Vocal Feature Extraction-Based Artificial Intelligent Model for Parkinson’s Disease Detection
As a neurodegenerative disorder, Parkinson’s disease (PD) affects the nerve cells of the human brain. Early detection and treatment can help to relieve the symptoms of PD. Recent PD studies have extracted the features from vocal disorders as a harbinger for PD detection, as patients face vocal chang...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-06-01
|
Series: | Diagnostics |
Subjects: | |
Online Access: | https://www.mdpi.com/2075-4418/11/6/1076 |
id |
doaj-db5fcc6a88dc4d14b06e175dbe6ec2d4 |
---|---|
record_format |
Article |
spelling |
doaj-db5fcc6a88dc4d14b06e175dbe6ec2d42021-06-30T23:59:16ZengMDPI AGDiagnostics2075-44182021-06-01111076107610.3390/diagnostics11061076Vocal Feature Extraction-Based Artificial Intelligent Model for Parkinson’s Disease DetectionMuntasir Hoq0Mohammed Nazim Uddin1Seung-Bo Park2Department of Computer Science and Engineering, East Delta University, Chattogram 4209, BangladeshDepartment of Computer Science and Engineering, East Delta University, Chattogram 4209, BangladeshDepartment of Software Convergence Engineering, Inha University, Incheon 22201, KoreaAs a neurodegenerative disorder, Parkinson’s disease (PD) affects the nerve cells of the human brain. Early detection and treatment can help to relieve the symptoms of PD. Recent PD studies have extracted the features from vocal disorders as a harbinger for PD detection, as patients face vocal changes and impairments at the early stages of PD. In this study, two hybrid models based on a Support Vector Machine (SVM) integrating with a Principal Component Analysis (PCA) and a Sparse Autoencoder (SAE) are proposed to detect PD patients based on their vocal features. The first model extracted and reduced the principal components of vocal features based on the explained variance of each feature using PCA. For the first time, the second model used a novel Deep Neural Network (DNN) of an SAE, consisting of multiple hidden layers with L1 regularization to compress the vocal features into lower-dimensional latent space. In both models, reduced features were fed into the SVM as inputs, which performed classification by learning hyperplanes, along with projecting the data into a higher dimension. An F1-score, a Mathews Correlation Coefficient (MCC), and a Precision-Recall curve were used, along with accuracy to evaluate the proposed models due to highly imbalanced data. With its highest accuracy of 0.935, F1-score of 0.951, and MCC value of 0.788, the probing results show that the proposed model of the SAE-SVM surpassed not only the former model of the PCA-SVM and other standard models including Multilayer Perceptron (MLP), Extreme Gradient Boosting (XGBoost), K-Nearest Neighbor (KNN), and Random Forest (RF), but also surpassed two recent studies using the same dataset. Oversampling and balancing the dataset with SMOTE boosted the performance of the models.https://www.mdpi.com/2075-4418/11/6/1076medical analyticsParkinson’s disease detectionprincipal component analysissparse autoencodersupport vector machine |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Muntasir Hoq Mohammed Nazim Uddin Seung-Bo Park |
spellingShingle |
Muntasir Hoq Mohammed Nazim Uddin Seung-Bo Park Vocal Feature Extraction-Based Artificial Intelligent Model for Parkinson’s Disease Detection Diagnostics medical analytics Parkinson’s disease detection principal component analysis sparse autoencoder support vector machine |
author_facet |
Muntasir Hoq Mohammed Nazim Uddin Seung-Bo Park |
author_sort |
Muntasir Hoq |
title |
Vocal Feature Extraction-Based Artificial Intelligent Model for Parkinson’s Disease Detection |
title_short |
Vocal Feature Extraction-Based Artificial Intelligent Model for Parkinson’s Disease Detection |
title_full |
Vocal Feature Extraction-Based Artificial Intelligent Model for Parkinson’s Disease Detection |
title_fullStr |
Vocal Feature Extraction-Based Artificial Intelligent Model for Parkinson’s Disease Detection |
title_full_unstemmed |
Vocal Feature Extraction-Based Artificial Intelligent Model for Parkinson’s Disease Detection |
title_sort |
vocal feature extraction-based artificial intelligent model for parkinson’s disease detection |
publisher |
MDPI AG |
series |
Diagnostics |
issn |
2075-4418 |
publishDate |
2021-06-01 |
description |
As a neurodegenerative disorder, Parkinson’s disease (PD) affects the nerve cells of the human brain. Early detection and treatment can help to relieve the symptoms of PD. Recent PD studies have extracted the features from vocal disorders as a harbinger for PD detection, as patients face vocal changes and impairments at the early stages of PD. In this study, two hybrid models based on a Support Vector Machine (SVM) integrating with a Principal Component Analysis (PCA) and a Sparse Autoencoder (SAE) are proposed to detect PD patients based on their vocal features. The first model extracted and reduced the principal components of vocal features based on the explained variance of each feature using PCA. For the first time, the second model used a novel Deep Neural Network (DNN) of an SAE, consisting of multiple hidden layers with L1 regularization to compress the vocal features into lower-dimensional latent space. In both models, reduced features were fed into the SVM as inputs, which performed classification by learning hyperplanes, along with projecting the data into a higher dimension. An F1-score, a Mathews Correlation Coefficient (MCC), and a Precision-Recall curve were used, along with accuracy to evaluate the proposed models due to highly imbalanced data. With its highest accuracy of 0.935, F1-score of 0.951, and MCC value of 0.788, the probing results show that the proposed model of the SAE-SVM surpassed not only the former model of the PCA-SVM and other standard models including Multilayer Perceptron (MLP), Extreme Gradient Boosting (XGBoost), K-Nearest Neighbor (KNN), and Random Forest (RF), but also surpassed two recent studies using the same dataset. Oversampling and balancing the dataset with SMOTE boosted the performance of the models. |
topic |
medical analytics Parkinson’s disease detection principal component analysis sparse autoencoder support vector machine |
url |
https://www.mdpi.com/2075-4418/11/6/1076 |
work_keys_str_mv |
AT muntasirhoq vocalfeatureextractionbasedartificialintelligentmodelforparkinsonsdiseasedetection AT mohammednazimuddin vocalfeatureextractionbasedartificialintelligentmodelforparkinsonsdiseasedetection AT seungbopark vocalfeatureextractionbasedartificialintelligentmodelforparkinsonsdiseasedetection |
_version_ |
1721349892318691328 |