Association between abnormal brain functional connectivity in children and psychopathology: A study based on graph theory and machine learning

João Ricardo Sato; Claudinei Eduardo Biazoli; Giovanni Abrahão Salum; Ary Gadelha; Nicolas Crossley Karmelic; Gilson Vieira; André Zugman; Felipe Almeida Picon; Pedro Mario Pan; Marcelo Queiroz Hoexter; Edson Amaro; Mauricio Anés; Luciana Monteiro Moura; Marco Antonio Gomes Del’Aquilla; Philip Mcguire; Luis Augusto Rohde; Euripedes Constantino Miguel; Andrea Parolin Jackowski; Rodrigo Affonseca Bressan

doi:10.1080/15622975.2016.1274050

Association between abnormal brain functional connectivity in children and psychopathology: A study based on graph theory and machine learning

João Ricardo Sato^*, Claudinei Eduardo Biazoli, Giovanni Abrahão Salum, Ary Gadelha, Nicolas Crossley Karmelic, Gilson Vieira, André Zugman, Felipe Almeida Picon, Pedro Mario Pan, Marcelo Queiroz Hoexter, Edson Amaro, Mauricio Anés, Luciana Monteiro Moura, Marco Antonio Gomes Del’Aquilla, Philip Mcguire, Luis Augusto Rohde, Euripedes Constantino Miguel, Andrea Parolin Jackowski, Rodrigo Affonseca Bressan

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

11 Citations (Scopus)

Abstract

Objectives: One of the major challenges facing psychiatry is how to incorporate biological measures in the classification of mental health disorders. Many of these disorders affect brain development and its connectivity. In this study, we propose a novel method for assessing brain networks based on the combination of a graph theory measure (eigenvector centrality) and a one-class support vector machine (OC-SVM). Methods: We applied this approach to resting-state fMRI data from 622 children and adolescents. Eigenvector centrality (EVC) of nodes from positive- and negative-task networks were extracted from each subject and used as input to an OC-SVM to label individual brain networks as typical or atypical. We hypothesised that classification of these subjects regarding the pattern of brain connectivity would predict the level of psychopathology. Results: Subjects with atypical brain network organisation had higher levels of psychopathology (p

Original language	English
Pages (from-to)	1-11
Number of pages	11
Journal	World Journal of Biological Psychiatry
Early online date	8 Feb 2017
DOIs	https://doi.org/10.1080/15622975.2016.1274050
Publication status	E-pub ahead of print - 8 Feb 2017

Keywords

children
Connectivity
fMRI
machine learning
psychopathology

Access to Document

10.1080/15622975.2016.1274050

Cite this

Sato, J. R., Biazoli, C. E., Salum, G. A., Gadelha, A., Crossley Karmelic, N., Vieira, G., Zugman, A., Picon, F. A., Pan, P. M., Hoexter, M. Q., Amaro, E., Anés, M., Moura, L. M., Del’Aquilla, M. A. G., Mcguire, P., Rohde, L. A., Miguel, E. C., Jackowski, A. P., & Bressan, R. A. (2017). Association between abnormal brain functional connectivity in children and psychopathology: A study based on graph theory and machine learning. World Journal of Biological Psychiatry, 1-11. Advance online publication. https://doi.org/10.1080/15622975.2016.1274050

@article{2b4e160697524c7a98c43655a08e35ed,

title = "Association between abnormal brain functional connectivity in children and psychopathology: A study based on graph theory and machine learning",

abstract = "Objectives: One of the major challenges facing psychiatry is how to incorporate biological measures in the classification of mental health disorders. Many of these disorders affect brain development and its connectivity. In this study, we propose a novel method for assessing brain networks based on the combination of a graph theory measure (eigenvector centrality) and a one-class support vector machine (OC-SVM). Methods: We applied this approach to resting-state fMRI data from 622 children and adolescents. Eigenvector centrality (EVC) of nodes from positive- and negative-task networks were extracted from each subject and used as input to an OC-SVM to label individual brain networks as typical or atypical. We hypothesised that classification of these subjects regarding the pattern of brain connectivity would predict the level of psychopathology. Results: Subjects with atypical brain network organisation had higher levels of psychopathology (p ",

