Machine learning models for Parkinson's disease detection and stage classification based on spatial-temporal gait parameters
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Outros Autores: | , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1016/j.gaitpost.2022.08.014 http://hdl.handle.net/11449/240709 |
Resumo: | Background: Parkinson's disease (PD) is a chronic and progressive neurodegenerative disease with no cure, presenting a challenging diagnosis and management. However, despite a significant number of criteria and guidelines have been proposed to improve the diagnosis of PD and to determine the PD stage, the gold standard for diagnosis and symptoms monitoring of PD is still mainly based on clinical evaluation, which includes several subjective factors. The use of machine learning (ML) algorithms in spatial-temporal gait parameters is an interesting advance with easy interpretation and objective factors that may assist in PD diagnostic and follow up. Research question: This article studies ML algorithms for: i) distinguish people with PD vs. matched-healthy individuals; and ii) to discriminate PD stages, based on selected spatial-temporal parameters, including variability and asymmetry. Methods: Gait data acquired from 63 people with PD with different levels of PD motor symptoms severity, and 63 matched-control group individuals, during self-selected walking speed, was study in the experiments. Results: In the PD diagnosis, a classification accuracy of 84.6 %, with a precision of 0.923 and a recall of 0.800, was achieved by the Naïve Bayes algorithm. We found four significant gait features in PD diagnosis: step length, velocity and width, and step width variability. As to the PD stage identification, the Random Forest outperformed the other studied ML algorithms, by reaching an Area Under the ROC curve of 0.786. We found two relevant gait features in identifying the PD stage: stride width variability and step double support time variability. Significance: The results showed that the studied ML algorithms have potential both to PD diagnosis and stage identification by analysing gait parameters. |
id |
UNSP_96278724fff8733f1ff9e6a8c55aa014 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/240709 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Machine learning models for Parkinson's disease detection and stage classification based on spatial-temporal gait parametersAlgorithmArtificial intelligenceClassificationFeature selectionParkinson's diseaseProgressionBackground: Parkinson's disease (PD) is a chronic and progressive neurodegenerative disease with no cure, presenting a challenging diagnosis and management. However, despite a significant number of criteria and guidelines have been proposed to improve the diagnosis of PD and to determine the PD stage, the gold standard for diagnosis and symptoms monitoring of PD is still mainly based on clinical evaluation, which includes several subjective factors. The use of machine learning (ML) algorithms in spatial-temporal gait parameters is an interesting advance with easy interpretation and objective factors that may assist in PD diagnostic and follow up. Research question: This article studies ML algorithms for: i) distinguish people with PD vs. matched-healthy individuals; and ii) to discriminate PD stages, based on selected spatial-temporal parameters, including variability and asymmetry. Methods: Gait data acquired from 63 people with PD with different levels of PD motor symptoms severity, and 63 matched-control group individuals, during self-selected walking speed, was study in the experiments. Results: In the PD diagnosis, a classification accuracy of 84.6 %, with a precision of 0.923 and a recall of 0.800, was achieved by the Naïve Bayes algorithm. We found four significant gait features in PD diagnosis: step length, velocity and width, and step width variability. As to the PD stage identification, the Random Forest outperformed the other studied ML algorithms, by reaching an Area Under the ROC curve of 0.786. We found two relevant gait features in identifying the PD stage: stride width variability and step double support time variability. Significance: The results showed that the studied ML algorithms have potential both to PD diagnosis and stage identification by analysing gait parameters.Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)Faculdade de Engenharia Universidade do PortoSão Paulo State University (Unesp) Department of Physical Education Human Movement Research Laboratory (MOVI-LAB)Instituto de Ciência e Inovação em Engenharia Mecânica e Engenharia Industrial Departamento de Engenharia Mecânica Faculdade de Engenharia Universidade do PortoSão Paulo State University (Unesp) Department of Physical Education Human Movement Research Laboratory (MOVI-LAB)FAPESP: #14/20549-0FAPESP: #17/19516-8FAPESP: #20/01250-4CAPES: 001Universidade do PortoUniversidade Estadual Paulista (UNESP)Ferreira, Marta Isabel A.S.NBarbieri, Fabio AugustoMoreno, Vinícius Christianini [UNESP]Penedo, Tiago [UNESP]Tavares, João Manuel R.S.2023-03-01T20:29:30Z2023-03-01T20:29:30Z2022-10-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article49-55http://dx.doi.org/10.1016/j.gaitpost.2022.08.014Gait and Posture, v. 98, p. 49-55.1879-22190966-6362http://hdl.handle.net/11449/24070910.1016/j.gaitpost.2022.08.0142-s2.0-85136686469Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengGait and Postureinfo:eu-repo/semantics/openAccess2023-03-01T20:29:30Zoai:repositorio.unesp.br:11449/240709Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462023-03-01T20:29:30Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Machine learning models for Parkinson's disease detection and stage classification based on spatial-temporal gait parameters |
