Parkinson’s Disease Diagnosis in Cepstral Domain Using MFCC and Dimensionality Reduction with SVM Classifier

Abstract

Parkinson’s disease (PD) is one of the most common and serious neurological diseases. Impairments in voice have been reported to be the early biomarkers of the disease. Hence, development of PD diagnostic tool will help early diagnosis of the disease. Additionally, intelligent system developed for binary classification of PD and healthy controls can also be exploited in future as an instrument for prodromal diagnosis. Notably, patients with rapid eye movement (REM) sleep behaviour disorder (RBD) represent a good model as they develop PD with a high probability. It has been shown that slight speech and voice impairment may be a sensitive marker of preclinical PD. In this study, we propose PD detection by extracting cepstral features from the voice signals collected from people with PD and healthy subjects. To classify the extracted features, we propose to use dimensionality reduction through linear discriminant analysis and classification through support vector machine. In order to validate the effectiveness of the proposed method, we also developed ten different machine learning models. It was observed that the proposed method yield area under the curve (AUC) of 88%, sensitivity of 73.33%, and specificity of 84%. Moreover, the proposed intelligent system was simulated using publicly available multiple types of voice database. Additionally, the data were collected from patients under on-state. The obtained results on the public database are promising compared to the previously published work.

Voice in Parkinson's Disease: A Machine Learning Study

“…Our study is therefore the first one to provide a thorought classification of voice in PD patients, according to the stage (i.e., de novo ) and severity of the disease as well as the effect of chronic L-Dopa treatment. Also, supporting the biological plausibility of our results, the most relevant voice features selected by our machine learning algorithms (among the large dataset of features examined), include those previously identified by spectral analysis such as the fundamental frequency ( 3 , 12 – 16 , 26 , 45 ). Moreover, our study showed for the first time significant clinico-instrumental correlations: the higher LR values attributed by machine learning, the longer the disease duration, the higher severity of motor symptoms, and finally the greater voice impairment in patients with PD.…”

A novel sample and feature dependent ensemble approach for Parkinson’s disease detection

“…The second dataset is also multiple types of voice phonations dataset. The dataset was collected by Rahman et al [50] in Lady Reading Hospital (Medical Teaching Institution), Pakistan. The dataset is a relatively bigger dataset and was collected from 160 subjects out of which 60 subjects belong to PD class and the remaining 100 subjects are from the healthy class.…”

“…For classification purposes, they developed an SVM model with different types of kernels and obtained PD detection accuracy of 87.5% accuracy using LOSO CV [19]. Recently, Rahman et al [50] collected a relatively bigger dataset and showed that high PD detection accuracy on a bigger dataset is a challenging task. Most recently, Ali et al showed that instead of selecting features from multiple types of voice data, improved performance can be obtained by selecting samples before feature selection [13].…”

A comparative and comprehensive study of prediction of Parkinson’s disease

“…Our mechanized ML approach permits complex prescient models to be reproducible and available to the local area. Shahid and Singh [65] proposed a PCA based profound neural organization (DNN) model to foresee Motor-UPDRS and Total-UPDRS in Parkinson's illness (PD) movement. The model utilized the decreased info highlight space of Parkinson's telemonitoring dataset for checking the movement.…”