Dynamic brain fluctuations outperform connectivity measures and mirror pathophysiological profiles across dementia subtypes: a multicenter study

Autores
Moguilner, Sebastian Gabriel; García, Adolfo Martín; Sanz Perl Hernandez, Yonatan; Tagliazucchi, Enzo Rodolfo; Piguet, Olivier; Kumfor, Fiona; Reyes, Pablo; Matallana, Diana; Sedeño, Lucas; Ibañez, Agustin Mariano
Año de publicación
2021
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
From molecular mechanisms to global brain networks, atypical fluctuations are the hallmark of neurodegeneration. Yet, traditional fMRI research on resting-state networks (RSNs) has favored static and average connectivity methods, which by overlooking the fluctuation dynamics triggered by neurodegeneration, have yielded inconsistent results. The present multicenter study introduces a data-driven machine learning pipeline based on dynamic connectivity fluctuation analysis (DCFA) on RS-fMRI data from 300 participants belonging to three groups: behavioral variant frontotemporal dementia (bvFTD) patients, Alzheimer's disease (AD) patients, and healthy controls. We considered non-linear oscillatory patterns across combined and individual resting-state networks (RSNs), namely: the salience network (SN), mostly affected in bvFTD; the default mode network (DMN), mostly affected in AD; the executive network (EN), partially compromised in both conditions; the motor network (MN); and the visual network (VN). These RSNs were entered as features for dementia classification using a recent robust machine learning approach (a Bayesian hyperparameter tuned Gradient Boosting Machines (GBM) algorithm), across four independent datasets with different MR scanners and recording parameters. The machine learning classification accuracy analysis revealed a systematic and unique tailored architecture of RSN disruption. The classification accuracy ranking showed that the most affected networks for bvFTD were the SN + EN network pair (mean accuracy = 86.43%, AUC = 0.91, sensitivity = 86.45%, specificity = 87.54%); for AD, the DMN + EN network pair (mean accuracy = 86.63%, AUC = 0.89, sensitivity = 88.37%, specificity = 84.62%); and for the bvFTD vs. AD classification, the DMN + SN network pair (mean accuracy = 82.67%, AUC = 0.86, sensitivity = 81.27%, specificity = 83.01%). Moreover, the DFCA classification systematically outperformed canonical connectivity approaches (including both static and linear dynamic connectivity). Our findings suggest that non-linear dynamical fluctuations surpass two traditional seed-based functional connectivity approaches and provide a pathophysiological characterization of global brain networks in neurodegenerative conditions (AD and bvFTD) across multicenter data.
Fil: Moguilner, Sebastian Gabriel. University of California; Estados Unidos. Trinity College; Irlanda. Fundación Escuela de Medicina Nuclear; Argentina. Comisión Nacional de Energía Atómica; Argentina
Fil: García, Adolfo Martín. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. University of California; Estados Unidos. Trinity College; Irlanda. Universidad de San Andrés; Argentina. Universidad Catolica de Cuyo. Facultad de Educacion.; Argentina
Fil: Sanz Perl Hernandez, Yonatan. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad de San Andrés; Argentina. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Física; Argentina
Fil: Tagliazucchi, Enzo Rodolfo. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Física; Argentina
Fil: Piguet, Olivier. The University Of Sydney; Australia
Fil: Kumfor, Fiona. The University Of Sydney; Australia
Fil: Reyes, Pablo. Pontificia Universidad Javeriana; Colombia. Hospital Universitario Fundación Santa Fe; Colombia. Hospital Universitario San Ignacio; Colombia