title |
Machine learning models for Parkinson's disease detection and stage classification based on spatial-temporal gait parameters |
spellingShingle |
Machine learning models for Parkinson's disease detection and stage classification based on spatial-temporal gait parameters Ferreira, Marta Isabel A.S.N Algorithm Artificial intelligence Classification Feature selection Parkinson's disease Progression |
title_short |
Machine learning models for Parkinson's disease detection and stage classification based on spatial-temporal gait parameters |
title_full |
Machine learning models for Parkinson's disease detection and stage classification based on spatial-temporal gait parameters |
title_fullStr |
Machine learning models for Parkinson's disease detection and stage classification based on spatial-temporal gait parameters |
title_full_unstemmed |
Machine learning models for Parkinson's disease detection and stage classification based on spatial-temporal gait parameters |
title_sort |
Machine learning models for Parkinson's disease detection and stage classification based on spatial-temporal gait parameters |
author |
Ferreira, Marta Isabel A.S.N |
author_facet |
Ferreira, Marta Isabel A.S.N Barbieri, Fabio Augusto Moreno, Vinícius Christianini [UNESP] Penedo, Tiago [UNESP] Tavares, João Manuel R.S. |
author_role |
author |
author2 |
Barbieri, Fabio Augusto Moreno, Vinícius Christianini [UNESP] Penedo, Tiago [UNESP] Tavares, João Manuel R.S. |
author2_role |
author author author author |
dc.contributor.none.fl_str_mv |
Universidade do Porto Universidade Estadual Paulista (UNESP) |
dc.contributor.author.fl_str_mv |
Ferreira, Marta Isabel A.S.N Barbieri, Fabio Augusto Moreno, Vinícius Christianini [UNESP] Penedo, Tiago [UNESP] Tavares, João Manuel R.S. |
dc.subject.por.fl_str_mv |
Algorithm Artificial intelligence Classification Feature selection Parkinson's disease Progression |
topic |
Algorithm Artificial intelligence Classification Feature selection Parkinson's disease Progression |
description |
Background: Parkinson's disease (PD) is a chronic and progressive neurodegenerative disease with no cure, presenting a challenging diagnosis and management. However, despite a significant number of criteria and guidelines have been proposed to improve the diagnosis of PD and to determine the PD stage, the gold standard for diagnosis and symptoms monitoring of PD is still mainly based on clinical evaluation, which includes several subjective factors. The use of machine learning (ML) algorithms in spatial-temporal gait parameters is an interesting advance with easy interpretation and objective factors that may assist in PD diagnostic and follow up. Research question: This article studies ML algorithms for: i) distinguish people with PD vs. matched-healthy individuals; and ii) to discriminate PD stages, based on selected spatial-temporal parameters, including variability and asymmetry. Methods: Gait data acquired from 63 people with PD with different levels of PD motor symptoms severity, and 63 matched-control group individuals, during self-selected walking speed, was study in the experiments. Results: In the PD diagnosis, a classification accuracy of 84.6 %, with a precision of 0.923 and a recall of 0.800, was achieved by the Naïve Bayes algorithm. We found four significant gait features in PD diagnosis: step length, velocity and width, and step width variability. As to the PD stage identification, the Random Forest outperformed the other studied ML algorithms, by reaching an Area Under the ROC curve of 0.786. We found two relevant gait features in identifying the PD stage: stride width variability and step double support time variability. Significance: The results showed that the studied ML algorithms have potential both to PD diagnosis and stage identification by analysing gait parameters. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-10-01 2023-03-01T20:29:30Z 2023-03-01T20:29:30Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.1016/j.gaitpost.2022.08.014 Gait and Posture, v. 98, p. 49-55. 1879-2219 0966-6362 http://hdl.handle.net/11449/240709 10.1016/j.gaitpost.2022.08.014 2-s2.0-85136686469 |
url |
http://dx.doi.org/10.1016/j.gaitpost.2022.08.014 http://hdl.handle.net/11449/240709 |
identifier_str_mv |
Gait and Posture, v. 98, p. 49-55. 1879-2219 0966-6362 10.1016/j.gaitpost.2022.08.014 2-s2.0-85136686469 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Gait and Posture |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
49-55 |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1797790419269976064 |