Abnormal functional resting-state networks in ADHD : graph theory and pattern recognition analysis of fMRI data
Autor(a) principal: | |
---|---|
Data de Publicação: | 2014 |
Outros Autores: | , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFRGS |
Texto Completo: | http://hdl.handle.net/10183/181637 |
Resumo: | The framework of graph theory provides useful tools for investigating the neural substrates of neuropsychiatric disorders. Graph description measures may be useful as predictor variables in classification procedures. Here, we consider several centrality measures as predictor features in a classification algorithm to identify nodes of resting-state networks containing predictive information that can discriminate between typical developing children and patients with attention-deficit/hyperactivity disorder (ADHD). The prediction was based on a support vector machines classifier. The analyses were performed in a multisite and publicly available resting-state fMRI dataset of healthy children and ADHD patients: the ADHD-200 database. Network centrality measures contained little predictive information for the discrimination between ADHD patients and healthy subjects. However, the classification between inattentive and combined ADHD subtypes was more promising, achieving accuracies higher than 65% (balance between sensitivity and specificity) in some sites. Finally, brain regions were ranked according to the amount of discriminant information and the most relevant were mapped. As hypothesized, we found that brain regions in motor, frontoparietal, and default mode networks contained the most predictive information. We concluded that the functional connectivity estimations are strongly dependent on the sample characteristics. Thus different acquisition protocols and clinical heterogeneity decrease the predictive values of the graph descriptors. |
id |
UFRGS-2_310b3569e8a545a19543aa8593731f28 |
---|---|
oai_identifier_str |
oai:www.lume.ufrgs.br:10183/181637 |
network_acronym_str |
UFRGS-2 |
network_name_str |
Repositório Institucional da UFRGS |
repository_id_str |
|
spelling |
Siqueira, Anderson dos SantosBiazoli Junior, Claudinei EduardoComfort, William EdgarRohde, Luis Augusto PaimSato, João Ricardo2018-09-05T02:29:00Z20142314-6141http://hdl.handle.net/10183/181637001074288The framework of graph theory provides useful tools for investigating the neural substrates of neuropsychiatric disorders. Graph description measures may be useful as predictor variables in classification procedures. Here, we consider several centrality measures as predictor features in a classification algorithm to identify nodes of resting-state networks containing predictive information that can discriminate between typical developing children and patients with attention-deficit/hyperactivity disorder (ADHD). The prediction was based on a support vector machines classifier. The analyses were performed in a multisite and publicly available resting-state fMRI dataset of healthy children and ADHD patients: the ADHD-200 database. Network centrality measures contained little predictive information for the discrimination between ADHD patients and healthy subjects. However, the classification between inattentive and combined ADHD subtypes was more promising, achieving accuracies higher than 65% (balance between sensitivity and specificity) in some sites. Finally, brain regions were ranked according to the amount of discriminant information and the most relevant were mapped. As hypothesized, we found that brain regions in motor, frontoparietal, and default mode networks contained the most predictive information. We concluded that the functional connectivity estimations are strongly dependent on the sample characteristics. Thus different acquisition protocols and clinical heterogeneity decrease the predictive values of the graph descriptors.application/pdfengBiomed research international. New York. Vol. 2014 (2014), 380531, 10 p.Transtorno do déficit de atenção com hiperatividadeReconhecimento automatizado de padrãoDescansoRede nervosaImagem por ressonância magnéticaAbnormal functional resting-state networks in ADHD : graph theory and pattern recognition analysis of fMRI dataEstrangeiroinfo:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UFRGSinstname:Universidade Federal do Rio Grande do Sul (UFRGS)instacron:UFRGSORIGINAL001074288.pdfTexto completo (inglês)application/pdf2902817http://www.lume.ufrgs.br/bitstream/10183/181637/1/001074288.pdf6042a1e458aa255e210c550b7354df8eMD51TEXT001074288.pdf.txt001074288.pdf.txtExtracted Texttext/plain40031http://www.lume.ufrgs.br/bitstream/10183/181637/2/001074288.pdf.txt23c6a033fa7712a5b3989b0ad2736330MD52THUMBNAIL001074288.pdf.jpg001074288.pdf.jpgGenerated Thumbnailimage/jpeg1804http://www.lume.ufrgs.br/bitstream/10183/181637/3/001074288.pdf.jpg0ececb43c4158e2384b96994a5c47418MD5310183/1816372018-10-05 07:46:20.385oai:www.lume.ufrgs.br:10183/181637Repositório de PublicaçõesPUBhttps://lume.ufrgs.br/oai/requestopendoar:2018-10-05T10:46:20Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS)false |