Fil: Matallana, Diana. Pontificia Universidad Javeriana; Colombia. Hospital Universitario Fundación Santa Fe; Colombia. Hospital Universitario San Ignacio; Colombia
Fil: Sedeño, Lucas. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Houssay. Instituto de Neurociencias Cognitivas y Traslacional; Argentina
Fil: Ibañez, Agustin Mariano. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. University of California; Estados Unidos. Trinity College; Irlanda. Universidad de San Andrés; Argentina. Universidad Autónoma del Caribe; Colombia. Universidad Adolfo Ibañez; Chile
Materia
AD
BVFTD
COPULA-BASED DEPENDENCE MEASURE
DYNAMIC FUNCTIONAL CONNECTIVITY
FMRI RESTING-STATE CONNECTIVITY
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-nd/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/166278
Acceder
id CONICETDig_6ae2c3e1eda5bee97812e8dfce3dc17c
oai_identifier_str oai:ri.conicet.gov.ar:11336/166278
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Dynamic brain fluctuations outperform connectivity measures and mirror pathophysiological profiles across dementia subtypes: a multicenter studyMoguilner, Sebastian GabrielGarcía, Adolfo MartínSanz Perl Hernandez, YonatanTagliazucchi, Enzo RodolfoPiguet, OlivierKumfor, FionaReyes, PabloMatallana, DianaSedeño, LucasIbañez, Agustin MarianoADBVFTDCOPULA-BASED DEPENDENCE MEASUREDYNAMIC FUNCTIONAL CONNECTIVITYFMRI RESTING-STATE CONNECTIVITYhttps://purl.org/becyt/ford/5.1https://purl.org/becyt/ford/5From molecular mechanisms to global brain networks, atypical fluctuations are the hallmark of neurodegeneration. Yet, traditional fMRI research on resting-state networks (RSNs) has favored static and average connectivity methods, which by overlooking the fluctuation dynamics triggered by neurodegeneration, have yielded inconsistent results. The present multicenter study introduces a data-driven machine learning pipeline based on dynamic connectivity fluctuation analysis (DCFA) on RS-fMRI data from 300 participants belonging to three groups: behavioral variant frontotemporal dementia (bvFTD) patients, Alzheimer's disease (AD) patients, and healthy controls. We considered non-linear oscillatory patterns across combined and individual resting-state networks (RSNs), namely: the salience network (SN), mostly affected in bvFTD; the default mode network (DMN), mostly affected in AD; the executive network (EN), partially compromised in both conditions; the motor network (MN); and the visual network (VN). These RSNs were entered as features for dementia classification using a recent robust machine learning approach (a Bayesian hyperparameter tuned Gradient Boosting Machines (GBM) algorithm), across four independent datasets with different MR scanners and recording parameters. The machine learning classification accuracy analysis revealed a systematic and unique tailored architecture of RSN disruption. The classification accuracy ranking showed that the most affected networks for bvFTD were the SN + EN network pair (mean accuracy = 86.43%, AUC = 0.91, sensitivity = 86.45%, specificity = 87.54%); for AD, the DMN + EN network pair (mean accuracy = 86.63%, AUC = 0.89, sensitivity = 88.37%, specificity = 84.62%); and for the bvFTD vs. AD classification, the DMN + SN network pair (mean accuracy = 82.67%, AUC = 0.86, sensitivity = 81.27%, specificity = 83.01%). Moreover, the DFCA classification systematically outperformed canonical connectivity approaches (including both static and linear dynamic connectivity). Our findings suggest that non-linear dynamical fluctuations surpass two traditional seed-based functional connectivity approaches and provide a pathophysiological characterization of global brain networks in neurodegenerative conditions (AD and bvFTD) across multicenter data.Fil: Moguilner, Sebastian Gabriel. University of California; Estados Unidos. Trinity College; Irlanda. Fundación Escuela de Medicina Nuclear; Argentina. Comisión Nacional de Energía Atómica; ArgentinaFil: García, Adolfo Martín. