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

Author(s):Show less -

Sato, Joao Ricardo ^{[1, 2, 3, 4]} ; Biazoli, Jr., Claudinei Eduardo ^{[1, 2]} ; Salum, Giovanni Abrahao ^{[5, 6, 3]} ; Gadelha, Ary ^{[3, 4]} ; Crossley, Nicolas ^[7] ; Vieira, Gilson ^{[2, 8]} ; Zugman, Andre ^{[3, 4]} ; Picon, Felipe Almeida ^{[5, 6, 3]} ; Pan, Pedro Mario ^{[3, 4]} ; Hoexter, Marcelo Queiroz ^{[9, 3, 4]} ; Amaro, Jr., Edson ^[10] ; Anes, Mauricio ^{[5, 6, 3]} ; Moura, Luciana Monteiro ^{[3, 4]} ; Gomes Del'Aquilla, Marco Antonio ^{[3, 4]} ; Mcguire, Philip ^[7] ; Rohde, Luis Augusto ^{[5, 6, 3]} ; Miguel, Euripedes Constantino ^{[9, 3]} ; Jackowski, Andrea Parolin ^{[3, 4]} ; Bressan, Rodrigo Affonseca ^{[3, 4]}

Affiliation

^[1] Univ Fed ABC, Ctr Math Computat & Cognit, Santo Andre - Brazil

^[2] Univ Sao Paulo, Sch Med, Dept Radiol, Sao Paulo - Brazil

^[3] CNPq, Natl Inst Dev Psychiat Children & Adolescents, Brasilia, DF - Brazil

^[4] Univ Fed Sao Paulo UNIFESP, Interdisciplinary Lab Clin Neurosci LiNC, Dept Psychiat, Sao Paulo - Brazil

^[5] Univ Fed Rio Grande do Sul, Dept Psychiat, Porto Alegre, RS - Brazil

^[6] Univ Fed Rio Grande do Sul, Hosp Clin Porto Alegre, Porto Alegre, RS - Brazil

^[7] Kings Coll London, Inst Psychiat, Dept Psychosis Studies, London - England

^[8] Univ Sao Paulo, Inst Math & Stat, Bioinformat Program, Sao Paulo - Brazil

^[9] Univ Sao Paulo, Sch Med, Dept Psychiat, Sao Paulo - Brazil

^[10] Univ Sao Paulo, Fac Med, Inst Radiol InRad, Sao Paulo - Brazil

• Document type: Journal article
• Source: WORLD JOURNAL OF BIOLOGICAL PSYCHIATRY; v. 19, n. 2, p. 119-129, 2018.
• Web of Science Citations: 2

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<0.001). There was a greater EVC in the typical group at the bilateral posterior cingulate and bilateral posterior temporal cortices; and significant decreases in EVC at left temporal pole.Conclusions: The combination of graph theory methods and an OC-SVM is a promising method to characterise neurodevelopment, and may be useful to understand the deviations leading to mental disorders. (AU)

• FAPESP's process: 13/10498-6 - Machine learning in neuroimaging: development of methods and clinical applications in psychiatric disorders
• Grantee: João Ricardo Sato
• Support type: Regular Research Grants
• FAPESP's process: 13/08531-5 - High risk cohort study for psychiatric disorders in childhood: 3-year follow-up neuroimaging study
• Grantee: Andrea Parolin Jackowski
• Support type: Regular Research Grants
• FAPESP's process: 08/57896-8 - National Institute for Developmental Psychiatry
• Grantee: Eurípedes Constantino Miguel Filho
• Support type: Research Projects - Thematic Grants
• FAPESP's process: 13/00506-1 - Time series, wavelets and functional data analysis
• Grantee: Pedro Alberto Morettin
• Support type: Research Projects - Thematic Grants