dc.title.pt_BR.fl_str_mv |
Abnormal functional resting-state networks in ADHD : graph theory and pattern recognition analysis of fMRI data |
title |
Abnormal functional resting-state networks in ADHD : graph theory and pattern recognition analysis of fMRI data |
spellingShingle |
Abnormal functional resting-state networks in ADHD : graph theory and pattern recognition analysis of fMRI data Siqueira, Anderson dos Santos Transtorno do déficit de atenção com hiperatividade Reconhecimento automatizado de padrão Descanso Rede nervosa Imagem por ressonância magnética |
title_short |
Abnormal functional resting-state networks in ADHD : graph theory and pattern recognition analysis of fMRI data |
title_full |
Abnormal functional resting-state networks in ADHD : graph theory and pattern recognition analysis of fMRI data |
title_fullStr |
Abnormal functional resting-state networks in ADHD : graph theory and pattern recognition analysis of fMRI data |
title_full_unstemmed |
Abnormal functional resting-state networks in ADHD : graph theory and pattern recognition analysis of fMRI data |
title_sort |
Abnormal functional resting-state networks in ADHD : graph theory and pattern recognition analysis of fMRI data |
author |
Siqueira, Anderson dos Santos |
author_facet |
Siqueira, Anderson dos Santos Biazoli Junior, Claudinei Eduardo Comfort, William Edgar Rohde, Luis Augusto Paim Sato, João Ricardo |
author_role |
author |
author2 |
Biazoli Junior, Claudinei Eduardo Comfort, William Edgar Rohde, Luis Augusto Paim Sato, João Ricardo |
author2_role |
author author author author |
dc.contributor.author.fl_str_mv |
Siqueira, Anderson dos Santos Biazoli Junior, Claudinei Eduardo Comfort, William Edgar Rohde, Luis Augusto Paim Sato, João Ricardo |
dc.subject.por.fl_str_mv |
Transtorno do déficit de atenção com hiperatividade Reconhecimento automatizado de padrão Descanso Rede nervosa Imagem por ressonância magnética |
topic |
Transtorno do déficit de atenção com hiperatividade Reconhecimento automatizado de padrão Descanso Rede nervosa Imagem por ressonância magnética |
description |
The framework of graph theory provides useful tools for investigating the neural substrates of neuropsychiatric disorders. Graph description measures may be useful as predictor variables in classification procedures. Here, we consider several centrality measures as predictor features in a classification algorithm to identify nodes of resting-state networks containing predictive information that can discriminate between typical developing children and patients with attention-deficit/hyperactivity disorder (ADHD). The prediction was based on a support vector machines classifier. The analyses were performed in a multisite and publicly available resting-state fMRI dataset of healthy children and ADHD patients: the ADHD-200 database. Network centrality measures contained little predictive information for the discrimination between ADHD patients and healthy subjects. However, the classification between inattentive and combined ADHD subtypes was more promising, achieving accuracies higher than 65% (balance between sensitivity and specificity) in some sites. Finally, brain regions were ranked according to the amount of discriminant information and the most relevant were mapped. As hypothesized, we found that brain regions in motor, frontoparietal, and default mode networks contained the most predictive information. We concluded that the functional connectivity estimations are strongly dependent on the sample characteristics. Thus different acquisition protocols and clinical heterogeneity decrease the predictive values of the graph descriptors. |
publishDate |
2014 |
dc.date.issued.fl_str_mv |
2014 |
dc.date.accessioned.fl_str_mv |
2018-09-05T02:29:00Z |
dc.type.driver.fl_str_mv |
Estrangeiro info:eu-repo/semantics/article |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10183/181637 |
dc.identifier.issn.pt_BR.fl_str_mv |
2314-6141 |
dc.identifier.nrb.pt_BR.fl_str_mv |
001074288 |
identifier_str_mv |
2314-6141 001074288 |
url |
http://hdl.handle.net/10183/181637 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.ispartof.pt_BR.fl_str_mv |
Biomed research international. New York. Vol. 2014 (2014), 380531, 10 p. |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFRGS instname:Universidade Federal do Rio Grande do Sul (UFRGS) instacron:UFRGS |
instname_str |
Universidade Federal do Rio Grande do Sul (UFRGS) |
instacron_str |
UFRGS |
institution |
UFRGS |
reponame_str |
Repositório Institucional da UFRGS |
collection |
Repositório Institucional da UFRGS |
bitstream.url.fl_str_mv |
http://www.lume.ufrgs.br/bitstream/10183/181637/1/001074288.pdf http://www.lume.ufrgs.br/bitstream/10183/181637/2/001074288.pdf.txt http://www.lume.ufrgs.br/bitstream/10183/181637/3/001074288.pdf.jpg |
bitstream.checksum.fl_str_mv |
6042a1e458aa255e210c550b7354df8e 23c6a033fa7712a5b3989b0ad2736330 0ececb43c4158e2384b96994a5c47418 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS) |
repository.mail.fl_str_mv |
|
_version_ |
1801224949768126464 |