No Cover Image

Working paper 762 views 15 downloads

Improved classification of Alzheimer’s disease and mild cognitive impairment through dynamic functional network analysis

Nicolás Rubido, Venia Batziou, Marwan Fuad, Vesna Vuksanovic Orcid Logo

arXiv

Swansea University Authors: Venia Batziou, Vesna Vuksanovic Orcid Logo

DOI (Published version): 10.48550/arXiv.2505.03458

Abstract

Brain network analysis using functional MRI has advanced our understanding of cortical activity and its disruption in neurodegenerative disorders underlying dementia. Recently, research has focused on dynamic (time-varying) brain networks that capture both spatial and temporal patterns of regional c...

Full description

Published in: arXiv
Published:
URI: https://cronfa.swan.ac.uk/Record/cronfa69526
first_indexed 2025-05-16T09:52:23Z
last_indexed 2026-05-01T07:15:21Z
id cronfa69526
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2026-04-30T15:38:39.0488038</datestamp><bib-version>v2</bib-version><id>69526</id><entry>2025-05-16</entry><title>Improved classification of Alzheimer&#x2019;s disease and mild cognitive impairment through dynamic functional network analysis</title><swanseaauthors><author><sid>35a4b3e1c71f435e8dfdf2a35f442eaa</sid><ORCID/><firstname>Venia</firstname><surname>Batziou</surname><name>Venia Batziou</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>a1a6e2bd0b6ee99f648abb6201dea474</sid><ORCID>0000-0003-4655-698X</ORCID><firstname>Vesna</firstname><surname>Vuksanovic</surname><name>Vesna Vuksanovic</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2025-05-16</date><abstract>Brain network analysis using functional MRI has advanced our understanding of cortical activity and its disruption in neurodegenerative disorders underlying dementia. Recently, research has focused on dynamic (time-varying) brain networks that capture both spatial and temporal patterns of regional cortical co-activity. However, this approach remains relatively unexplored across the Alzheimer&#x2019;s disease (AD) spectrum. In this study, we analysed age- and sex-matched static and dynamic functional brain networks derived from resting-state fMRI data in 315 individuals with AD, mild cognitive impairment (MCI), and cognitively normal healthy controls (HC) from the ADNI-3 cohort. Functionalnetworks were constructed using the Juelich brain atlas, with static connectivity estimated from full time series and dynamic connectivity derived using a sliding-window approach. Group differences were assessed at both the link and node levels using non-parametric statistics and bootstrap resampling. While HC and MCI show similar static and dynamic patterns at the node level, clearer differences emerge in AD. We identified stable (stationary) differences in functional connectivity between white matter regions and parietal and somatosensory cortices, whereas temporally varying differences wereconsistently observed in connections involving the amygdala and hippocampal formation. In addition, node centrality analysis suggested that white matter connectivity differences are predominantly local in nature. Our results highlight shared and unique functional connectivity patterns in both static and dynamic functional networks, emphasising the importance of incorporating dynamic information into brain network analyses of the Alzheimer&#x2019;s spectrum. Furthermore, we trained a Random Forest model on regional BOLD time series informed by dynamic and static network metrics, achieving robust classification of MCI, AD, and HC groups and demonstrating the diagnostic potential of time-varying connectivity.</abstract><type>Working paper</type><journal>arXiv</journal><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher/><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic/><keywords/><publishedDay>0</publishedDay><publishedMonth>0</publishedMonth><publishedYear>0</publishedYear><publishedDate>0001-01-01</publishedDate><doi>10.48550/arXiv.2505.03458</doi><url/><notes>Preprint article before certification by peer review.</notes><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><apcterm/><funders/><projectreference/><lastEdited>2026-04-30T15:38:39.0488038</lastEdited><Created>2025-05-16T10:50:20.4610432</Created><path><level id="1">Faculty of Medicine, Health and Life Sciences</level><level id="2">Swansea University Medical School - Health Data Science</level></path><authors><author><firstname>Nicol&#xE1;s</firstname><surname>Rubido</surname><order>1</order></author><author><firstname>Venia</firstname><surname>Batziou</surname><orcid/><order>2</order></author><author><firstname>Marwan</firstname><surname>Fuad</surname><order>3</order></author><author><firstname>Vesna</firstname><surname>Vuksanovic</surname><orcid>0000-0003-4655-698X</orcid><order>4</order></author></authors><documents><document><filename>69526__36653__31dabb28830b410d873a6f0503b82d0e.pdf</filename><originalFilename>ArXiv_April26_vv.pdf</originalFilename><uploaded>2026-04-30T15:26:58.5258153</uploaded><type>Output</type><contentLength>9378425</contentLength><contentType>application/pdf</contentType><version>Pre-print</version><cronfaStatus>true</cronfaStatus><copyrightCorrect>false</copyrightCorrect></document></documents><OutputDurs/></rfc1807>
