Feature selection before EEG classification supports the diagnosis of Alzheimer's disease

Página do item simplificado
dc.citation.issue10
dc.citation.volume128
dc.contributor.authorTrambaiolli, L. R.
dc.contributor.authorSpolaor, N.
dc.contributor.authorLorena, A. C. [UNIFESP]
dc.contributor.authorAnghinah, R.
dc.contributor.authorSato, J. R.
dc.coverageClare
dc.date.accessioned2020-08-04T13:39:59Z
dc.date.available2020-08-04T13:39:59Z
dc.date.issued2017
dc.description.abstractObjective: In many decision support systems, some input features can be marginal or irrelevant to the diagnosis, while others can be redundant among each other. Thus, feature selection (FS) algorithms are often considered to find relevant/non-redundant features.& para;& para;Objective: This study aimed to evaluate the relevance of FS approaches applied to Alzheimer's Disease (AD) EEG-based diagnosis and compare the selected features with previous clinical findings.& para;& para;Methods: Eight different FS algorithms were applied to EEG spectral measures from 22 AD patients and 12 healthy age-matched controls. The FS contribution was evaluated by considering the leave-one-subject-out accuracy of Support Vector Machine classifiers built in the datasets described by the selected features.& para;& para;Results: The Filtered Subset Evaluator technique achieved the best performance improvement both on a per-patient basis (91.18% of accuracy) and on a per-epoch basis (85.29 +/- 21.62%), after removing 88.76 +/- 1.12% of the original features. All algorithms found out that alpha and beta bands are relevant features, which is in agreement with previous findings from the literature.& para;& para;Conclusion: Biologically plausible EEG datasets could achieve improved accuracies with pre-processing FS steps.& para;& para;Significance: The results suggest that the FS and classification techniques are an attractive complementary tool in order to reveal potential biomarkers aiding the AD clinical diagnosis. (C) 2017 Published by Elsevier Ireland Ltd on behalf of International Federation of Clinical Neurophysiology.en
dc.description.affiliationUniv Fed ABC, Ctr Math Comp & Cognit, Santo Andre, Brazil
dc.description.affiliationUniv Estadual Oeste Parana, Ctr Engn & Ciencias Exatas, Lab Bioinformat, Foz Do Iguacu, Brazil
dc.description.affiliationUniv Fed Sao Paulo, Inst Ciencia & Tecnol, Sao Jose Dos Campos, Brazil
dc.description.affiliationUniv Sao Paulo, Reference Ctr Cognit Disorders, Hosp Clin, Rua Arruda Alvim 206, Sao Paulo, Brazil
dc.description.affiliationUnifespUniv Fed Sao Paulo, Inst Ciencia & Tecnol, Sao Jose Dos Campos, Brazil
dc.description.sourceWeb of Science
dc.description.sponsorshipCoordenacao de Aperfeicoamento de Pessoal de Nivel Superior (CAPES)
dc.description.sponsorship"Universidade Federal do ABC" (UFABC)
dc.description.sponsorship"Conselho Nacional de Desenvolvimento Cientifico e Tecnologico" (CNPq)
dc.description.sponsorship"Fundacao de Amparo a Pesquisa do Estado de Sao Paulo" (FAPESP)
dc.description.sponsorshipIDFAPESP: 2013/10952-9
dc.description.sponsorshipIDFAPESP: 2013/10498-6
dc.description.sponsorshipIDFAPESP: 2013/00506-1
dc.description.sponsorshipIDFAPESP: 2012/22608-8
dc.format.extent2058-2067
dc.identifierhttp://dx.doi.org/10.1016/j.clinph.2017.06.251
dc.identifier.citationClinical Neurophysiology. Clare, v. 128, n. 10, p. 2058-2067, 2017.
dc.identifier.doi10.1016/j.clinph.2017.06.251
dc.identifier.issn1388-2457
dc.identifier.urihttps://repositorio.unifesp.br/handle/11600/57219
dc.identifier.wosWOS:000415787900032
dc.language.isoeng
dc.publisherElsevier Ireland Ltd
dc.relation.ispartofClinical Neurophysiology
dc.rightsinfo:eu-repo/semantics/restrictedAccess
dc.subjectFeature selectionen
dc.subjectDementiaen
dc.subjectAlzheimer's diseaseen
dc.subjectElectroencephalographyen
dc.subjectPattern recognitionen
dc.titleFeature selection before EEG classification supports the diagnosis of Alzheimer's diseaseen
dc.typeinfo:eu-repo/semantics/article
Arquivos
Coleções
ICT - Artigos