Regularized Functional Connectivity in Schizophrenia
Regularization may be used as an alternative to dimensionality reduction when the number of variables in a model is much larger than the number of available observations. In a recent study from our group regularized regression was employed to quantify brain functional connectivity in a sample of hea...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2022-05-01
|
Series: | Frontiers in Human Neuroscience |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fnhum.2022.878028/full |
_version_ | 1818203587891691520 |
---|---|
author | Raymond Salvador Raymond Salvador Paola Fuentes-Claramonte Paola Fuentes-Claramonte María Ángeles García-León María Ángeles García-León Núria Ramiro Joan Soler-Vidal Joan Soler-Vidal Joan Soler-Vidal María Llanos Torres Pilar Salgado-Pineda Pilar Salgado-Pineda Josep Munuera Aristotle Voineskos Aristotle Voineskos Edith Pomarol-Clotet Edith Pomarol-Clotet |
author_facet | Raymond Salvador Raymond Salvador Paola Fuentes-Claramonte Paola Fuentes-Claramonte María Ángeles García-León María Ángeles García-León Núria Ramiro Joan Soler-Vidal Joan Soler-Vidal Joan Soler-Vidal María Llanos Torres Pilar Salgado-Pineda Pilar Salgado-Pineda Josep Munuera Aristotle Voineskos Aristotle Voineskos Edith Pomarol-Clotet Edith Pomarol-Clotet |
author_sort | Raymond Salvador |
collection | DOAJ |
description | Regularization may be used as an alternative to dimensionality reduction when the number of variables in a model is much larger than the number of available observations. In a recent study from our group regularized regression was employed to quantify brain functional connectivity in a sample of healthy controls using a brain parcellation and resting state fMRI images. Here regularization is applied to evaluate resting state connectivity abnormalities at the voxel level in a sample of patients with schizophrenia. Specifically, ridge regression is implemented with different degrees of regularization. Results are compared to those delivered by the weighted global brain connectivity method (GBC), which is based on averaged bivariate correlations and from the non-redundant connectivity method (NRC), a dimensionality reduction approach that applies supervised principal component regressions. Ridge regression is able to detect a larger set of abnormally connected regions than both GBC and NRC methods, including schizophrenia related connectivity reductions in fronto-medial, somatosensory and occipital structures. Due to its multivariate nature, the proposed method is much more sensitive to group abnormalities than the GBC, but it also outperforms the NRC, which is multivariate too. Voxel based regularized regression is a simple and sensitive alternative for quantifying brain functional connectivity. |
first_indexed | 2024-12-12T03:27:43Z |
format | Article |
id | doaj.art-5f74653fd97543d584a97bf9f7dcdc34 |
institution | Directory Open Access Journal |
issn | 1662-5161 |
language | English |
last_indexed | 2024-12-12T03:27:43Z |
publishDate | 2022-05-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Human Neuroscience |
spelling | doaj.art-5f74653fd97543d584a97bf9f7dcdc342022-12-22T00:39:59ZengFrontiers Media S.A.Frontiers in Human Neuroscience1662-51612022-05-011610.3389/fnhum.2022.878028878028Regularized Functional Connectivity in SchizophreniaRaymond Salvador0Raymond Salvador1Paola Fuentes-Claramonte2Paola Fuentes-Claramonte3María Ángeles García-León4María Ángeles García-León5Núria Ramiro6Joan Soler-Vidal7Joan Soler-Vidal8Joan Soler-Vidal9María Llanos Torres10Pilar Salgado-Pineda11Pilar Salgado-Pineda12Josep Munuera13Aristotle Voineskos14Aristotle Voineskos15Edith Pomarol-Clotet16Edith Pomarol-Clotet17FIDMAG Germanes Hospitalàries Research Foundation, Barcelona, SpainCentro de Investigación Biomédica en Red de Salud Mental, Barcelona, SpainFIDMAG Germanes Hospitalàries Research Foundation, Barcelona, SpainCentro de Investigación Biomédica en Red de Salud Mental, Barcelona, SpainFIDMAG Germanes Hospitalàries Research Foundation, Barcelona, SpainCentro de Investigación Biomédica en Red de Salud Mental, Barcelona, SpainDepartment of Psychiatry, Hospital Sant Rafael, Barcelona, SpainFIDMAG Germanes Hospitalàries Research Foundation, Barcelona, SpainCentro de Investigación Biomédica en Red de Salud Mental, Barcelona, SpainBenito Menni Centre Assistencial en Salut Mental, Sant Boi de Llobregat, Barcelona, SpainHospital Mare de Déu de la Mercé, Unitat Polivalent, Barcelona, SpainFIDMAG