keywords = "children, Connectivity, fMRI, machine learning, psychopathology",

author = "Sato, {Jo{\~a}o Ricardo} and Biazoli, {Claudinei Eduardo} and Salum, {Giovanni Abrah{\~a}o} and Ary Gadelha and {Crossley Karmelic}, Nicolas and Gilson Vieira and Andr{\'e} Zugman and Picon, {Felipe Almeida} and Pan, {Pedro Mario} and Hoexter, {Marcelo Queiroz} and Edson Amaro and Mauricio An{\'e}s and Moura, {Luciana Monteiro} and Del{\textquoteright}Aquilla, {Marco Antonio Gomes} and Philip Mcguire and Rohde, {Luis Augusto} and Miguel, {Euripedes Constantino} and Jackowski, {Andrea Parolin} and Bressan, {Rodrigo Affonseca}",

year = "2017",

month = feb,

day = "8",

doi = "10.1080/15622975.2016.1274050",

language = "English",

pages = "1--11",

journal = "World Journal of Biological Psychiatry",

issn = "1562-2975",

publisher = "Taylor & Francis",

}

Sato, JR, Biazoli, CE, Salum, GA, Gadelha, A, Crossley Karmelic, N, Vieira, G, Zugman, A, Picon, FA, Pan, PM, Hoexter, MQ, Amaro, E, Anés, M, Moura, LM, Del’Aquilla, MAG, Mcguire, P, Rohde, LA, Miguel, EC, Jackowski, AP & Bressan, RA 2017, 'Association between abnormal brain functional connectivity in children and psychopathology: A study based on graph theory and machine learning', World Journal of Biological Psychiatry, pp. 1-11. https://doi.org/10.1080/15622975.2016.1274050

TY - JOUR

T1 - Association between abnormal brain functional connectivity in children and psychopathology

T2 - A study based on graph theory and machine learning

AU - Sato, João Ricardo

AU - Biazoli, Claudinei Eduardo

AU - Salum, Giovanni Abrahão

AU - Gadelha, Ary

AU - Crossley Karmelic, Nicolas

AU - Vieira, Gilson

AU - Zugman, André

AU - Picon, Felipe Almeida

AU - Pan, Pedro Mario

AU - Hoexter, Marcelo Queiroz

AU - Amaro, Edson

AU - Anés, Mauricio

AU - Moura, Luciana Monteiro

AU - Del’Aquilla, Marco Antonio Gomes

AU - Mcguire, Philip

AU - Rohde, Luis Augusto

AU - Miguel, Euripedes Constantino

AU - Jackowski, Andrea Parolin

AU - Bressan, Rodrigo Affonseca

PY - 2017/2/8

Y1 - 2017/2/8

N2 - Objectives: One of the major challenges facing psychiatry is how to incorporate biological measures in the classification of mental health disorders. Many of these disorders affect brain development and its connectivity. In this study, we propose a novel method for assessing brain networks based on the combination of a graph theory measure (eigenvector centrality) and a one-class support vector machine (OC-SVM). Methods: We applied this approach to resting-state fMRI data from 622 children and adolescents. Eigenvector centrality (EVC) of nodes from positive- and negative-task networks were extracted from each subject and used as input to an OC-SVM to label individual brain networks as typical or atypical. We hypothesised that classification of these subjects regarding the pattern of brain connectivity would predict the level of psychopathology. Results: Subjects with atypical brain network organisation had higher levels of psychopathology (p

AB - Objectives: One of the major challenges facing psychiatry is how to incorporate biological measures in the classification of mental health disorders. Many of these disorders affect brain development and its connectivity. In this study, we propose a novel method for assessing brain networks based on the combination of a graph theory measure (eigenvector centrality) and a one-class support vector machine (OC-SVM). Methods: We applied this approach to resting-state fMRI data from 622 children and adolescents. Eigenvector centrality (EVC) of nodes from positive- and negative-task networks were extracted from each subject and used as input to an OC-SVM to label individual brain networks as typical or atypical. We hypothesised that classification of these subjects regarding the pattern of brain connectivity would predict the level of psychopathology. Results: Subjects with atypical brain network organisation had higher levels of psychopathology (p

KW - children

KW - Connectivity

KW - fMRI

KW - machine learning

KW - psychopathology

UR - http://www.scopus.com/inward/record.url?scp=85011841876&partnerID=8YFLogxK

U2 - 10.1080/15622975.2016.1274050

DO - 10.1080/15622975.2016.1274050

M3 - Article

AN - SCOPUS:85011841876

SN - 1562-2975

SP - 1

EP - 11

JO - World Journal of Biological Psychiatry

JF - World Journal of Biological Psychiatry

ER -

Association between abnormal brain functional connectivity in children and psychopathology: A study based on graph theory and machine learning

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this