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. University of California; Estados Unidos. Trinity College; Irlanda. Universidad de San Andrés; Argentina. Universidad Catolica de Cuyo. Facultad de Educacion.; ArgentinaFil: Sanz Perl Hernandez, Yonatan. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad de San Andrés; Argentina. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Física; ArgentinaFil: Tagliazucchi, Enzo Rodolfo. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Física; ArgentinaFil: Piguet, Olivier. The University Of Sydney; AustraliaFil: Kumfor, Fiona. The University Of Sydney; AustraliaFil: Reyes, Pablo. Pontificia Universidad Javeriana; Colombia. Hospital Universitario Fundación Santa Fe; Colombia. Hospital Universitario San Ignacio; ColombiaFil: Matallana, Diana. Pontificia Universidad Javeriana; Colombia. Hospital Universitario Fundación Santa Fe; Colombia. Hospital Universitario San Ignacio; ColombiaFil: Sedeño, Lucas. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Houssay. Instituto de Neurociencias Cognitivas y Traslacional; ArgentinaFil: Ibañez, Agustin Mariano. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. University of California; Estados Unidos. Trinity College; Irlanda. Universidad de San Andrés; Argentina. Universidad Autónoma del Caribe; Colombia. Universidad Adolfo Ibañez; ChileElsevier2021-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfapplication/pdfapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/166278Moguilner, Sebastian Gabriel; García, Adolfo Martín; Sanz Perl Hernandez, Yonatan; Tagliazucchi, Enzo Rodolfo; Piguet, Olivier; et al.; Dynamic brain fluctuations outperform connectivity measures and mirror pathophysiological profiles across dementia subtypes: a multicenter study; Elsevier; Journal Neuroimag; 225; 1-2021; 1-121053-8119CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://www.sciencedirect.com/science/article/pii/S1053811920310077info:eu-repo/semantics/altIdentifier/doi/10.1016/j.neuroimage.2020.117522info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-nd/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-10-22T11:09:47Zoai:ri.conicet.gov.ar:11336/166278instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-10-22 11:09:48.283CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Dynamic brain fluctuations outperform connectivity measures and mirror pathophysiological profiles across dementia subtypes: a multicenter study
title Dynamic brain fluctuations outperform connectivity measures and mirror pathophysiological profiles across dementia subtypes: a multicenter study
spellingShingle Dynamic brain fluctuations outperform connectivity measures and mirror pathophysiological profiles across dementia subtypes: a multicenter study
Moguilner, Sebastian Gabriel
AD
BVFTD
COPULA-BASED DEPENDENCE MEASURE
DYNAMIC FUNCTIONAL CONNECTIVITY
FMRI RESTING-STATE CONNECTIVITY
title_short Dynamic brain fluctuations outperform connectivity measures and mirror pathophysiological profiles across dementia subtypes: a multicenter study
title_full Dynamic brain fluctuations outperform connectivity measures and mirror pathophysiological profiles across dementia subtypes: a multicenter study
title_fullStr Dynamic brain fluctuations outperform connectivity measures and mirror pathophysiological profiles across dementia subtypes: a multicenter study