Germanes Hospitalàries Research Foundation, Barcelona, SpainCentro de Investigación Biomédica en Red de Salud Mental, Barcelona, SpainDepartment of Diagnostic Imaging, Hospital Sant Joan de Déu, Barcelona, SpainCampbell Family Mental Health Research Institute, Toronto, ON, CanadaDepartment of Psychiatry, University of Toronto, Toronto, ON, CanadaFIDMAG Germanes Hospitalàries Research Foundation, Barcelona, SpainCentro de Investigación Biomédica en Red de Salud Mental, Barcelona, SpainRegularization may be used as an alternative to dimensionality reduction when the number of variables in a model is much larger than the number of available observations. In a recent study from our group regularized regression was employed to quantify brain functional connectivity in a sample of healthy controls using a brain parcellation and resting state fMRI images. Here regularization is applied to evaluate resting state connectivity abnormalities at the voxel level in a sample of patients with schizophrenia. Specifically, ridge regression is implemented with different degrees of regularization. Results are compared to those delivered by the weighted global brain connectivity method (GBC), which is based on averaged bivariate correlations and from the non-redundant connectivity method (NRC), a dimensionality reduction approach that applies supervised principal component regressions. Ridge regression is able to detect a larger set of abnormally connected regions than both GBC and NRC methods, including schizophrenia related connectivity reductions in fronto-medial, somatosensory and occipital structures. Due to its multivariate nature, the proposed method is much more sensitive to group abnormalities than the GBC, but it also outperforms the NRC, which is multivariate too. Voxel based regularized regression is a simple and sensitive alternative for quantifying brain functional connectivity.https://www.frontiersin.org/articles/10.3389/fnhum.2022.878028/fullresting state fMRIschizophreniafunctional connectivityridge regressionglobal brain connectivity |
spellingShingle | Raymond Salvador Raymond Salvador Paola Fuentes-Claramonte Paola Fuentes-Claramonte María Ángeles García-León María Ángeles García-León Núria Ramiro Joan Soler-Vidal Joan Soler-Vidal Joan Soler-Vidal María Llanos Torres Pilar Salgado-Pineda Pilar Salgado-Pineda Josep Munuera Aristotle Voineskos Aristotle Voineskos Edith Pomarol-Clotet Edith Pomarol-Clotet Regularized Functional Connectivity in Schizophrenia Frontiers in Human Neuroscience resting state fMRI schizophrenia functional connectivity ridge regression global brain connectivity |
title | Regularized Functional Connectivity in Schizophrenia |
title_full | Regularized Functional Connectivity in Schizophrenia |
title_fullStr | Regularized Functional Connectivity in Schizophrenia |
title_full_unstemmed | Regularized Functional Connectivity in Schizophrenia |
title_short | Regularized Functional Connectivity in Schizophrenia |
title_sort | regularized functional connectivity in schizophrenia |
topic | resting state fMRI schizophrenia functional connectivity ridge regression global brain connectivity |
url | https://www.frontiersin.org/articles/10.3389/fnhum.2022.878028/full |
work_keys_str_mv | AT raymondsalvador regularizedfunctionalconnectivityinschizophrenia AT raymondsalvador regularizedfunctionalconnectivityinschizophrenia AT paolafuentesclaramonte regularizedfunctionalconnectivityinschizophrenia AT paolafuentesclaramonte regularizedfunctionalconnectivityinschizophrenia AT mariaangelesgarcialeon regularizedfunctionalconnectivityinschizophrenia AT mariaangelesgarcialeon regularizedfunctionalconnectivityinschizophrenia AT nuriaramiro regularizedfunctionalconnectivityinschizophrenia AT joansolervidal regularizedfunctionalconnectivityinschizophrenia AT joansolervidal regularizedfunctionalconnectivityinschizophrenia AT joansolervidal regularizedfunctionalconnectivityinschizophrenia AT mariallanostorres regularizedfunctionalconnectivityinschizophrenia AT pilarsalgadopineda regularizedfunctionalconnectivityinschizophrenia AT pilarsalgadopineda regularizedfunctionalconnectivityinschizophrenia AT josepmunuera regularizedfunctionalconnectivityinschizophrenia AT aristotlevoineskos regularizedfunctionalconnectivityinschizophrenia AT aristotlevoineskos regularizedfunctionalconnectivityinschizophrenia AT edithpomarolclotet regularizedfunctionalconnectivityinschizophrenia AT edithpomarolclotet regularizedfunctionalconnectivityinschizophrenia |