-generation PTH assays were implemented on the LIAISON XL platform.ResultsMedian PTH and 25OHD values in the 898 healthy subjects were 18.8 ng/l and 23.6 ng/ml respectively. PTH was lower in subjects with 25OHD ≥30 ng/ml than in those with lower values. Among the 183 subjects with 25OHD ≥30 ng/ml, those aged ≥60 years (n=31) had higher PTH values than younger subjects, independent of 25OHD, BMI, and eGFR (P<0.001). Given the small number of subjects aged ≥60 years, we adopted the 95% CI of PTH values for the entire group of 183 vitamin D-replete subjects (9.4–28.9 ng/l) as our reference values. With 28.9 ng/l as the upper limit of normal (ULN) rather than the manufacturer's ULN of 38.4 ng/l, the percentage of PHPT patients with ‘high’ PTH values rose to 90.1% from 66.6% (P<0.001), and 18.6% of the dialysis patients were classified differently in view of the KDIGO target range (two to nine times the ULN).ConclusionWhen only subjects with 25OHD ≥30 ng/ml were included in the reference population, the PTH ULN fell by 22.4%, diagnostic sensitivity for PHPT improved, and the classification of dialysis patients was modified.

scholarly journals The Potential of the Quick Detection of Selectins Using Raman Spectroscopy to Discriminate Lung Cancer Patients from Healthy Subjects

2018 ◽  
Vol 2018 ◽  
pp. 1-5
Author(s):  
Edyta Wolny-Rokicka ◽  
Andrzej Tukiendorf ◽  
Jerzy Wydmański ◽  
Agnieszka Zembroń-Łacny
Keyword(s):  
Lung Cancer ◽  
Raman Spectroscopy ◽  
Cancer Patients ◽  
Healthy Subjects ◽  
Intervention Group ◽  
Medical Intervention ◽  
Lung Cancer Patients ◽  
Rs Analysis ◽  
Group 2

This study aimed at determining the concentration of P-selectins in lung cancer patients in different stages and healthy subjects. Then, the ability of the methodology developed to discriminate the existence of lung cancer was also evaluated. Serum spectra were obtained using Raman spectroscopy (RS). Blood samples were taken from subjects divided into two groups: group 1—comparing data from 22 patients clinically diagnosed with cancer before versus after medical intervention; group 2—comparing data from 10 palliative patients versus 17 healthy volunteers. The RS analysis of the samples revealed the presence of five very similar peaks in both groups 1 and 2. This leads to the conclusion that a medical intervention in cancer cases gives results comparable to those obtained from healthy subjects. The study indicates that the use of Raman spectroscopy can produce a better classification of cancer patients. However, diagnostically the results have not been statistically significant, probably due to the limited number of samples gathered. A larger number of samples would be required for future verification.

scholarly journals Kynurenic Acid Levels are Increased in the CSF of Alzheimer’s Disease Patients

Biomolecules ◽  
2020 ◽  
Vol 10 (4) ◽  
pp. 571 ◽  
Author(s):  
Marta González-Sánchez ◽  
Javier Jiménez ◽  
Arantzazu Narváez ◽  
Desiree Antequera ◽  
Sara Llamas-Velasco ◽  
...  
Keyword(s):  
Neurodegenerative Diseases ◽  
Neurodegenerative Disorders ◽  
Healthy Subjects ◽  
Kynurenic Acid ◽  
Kynurenine Pathway ◽  
Healthy Controls ◽  
Specific Increase ◽  
Normal Controls ◽  
Lateral Sclerosis

Kynurenic acid (KYNA) is a product of the tryptophan (TRP) metabolism via the kynurenine pathway (KP). This pathway is activated in neurodegenerative disorders, such as Alzheimer´s disease (AD). KYNA is primarily produced by astrocytes and is considered neuroprotective. Thus, altered KYNA levels may suggest an inflammatory response. Very recently, significant increases in KYNA levels were reported in cerebrospinal fluid (CSF) from AD patients compared with normal controls. In this study, we assessed the accuracy of KYNA in CSF for the classification of patients with AD, cognitively healthy controls, and patients with a variety of other neurodegenerative diseases, including frontotemporal dementia (FTD), amyotrophic lateral sclerosis (ALS), and progressive supranuclear palsy (PSP). Averaged KYNA concentration in CSF was higher in patients with AD when compared with healthy subjects and with all the other differentially diagnosed groups. There were no significant differences in KYNA levels in CSF between any other neurodegenerative groups and controls. These results suggest a specific increase in KYNA concentration in CSF from AD patients not seen in other neurodegenerative diseases.

Sign in / Sign up

Export Citation Format

Share Document