title_full_unstemmed Dynamic brain fluctuations outperform connectivity measures and mirror pathophysiological profiles across dementia subtypes: a multicenter study
title_sort Dynamic brain fluctuations outperform connectivity measures and mirror pathophysiological profiles across dementia subtypes: a multicenter study
dc.creator.none.fl_str_mv Moguilner, Sebastian Gabriel
García, Adolfo Martín
Sanz Perl Hernandez, Yonatan
Tagliazucchi, Enzo Rodolfo
Piguet, Olivier
Kumfor, Fiona
Reyes, Pablo
Matallana, Diana
Sedeño, Lucas
Ibañez, Agustin Mariano
author Moguilner, Sebastian Gabriel
author_facet Moguilner, Sebastian Gabriel
García, Adolfo Martín
Sanz Perl Hernandez, Yonatan
Tagliazucchi, Enzo Rodolfo
Piguet, Olivier
Kumfor, Fiona
Reyes, Pablo
Matallana, Diana
Sedeño, Lucas
Ibañez, Agustin Mariano
author_role author
author2 García, Adolfo Martín
Sanz Perl Hernandez, Yonatan
Tagliazucchi, Enzo Rodolfo
Piguet, Olivier
Kumfor, Fiona
Reyes, Pablo
Matallana, Diana
Sedeño, Lucas
Ibañez, Agustin Mariano
author2_role author
author
author
author
author
author
author
author
author
dc.subject.none.fl_str_mv AD
BVFTD
COPULA-BASED DEPENDENCE MEASURE
DYNAMIC FUNCTIONAL CONNECTIVITY
FMRI RESTING-STATE CONNECTIVITY
topic AD
BVFTD
COPULA-BASED DEPENDENCE MEASURE
DYNAMIC FUNCTIONAL CONNECTIVITY
FMRI RESTING-STATE CONNECTIVITY
purl_subject.fl_str_mv https://purl.org/becyt/ford/5.1
https://purl.org/becyt/ford/5
dc.description.none.fl_txt_mv From molecular mechanisms to global brain networks, atypical fluctuations are the hallmark of neurodegeneration. Yet, traditional fMRI research on resting-state networks (RSNs) has favored static and average connectivity methods, which by overlooking the fluctuation dynamics triggered by neurodegeneration, have yielded inconsistent results. The present multicenter study introduces a data-driven machine learning pipeline based on dynamic connectivity fluctuation analysis (DCFA) on RS-fMRI data from 300 participants belonging to three groups: behavioral variant frontotemporal dementia (bvFTD) patients, Alzheimer's disease (AD) patients, and healthy controls. We considered non-linear oscillatory patterns across combined and individual resting-state networks (RSNs), namely: the salience network (SN), mostly affected in bvFTD; the default mode network (DMN), mostly affected in AD; the executive network (EN), partially compromised in both conditions; the motor network (MN); and the visual network (VN). These RSNs were entered as features for dementia classification using a recent robust machine learning approach (a Bayesian hyperparameter tuned Gradient Boosting Machines (GBM) algorithm), across four independent datasets with different MR scanners and recording parameters. The machine learning classification accuracy analysis revealed a systematic and unique tailored architecture of RSN disruption. The classification accuracy ranking showed that the most affected networks for bvFTD were the SN + EN network pair (mean accuracy = 86.43%, AUC = 0.91, sensitivity = 86.45%, specificity = 87.54%); for AD, the DMN + EN network pair (mean accuracy = 86.63%, AUC = 0.89, sensitivity = 88.37%, specificity = 84.62%); and for the bvFTD vs. AD classification, the DMN + SN network pair (mean accuracy = 82.67%, AUC = 0.86, sensitivity = 81.27%, specificity = 83.01%). Moreover, the DFCA classification systematically outperformed canonical connectivity approaches (including both static and linear dynamic connectivity). Our findings suggest that non-linear dynamical fluctuations surpass two traditional seed-based functional connectivity approaches and provide a pathophysiological characterization of global brain networks in neurodegenerative conditions (AD and bvFTD) across multicenter data.
