How to Build a Functional Connectomic Biomarker for Mild Cognitive Impairment From Source Reconstructed MEG Resting-State Activity: The Combination of ROI Representation and Connectivity Estimator Matters
dc.contributor.author | López García, María Eugenia | |
dc.contributor.author | Bruña Fernández, Ricardo | |
dc.contributor.author | Cuesta Prieto, Pablo | |
dc.contributor.author | Marcos Dolado, Alberto | |
dc.contributor.author | Maestu Unturbe, Fernando | |
dc.date.accessioned | 2024-02-08T08:15:19Z | |
dc.date.available | 2024-02-08T08:15:19Z | |
dc.date.issued | 2018-06-01 | |
dc.description.abstract | Our work aimed to demonstrate the combination of machine learning and graph theory for the designing of a connectomic biomarker for mild cognitive impairment (MCI) subjects using eyes-closed neuromagnetic recordings. The whole analysis based on source-reconstructed neuromagnetic activity. As ROI representation, we employed the principal component analysis (PCA) and centroid approaches. As representative bi-variate connectivity estimators for the estimation of intra and cross-frequency interactions, we adopted the phase locking value (PLV), the imaginary part (iPLV) and the correlation of the envelope (CorrEnv). Both intra and cross-frequency interactions (CFC) have been estimated with the three connectivity estimators within the seven frequency bands (intra-frequency) and in pairs (CFC), correspondingly. We demonstrated how different versions of functional connectivity graphs single-layer (SL-FCG) and multi-layer (ML-FCG) can give us a different view of the functional interactions across the brain areas. Finally, we applied machine learning techniques with main scope to build a reliable connectomic biomarker by analyzing both SL-FCG and ML-FCG in two different options: as a whole unit using a tensorial extraction algorithm and as single pair-wise coupling estimations. We concluded that edge-weighed feature selection strategy outperformed the tensorial treatment of SL-FCG and ML-FCG. The highest classification performance was obtained with the centroid ROI representation and edge-weighted analysis of the SL-FCG reaching the 98% for the CorrEnv in α1:α2 and 94% for the iPLV in α2. Classification performance based on the multi-layer participation coefficient, a multiplexity index reached 52% for iPLV and 52% for CorrEnv. Selected functional connections that build the multivariate connectomic biomarker in the edge-weighted scenario are located in default-mode, fronto-parietal, and cingulo-opercular network. Our analysis supports the notion of analyzing FCG simultaneously in intra and cross-frequency whole brain interactions with various connectivity estimators in beamformed recordings. | |
dc.description.department | Depto. de Psicología Experimental, Procesos Cognitivos y Logopedia | |
dc.description.department | Depto. de Radiología, Rehabilitación y Fisioterapia | |
dc.description.faculty | Fac. de Psicología | |
dc.description.faculty | Fac. de Medicina | |
dc.description.refereed | TRUE | |
dc.description.sponsorship | Comisión Europea | |
dc.description.sponsorship | Ministerio de Economía y Competitividad | |
dc.description.sponsorship | Ministerio de Educación | |
dc.description.status | pub | |
dc.identifier.citation | Dimitriadis SI, López ME, Bruña R,Cuesta P, Marcos A, Maestú F andPereda E (2018) How to Build aFunctional Connectomic Biomarker forMild Cognitive Impairment FromSource Reconstructed MEGResting-State Activity: The Combination of ROI Representationand Connectivity Estimator Matters.Front. Neurosci. 12:306 doi:10.3389/fnins.2018.00306 | |
dc.identifier.doi | 10.3389/fnins.2018.00306 | |
dc.identifier.essn | 1662-453X | |
dc.identifier.issn | 1662-4548 | |
dc.identifier.officialurl | https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2018.00306/full | |
dc.identifier.pmid | 29910704 | |
dc.identifier.relatedurl | https://pubmed.ncbi.nlm.nih.gov/29910704/ | |
dc.identifier.uri | https://hdl.handle.net/20.500.14352/100165 | |
dc.journal.title | Frontiers in Neuroscience | |
dc.language.iso | eng | |
dc.page.initial | 306 | |
dc.publisher | Frontiers | |
dc.relation.projectID | MR/K004360/1 | |
dc.relation.projectID | FIS2013-41057-P | |
dc.relation.projectID | TEC2016-80063-C3-2-R | |
dc.relation.projectID | PSI-2015-68793-C3-1-R | |
dc.relation.projectID | FPU13/06009 | |
dc.rights | Attribution 4.0 International | en |
dc.rights.accessRights | open access | |
dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | |
dc.subject.cdu | 612.8 | |
dc.subject.keyword | Connectomic biomarker | |
dc.subject.keyword | Magnetoencephalography | |
dc.subject.keyword | Mild cognitive impairment | |
dc.subject.keyword | Virtual source activity | |
dc.subject.keyword | Connectome data analysis | |
dc.subject.keyword | Multiplexity | |
dc.subject.keyword | Cross-frequency-coupling | |
dc.subject.keyword | Intrinsic coupling modes | |
dc.subject.ucm | Neurociencias (Medicina) | |
dc.subject.unesco | 2490 Neurociencias | |
dc.title | How to Build a Functional Connectomic Biomarker for Mild Cognitive Impairment From Source Reconstructed MEG Resting-State Activity: The Combination of ROI Representation and Connectivity Estimator Matters | |
dc.type | journal article | |
dc.type.hasVersion | VoR | |
dc.volume.number | 12 | |
dspace.entity.type | Publication | |
relation.isAuthorOfPublication | ddd4612a-44c8-4cb3-bd54-2332d6f37877 | |
relation.isAuthorOfPublication | ef335315-bb52-49b1-8703-63c7caae45f8 | |
relation.isAuthorOfPublication | 7070623b-91a0-4590-86f6-227266503c1e | |
relation.isAuthorOfPublication | 542b2457-e80a-4114-ae20-6ca71cd3c79f | |
relation.isAuthorOfPublication | afa98131-b2fe-40fd-8f89-f3994d80ab72 | |
relation.isAuthorOfPublication.latestForDiscovery | ddd4612a-44c8-4cb3-bd54-2332d6f37877 |
Download
Original bundle
1 - 1 of 1
Loading...
- Name:
- Dimitriadis et al. 2018 Front. Neurosci. 12.306.pdf
- Size:
- 4.17 MB
- Format:
- Adobe Portable Document Format