Autor según el artículo: Salvador R; Verdolini N; Garcia-Ruiz B; Jiménez E; Sarró S; Vilella E; Vieta E; Canales-Rodríguez EJ; Pomarol-Clotet E; Voineskos AN
Departamento: Medicina i Cirurgia
Autor/es de la URV: Vilella Cuadrada, Elisabet
Palabras clave: Ridge regression Random forest Global brain connectivity Gender Brain connectivity Age
Resumen: © Copyright © 2020 Salvador, Verdolini, Garcia-Ruiz, Jiménez, Sarró, Vilella, Vieta, Canales-Rodríguez, Pomarol-Clotet and Voineskos. Functional connectivity analyses are typically based on matrices containing bivariate measures of covariability, such as correlations. Although this has been a fruitful approach, it may not be the optimal strategy to fully explore the complex associations underlying brain activity. Here, we propose extending connectivity to multivariate functions relating to the temporal dynamics of a region with the rest of the brain. The main technical challenges of such an approach are multidimensionality and its associated risk of overfitting or even the non-uniqueness of model solutions. To minimize these risks, and as an alternative to the more common dimensionality reduction methods, we propose using two regularized multivariate connectivity models. On the one hand, simple linear functions of all brain nodes were fitted with ridge regression. On the other hand, a more flexible approach to avoid linearity and additivity assumptions was implemented through random forest regression. Similarities and differences between both methods and with simple averages of bivariate correlations (i.e., weighted global brain connectivity) were evaluated on a resting state sample of N = 173 healthy subjects. Results revealed distinct connectivity patterns from the two proposed methods, which were especially relevant in the age-related analyses where both ridge and random forest regressions showed significant patterns of age-related disconnection, almost completely absent from the much less sensitive global brain connectivity maps. On the other hand, the greater flexibility provided by the random forest algorithm allowed detecting sex-specific differences. The generic framework of multivariate connectivity implemented here may be easily extended to other types of regularized models.
Áreas temáticas: Saúde coletiva Psicología Neurosciences Neuroscience (miscellaneous) Neuroscience (all) Medicina veterinaria Medicina iii Medicina ii Medicina i Interdisciplinar General neuroscience Filosofía Engenharias iv Educação física Ciências biológicas ii Ciências biológicas i Ciência da computação Biodiversidade Administração, ciências contábeis e turismo
Acceso a la licencia de uso: https://creativecommons.org/licenses/by/3.0/es/
Direcció de correo del autor: elisabet.vilella@urv.cat
Identificador del autor: 0000-0002-1887-5919
Fecha de alta del registro: 2023-02-23
Versión del articulo depositado: info:eu-repo/semantics/publishedVersion
Referencia al articulo segun fuente origial: Frontiers In Neuroscience. 14 (569540):
Referencia de l'ítem segons les normes APA: Salvador R; Verdolini N; Garcia-Ruiz B; Jiménez E; Sarró S; Vilella E; Vieta E; Canales-Rodríguez EJ; Pomarol-Clotet E; Voineskos AN (2020). Multivariate Brain Functional Connectivity Through Regularized Estimators. Frontiers In Neuroscience, 14(569540), -. DOI: 10.3389/fnins.2020.569540
URL Documento de licencia: https://repositori.urv.cat/ca/proteccio-de-dades/
Entidad: Universitat Rovira i Virgili
Año de publicación de la revista: 2020
Tipo de publicación: Journal Publications
Repositori URV