Fil: Moguilner, Sebastian Gabriel. University of California; Estados Unidos. Trinity College; Irlanda. Fundación Escuela de Medicina Nuclear; Argentina. Comisión Nacional de Energía Atómica; Argentina
Fil: García, Adolfo Martín. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. University of California; Estados Unidos. Trinity College; Irlanda. Universidad de San Andrés; Argentina. Universidad Catolica de Cuyo. Facultad de Educacion.; Argentina
Fil: Sanz Perl Hernandez, Yonatan. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad de San Andrés; Argentina. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Física; Argentina
Fil: Tagliazucchi, Enzo Rodolfo. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Física; Argentina
Fil: Piguet, Olivier. The University Of Sydney; Australia
Fil: Kumfor, Fiona. The University Of Sydney; Australia
Fil: Reyes, Pablo. Pontificia Universidad Javeriana; Colombia. Hospital Universitario Fundación Santa Fe; Colombia. Hospital Universitario San Ignacio; Colombia
Fil: Matallana, Diana. Pontificia Universidad Javeriana; Colombia. Hospital Universitario Fundación Santa Fe; Colombia. Hospital Universitario San Ignacio; Colombia
Fil: Sedeño, Lucas. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Houssay. Instituto de Neurociencias Cognitivas y Traslacional; Argentina
Fil: Ibañez, Agustin Mariano. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. University of California; Estados Unidos. Trinity College; Irlanda. Universidad de San Andrés; Argentina. Universidad Autónoma del Caribe; Colombia. Universidad Adolfo Ibañez; Chile
description From molecular mechanisms to global brain networks, atypical fluctuations are the hallmark of neurodegeneration. Yet, traditional fMRI research on resting-state networks (RSNs) has favored static and average connectivity methods, which by overlooking the fluctuation dynamics triggered by neurodegeneration, have yielded inconsistent results. The present multicenter study introduces a data-driven machine learning pipeline based on dynamic connectivity fluctuation analysis (DCFA) on RS-fMRI data from 300 participants belonging to three groups: behavioral variant frontotemporal dementia (bvFTD) patients, Alzheimer's disease (AD) patients, and healthy controls. We considered non-linear oscillatory patterns across combined and individual resting-state networks (RSNs), namely: the salience network (SN), mostly affected in bvFTD; the default mode network (DMN), mostly affected in AD; the executive network (EN), partially compromised in both conditions; the motor network (MN); and the visual network (VN). These RSNs were entered as features for dementia classification using a recent robust machine learning approach (a Bayesian hyperparameter tuned Gradient Boosting Machines (GBM) algorithm), across four independent datasets with different MR scanners and recording parameters. The machine learning classification accuracy analysis revealed a systematic and unique tailored architecture of RSN disruption. The classification accuracy ranking showed that the most affected networks for bvFTD were the SN + EN network pair (mean accuracy = 86.43%, AUC = 0.91, sensitivity = 86.45%, specificity = 87.54%); for AD, the DMN + EN network pair (mean accuracy = 86.63%, AUC = 0.89, sensitivity = 88.37%, specificity = 84.62%); and for the bvFTD vs. AD classification, the DMN + SN network pair (mean accuracy = 82.67%, AUC = 0.86, sensitivity = 81.27%, specificity = 83.01%). Moreover, the DFCA classification systematically outperformed canonical connectivity approaches (including both static and linear dynamic connectivity). Our findings suggest that non-linear dynamical fluctuations surpass two traditional seed-based functional connectivity approaches and provide a pathophysiological characterization of global brain networks in neurodegenerative conditions (AD and bvFTD) across multicenter data.
publishDate 2021
dc.date.none.fl_str_mv 2021-01
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/166278
Moguilner, Sebastian Gabriel; García, Adolfo Martín; Sanz Perl Hernandez, Yonatan; Tagliazucchi, Enzo Rodolfo; Piguet, Olivier; et al.; Dynamic brain fluctuations outperform connectivity measures and mirror pathophysiological profiles across dementia subtypes: a multicenter study; Elsevier; Journal Neuroimag; 225; 1-2021; 1-12
1053-8119
CONICET Digital
CONICET
url http://hdl.handle.net/11336/166278
identifier_str_mv Moguilner, Sebastian Gabriel; García, Adolfo Martín; Sanz Perl Hernandez, Yonatan; Tagliazucchi, Enzo Rodolfo; Piguet, Olivier; et al.; Dynamic brain fluctuations outperform connectivity measures and mirror pathophysiological profiles across dementia subtypes: a multicenter study; Elsevier; Journal Neuroimag; 225; 1-2021; 1-12
1053-8119
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://www.sciencedirect.com/science/article/pii/S1053811920310077
info:eu-repo/semantics/altIdentifier/doi/10.1016/j.neuroimage.2020.117522
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-nd/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-nd/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
application/pdf
application/pdf
application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1846781450083368960
score 12.982451

Publicaciones similares