Pattern recognition methods for multi stage classification of parkinson's disease utilizing voice features

Caesarendra, Wahyu; Putri, Farika Tono; Ariyanto, Mochammad; Setiawan, Joga Dharma

doi:10.1109/aim.2015.7222636

Cited by 18 publications

(7 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tsanas et al targeted identification of PD based on vocal performance (SVM classifier, 90% accuracy) [64]. Caesarendra et al analysed pattern recognition with voice features in PD stage classification (SVM, 79.17% accuracy) [65]. Hauptman et.…”

Section: Discussionmentioning

confidence: 99%

Detection of Speech Impairments Using Cepstrum, Auditory Spectrogram and Wavelet Time Scattering Domain Features

et al. 2020

View full text Add to dashboard Cite

We adopt Bidirectional Long Short-Term Memory (BiLSTM) neural network and Wavelet Scattering Transform with Support Vector Machine (WST-SVM) classifier for detecting speech impairments of patients at the early stage of central nervous system disorders (CNSD). The study includes 339 voice samples collected from 15 subjects: 7 patients with early stage CNSD (3 Huntington, 1 Parkinson, 1 cerebral palsy, 1 post stroke, 1 early dementia), other 8 subjects were healthy. Speech data is collected using voice recorder from Neural Impairment Test Suite (NITS) mobile app. Features are extracted from pitch contours, Mel-frequency cepstral coefficients (MFCC), Gammatone cepstral coefficients (GTCC), Gabor (analytic Morlet) wavelet and auditory spectrograms. 94.50% (BiLSTM) and 96.3% (WST-SVM) accuracy is achieved for solving healthy vs. impaired classification problem. The developed method can be applied for automated CNSD patient health state monitoring and clinical decision support systems as well as a part of Internet of Medical Things (IoMT). INDEX TERMS Neural impairment, mobile app, deep learning, wavelet scattering, decision support, speech processing, digital health, Internet of Medical Things.

show abstract

Section: Discussionmentioning

confidence: 99%

Detection of Speech Impairments Using Cepstrum, Auditory Spectrogram and Wavelet Time Scattering Domain Features

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Feature extraction using the signal-to-noise ratio (SNR), harmonic-to-noise ratio (HNR), vocal fold excitation ratio (VFER), glottal to noise excitation (GNE), and empirical mode decomposition excitation ratio (EMD-ER) methods with random forest (RF) and SVM for classification were used in Tsanas et al [28]. Other approaches were introduced in An et al [29], namely syllable-level, low-level descriptor (LLD), formant, and phonotactic features with an SVM classifier and features from principal component analysis (PCA); while Caesarendra et al [30] introduced linear discriminant analysis (LDA), SVM, adaptive boosting (AdaBoost), KNN, and adaptive resonance theory-Kohonen neural network (ART-KNN).…”

Section: Related Workmentioning

confidence: 99%

A Mobile Application for Smart Computer-Aided Self-Administered Testing of Cognition, Speech, and Motor Impairment

Lauraitis

Maskeliūnas

Damaševičius

et al. 2020

Sensors

View full text Add to dashboard Cite

We present a model for digital neural impairment screening and self-assessment, which can evaluate cognitive and motor deficits for patients with symptoms of central nervous system (CNS) disorders, such as mild cognitive impairment (MCI), Parkinson’s disease (PD), Huntington’s disease (HD), or dementia. The data was collected with an Android mobile application that can track cognitive, hand tremor, energy expenditure, and speech features of subjects. We extracted 238 features as the model inputs using 16 tasks, 12 of them were based on a self-administered cognitive testing (SAGE) methodology and others used finger tapping and voice features acquired from the sensors of a smart mobile device (smartphone or tablet). Fifteen subjects were involved in the investigation: 7 patients with neurological disorders (1 with Parkinson’s disease, 3 with Huntington’s disease, 1 with early dementia, 1 with cerebral palsy, 1 post-stroke) and 8 healthy subjects. The finger tapping, SAGE, energy expenditure, and speech analysis features were used for neural impairment evaluations. The best results were achieved using a fusion of 13 classifiers for combined finger tapping and SAGE features (96.12% accuracy), and using bidirectional long short-term memory (BiLSTM) (94.29% accuracy) for speech analysis features.

show abstract

“…So far, many studies have used intelligent methods to diagnose PD on the Oxford Parkinson dataset, including basic machine learning methods [21,22], hybrid classifiers [14,20,23,24], evolutionary algorithms [25,26] and fuzzy expert system [24,27,28]. The study by Abiyev and Abizade [24] is one of the works that has been done to extract the diagnostic rules of PD.…”

Section: Introductionmentioning

confidence: 99%

A Novel Structure of Highly Interpretable Fuzzy Rules Extraction

Ahouz¹,

Golabpour

2021

Front Health Inform

View full text Add to dashboard Cite

Introduction: Extracting effective rules from medical data with two indicators of accuracy and high interpretability is essential to increase the accuracy and speed of diagnosis by specialists. As a result, the production of medical assistant systems that are able to detect the rules governing the data plays a vital role in early detection of the disease and thus increase the chances of treatment, disease control and maintaining the quality of life of patients.Material and Methods: In this paper, a system of automatic extraction of rules from medical data by a new hybrid method based on fuzzy logic and genetic algorithm is presented. Genetic algorithms are used to automatically generate these rules. The Parkinson UCI dataset including 195 records and 23 variables was used to evaluate the proposed method based on the criteria of interpretability, accuracy, sensitivity and specificity.Results: The evaluation of the proposed model on the Parkinson's dataset was the accuracy of 84.62%. This accuracy is supported by 4 fuzzy rules with an average rule length of 2 and using 7 linguistic terms extremely low, very low, low, normal, high, very high and extremely high. All fuzzy membership functions that represent each term have the same width.Conclusion: The proposed method, based on the three criteria of low number of rules, short rule length and symmetric membership functions with equal width for all variables, is quite suitable for automatic production of accurate and compact rules with high interpretability in medical data. . A 90% dimensionality reduction in the experimental evaluation showed that this model could be used to implement real-time systems.

show abstract

Pattern recognition methods for multi stage classification of parkinson's disease utilizing voice features

Cited by 18 publications

References 6 publications

Detection of Speech Impairments Using Cepstrum, Auditory Spectrogram and Wavelet Time Scattering Domain Features

Detection of Speech Impairments Using Cepstrum, Auditory Spectrogram and Wavelet Time Scattering Domain Features

A Mobile Application for Smart Computer-Aided Self-Administered Testing of Cognition, Speech, and Motor Impairment

A Novel Structure of Highly Interpretable Fuzzy Rules Extraction

Contact Info

Product

Resources

About