Parkinson’s Disease Diagnosis With Gait Characteristics Extracted Using Wavelet Transforms
Objective: Parkinson’s disease (PD) is a common neurodegenerative disorder among adult men and women. The analysis of abnormal gait patterns is among the most important techniques used in the early diagnosis of PD. The overall aim of this study is to identify PD patients using vertical gr...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Journal of Translational Engineering in Health and Medicine |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10114804/ |
_version_ | 1797829603691069440 |
---|---|
author | Dixon Vimalajeewa Ethan McDonald Megan Tung Brani Vidakovic |
author_facet | Dixon Vimalajeewa Ethan McDonald Megan Tung Brani Vidakovic |
author_sort | Dixon Vimalajeewa |
collection | DOAJ |
description | Objective: Parkinson’s disease (PD) is a common neurodegenerative disorder among adult men and women. The analysis of abnormal gait patterns is among the most important techniques used in the early diagnosis of PD. The overall aim of this study is to identify PD patients using vertical ground reaction force (VGRF) data produced from subjects while walking at a normal pace. Methods and procedures: The current study proposes a novel set of features extracted on the basis of self-similar, correlation, and entropy properties that are characterized by multiscale features of VGRF data in the wavelet-domain. Five discriminatory features have been proposed. PD diagnosis performance of those features are investigated by using a publicly available VGRF dataset (93 controls and 73 cases) and standard classifiers. Logistic regression (LR), support vector machine (SVM) and k-nearest neighbor (KNN) are used for the performance evaluation. Results: The SVM classifier outperformed the LR and KNN classifiers with an average accuracy of 88.89%, sensitivity of 89%, and specificity of 88%. The integration of these five features from the wavelet domain of data, with three time domain features, stance time, swing time and maximum force strike at toe improved the PD diagnosis performance (approximately by 10%), which outperforms existing studies that are based on the same data set. Conclusion: with the previously published approaches, the proposed prediction methodology consisting of the multiscale features in combination with the time domain features shows better performance with fewer features, compared to the existing PD diagnostic techniques. Clinical impact: The findings suggest that the proposed diagnostic method involving multiscale (wavelet) features can improve the efficacy of PD diagnosis. |
first_indexed | 2024-04-09T13:22:55Z |
format | Article |
id | doaj.art-361387601028427da585d276eefbd269 |
institution | Directory Open Access Journal |
issn | 2168-2372 |
language | English |
last_indexed | 2024-04-09T13:22:55Z |
publishDate | 2023-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Journal of Translational Engineering in Health and Medicine |
spelling | doaj.art-361387601028427da585d276eefbd2692023-05-10T23:00:14ZengIEEEIEEE Journal of Translational Engineering in Health and Medicine2168-23722023-01-011127128110.1109/JTEHM.2023.327279610114804Parkinson’s Disease Diagnosis With Gait Characteristics Extracted Using Wavelet TransformsDixon Vimalajeewa0https://orcid.org/0000-0001-6794-4776Ethan McDonald1Megan Tung2Brani Vidakovic3https://orcid.org/0000-0001-9155-9325Department of Statistics, Texas A&M University, College Station, TX, USADepartment of Statistics, Texas A&M University, College Station, TX, USADepartment of Statistics, Texas A&M University, College Station, TX, USADepartment of Statistics, Texas A&M University, College Station, TX, USAObjective: Parkinson’s disease (PD) is a common neurodegenerative disorder among adult men and women. The analysis of abnormal gait patterns is among the most important techniques used in the early diagnosis of PD. The overall aim of this study is to identify PD patients using vertical ground reaction force (VGRF) data produced from subjects while walking at a normal pace. Methods and procedures: The current study proposes a novel set of features extracted on the basis of self-similar, correlation, and entropy properties that are characterized by multiscale features of VGRF data in the wavelet-domain. Five discriminatory features have been proposed. PD diagnosis performance of those features are investigated by using a publicly available VGRF dataset (93 controls and 73 cases) and standard classifiers. Logistic regression (LR), support vector machine (SVM) and k-nearest neighbor (KNN) are used for the performance evaluation. Results: The SVM classifier outperformed the LR and KNN classifiers with an average accuracy of 88.89%, sensitivity of 89%, and specificity of 88%. The integration of these five features from the wavelet domain of data, with three time domain features, stance time, swing time and maximum force strike at toe improved the PD diagnosis performance (approximately by 10%), which outperforms existing studies that are based on the same data set. Conclusion: with the previously published approaches, the proposed prediction methodology consisting of the multiscale features in combination with the time domain features shows better performance with fewer features, compared to the existing PD diagnostic techniques. Clinical impact: The findings suggest that the proposed diagnostic method involving multiscale (wavelet) features can improve the efficacy of PD diagnosis.https://ieeexplore.ieee.org/document/10114804/Wavelet transformself-similarityentropylevel-wise cross correlationclassificationParkinson's disease |
spellingShingle | Dixon Vimalajeewa Ethan McDonald Megan Tung Brani Vidakovic Parkinson’s Disease Diagnosis With Gait Characteristics Extracted Using Wavelet Transforms IEEE Journal of Translational Engineering in Health and Medicine Wavelet transform self-similarity entropy level-wise cross correlation classification Parkinson's disease |
title | Parkinson’s Disease Diagnosis With Gait Characteristics Extracted Using Wavelet Transforms |
title_full | Parkinson’s Disease Diagnosis With Gait Characteristics Extracted Using Wavelet Transforms |
title_fullStr | Parkinson’s Disease Diagnosis With Gait Characteristics Extracted Using Wavelet Transforms |
title_full_unstemmed | Parkinson’s Disease Diagnosis With Gait Characteristics Extracted Using Wavelet Transforms |
title_short | Parkinson’s Disease Diagnosis With Gait Characteristics Extracted Using Wavelet Transforms |
title_sort | parkinson x2019 s disease diagnosis with gait characteristics extracted using wavelet transforms |
topic | Wavelet transform self-similarity entropy level-wise cross correlation classification Parkinson's disease |
url | https://ieeexplore.ieee.org/document/10114804/ |
work_keys_str_mv | AT dixonvimalajeewa parkinsonx2019sdiseasediagnosiswithgaitcharacteristicsextractedusingwavelettransforms AT ethanmcdonald parkinsonx2019sdiseasediagnosiswithgaitcharacteristicsextractedusingwavelettransforms AT megantung parkinsonx2019sdiseasediagnosiswithgaitcharacteristicsextractedusingwavelettransforms AT branividakovic parkinsonx2019sdiseasediagnosiswithgaitcharacteristicsextractedusingwavelettransforms |