spelling 2026-04-30T15:38:39.0488038 v2 69526 2025-05-16 Improved classification of Alzheimer’s disease and mild cognitive impairment through dynamic functional network analysis 35a4b3e1c71f435e8dfdf2a35f442eaa Venia Batziou Venia Batziou true false a1a6e2bd0b6ee99f648abb6201dea474 0000-0003-4655-698X Vesna Vuksanovic Vesna Vuksanovic true false 2025-05-16 Brain network analysis using functional MRI has advanced our understanding of cortical activity and its disruption in neurodegenerative disorders underlying dementia. Recently, research has focused on dynamic (time-varying) brain networks that capture both spatial and temporal patterns of regional cortical co-activity. However, this approach remains relatively unexplored across the Alzheimer’s disease (AD) spectrum. In this study, we analysed age- and sex-matched static and dynamic functional brain networks derived from resting-state fMRI data in 315 individuals with AD, mild cognitive impairment (MCI), and cognitively normal healthy controls (HC) from the ADNI-3 cohort. Functionalnetworks were constructed using the Juelich brain atlas, with static connectivity estimated from full time series and dynamic connectivity derived using a sliding-window approach. Group differences were assessed at both the link and node levels using non-parametric statistics and bootstrap resampling. While HC and MCI show similar static and dynamic patterns at the node level, clearer differences emerge in AD. We identified stable (stationary) differences in functional connectivity between white matter regions and parietal and somatosensory cortices, whereas temporally varying differences wereconsistently observed in connections involving the amygdala and hippocampal formation. In addition, node centrality analysis suggested that white matter connectivity differences are predominantly local in nature. Our results highlight shared and unique functional connectivity patterns in both static and dynamic functional networks, emphasising the importance of incorporating dynamic information into brain network analyses of the Alzheimer’s spectrum. Furthermore, we trained a Random Forest model on regional BOLD time series informed by dynamic and static network metrics, achieving robust classification of MCI, AD, and HC groups and demonstrating the diagnostic potential of time-varying connectivity. Working paper arXiv 0 0 0 0001-01-01 10.48550/arXiv.2505.03458 Preprint article before certification by peer review. COLLEGE NANME COLLEGE CODE Swansea University 2026-04-30T15:38:39.0488038 2025-05-16T10:50:20.4610432 Faculty of Medicine, Health and Life Sciences Swansea University Medical School - Health Data Science Nicolás Rubido 1 Venia Batziou 2 Marwan Fuad 3 Vesna Vuksanovic 0000-0003-4655-698X 4 69526__36653__31dabb28830b410d873a6f0503b82d0e.pdf ArXiv_April26_vv.pdf 2026-04-30T15:26:58.5258153 Output 9378425 application/pdf Pre-print true false
title Improved classification of Alzheimer’s disease and mild cognitive impairment through dynamic functional network analysis
spellingShingle Improved classification of Alzheimer’s disease and mild cognitive impairment through dynamic functional network analysis
Venia Batziou
Vesna Vuksanovic
title_short Improved classification of Alzheimer’s disease and mild cognitive impairment through dynamic functional network analysis
title_full Improved classification of Alzheimer’s disease and mild cognitive impairment through dynamic functional network analysis
title_fullStr Improved classification of Alzheimer’s disease and mild cognitive impairment through dynamic functional network analysis
title_full_unstemmed Improved classification of Alzheimer’s disease and mild cognitive impairment through dynamic functional network analysis
title_sort Improved classification of Alzheimer’s disease and mild cognitive impairment through dynamic functional network analysis
author_id_str_mv 35a4b3e1c71f435e8dfdf2a35f442eaa
a1a6e2bd0b6ee99f648abb6201dea474
author_id_fullname_str_mv 35a4b3e1c71f435e8dfdf2a35f442eaa_***_Venia Batziou
a1a6e2bd0b6ee99f648abb6201dea474_***_Vesna Vuksanovic
author Venia Batziou
Vesna Vuksanovic
author2 Nicolás Rubido
Venia Batziou
Marwan Fuad
Vesna Vuksanovic
format Working paper
container_title arXiv
institution Swansea University
doi_str_mv 10.48550/arXiv.2505.03458
college_str Faculty of Medicine, Health and Life Sciences
hierarchytype
hierarchy_top_id facultyofmedicinehealthandlifesciences
hierarchy_top_title Faculty of Medicine, Health and Life Sciences
hierarchy_parent_id facultyofmedicinehealthandlifesciences
hierarchy_parent_title Faculty of Medicine, Health and Life Sciences
department_str Swansea University Medical School - Health Data Science{{{_:::_}}}Faculty of Medicine, Health and Life Sciences{{{_:::_}}}Swansea University Medical School - Health Data Science
document_store_str 1
active_str 0
description Brain network analysis using functional MRI has advanced our understanding of cortical activity and its disruption in neurodegenerative disorders underlying dementia. Recently, research has focused on dynamic (time-varying) brain networks that capture both spatial and temporal patterns of regional cortical co-activity. However, this approach remains relatively unexplored across the Alzheimer’s disease (AD) spectrum. In this study, we analysed age- and sex-matched static and dynamic functional brain networks derived from resting-state fMRI data in 315 individuals with AD, mild cognitive impairment (MCI), and cognitively normal healthy controls (HC) from the ADNI-3 cohort. Functionalnetworks were constructed using the Juelich brain atlas, with static connectivity estimated from full time series and dynamic connectivity derived using a sliding-window approach. Group differences were assessed at both the link and node levels using non-parametric statistics and bootstrap resampling. While HC and MCI show similar static and dynamic patterns at the node level, clearer differences emerge in AD. We identified stable (stationary) differences in functional connectivity between white matter regions and parietal and somatosensory cortices, whereas temporally varying differences wereconsistently observed in connections involving the amygdala and hippocampal formation. In addition, node centrality analysis suggested that white matter connectivity differences are predominantly local in nature. Our results highlight shared and unique functional connectivity patterns in both static and dynamic functional networks, emphasising the importance of incorporating dynamic information into brain network analyses of the Alzheimer’s spectrum. Furthermore, we trained a Random Forest model on regional BOLD time series informed by dynamic and static network metrics, achieving robust classification of MCI, AD, and HC groups and demonstrating the diagnostic potential of time-varying connectivity.
published_date 0001-01-01T06:21:41Z
_version_ 1865139986375901184
score 11.105529

Similar Items