Evaluation of altered functional connections in male children with autism spectrum disorders on multiple-site data optimized with machine learning

Giovanna Spera, Alessandra Retico, Paolo Bosco, Elisa Ferrari, Letizia Palumbo, Piernicola Oliva, Filippo Muratori, Sara Calderoni

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

No univocal and reliable brain-based biomarkers have been detected to date in Autism Spectrum Disorders (ASD). Neuroimaging studies have consistently revealed alterations in brain structure and function of individuals with ASD; however, it remains difficult to ascertain the extent and localization of affected brain networks. In this context, the application of Machine Learning (ML) classification methods to neuroimaging data has the potential to contribute to a better distinction between subjects with ASD and typical development controls (TD). This study is focused on the analysis of resting-state fMRI data of individuals with ASD and matched TD, available within the ABIDE collection. To reduce the multiple sources of heterogeneity that impact on understanding the neural underpinnings of autistic condition, we selected a subgroup of 190 subjects (102 with ASD and 88 TD) according to the following criteria: male children (age range: 6.5–13 years); rs-fMRI data acquired with open eyes; data from the University sites that provided the largest number of scans (KKI, NYU, UCLA, UM). Connectivity values were evaluated as the linear correlation between pairs of time series of brain areas; then, a Linear kernel Support Vector Machine (L-SVM) classification, with an inter-site cross-validation scheme, was carried out. A permutation test was conducted to identify over-connectivity and under-connectivity alterations in the ASD group. The mean L-SVM classification performance, in terms of the area under the ROC curve (AUC), was 0.75 ± 0.05. The highest performance was obtained using data from KKI, NYU and UCLA sites in training and data from UM as testing set (AUC = 0.83). Specifically, stronger functional connectivity (FC) in ASD with respect to TD involve (p < 0.001) the angular gyrus with the precuneus in the right (R) hemisphere, and the R frontal operculum cortex with the pars opercularis of the left (L) inferior frontal gyrus. Weaker connections in ASD group with respect to TD are the intra-hemispheric R temporal fusiform cortex with the R hippocampus, and the L supramarginal gyrus with L planum polare. The results indicate that both under-and over-FC occurred in a selected cohort of ASD children relative to TD controls, and that these functional alterations are spread in different brain networks.

Original languageEnglish
Article number620
JournalFrontiers in Psychiatry
Volume10
DOIs
Publication statusPublished - Jan 1 2019

Keywords

  • ABIDE
  • Autism spectrum disorders
  • Children
  • Functional connectivity
  • Machine learning
  • Resting-state fMRI

ASJC Scopus subject areas

  • Psychiatry and Mental health

Cite this

Evaluation of altered functional connections in male children with autism spectrum disorders on multiple-site data optimized with machine learning. / Spera, Giovanna; Retico, Alessandra; Bosco, Paolo; Ferrari, Elisa; Palumbo, Letizia; Oliva, Piernicola; Muratori, Filippo; Calderoni, Sara.

In: Frontiers in Psychiatry, Vol. 10, 620, 01.01.2019.

Research output: Contribution to journalArticle

@article{b140f81c77274a39b31ff60b01f101db,
title = "Evaluation of altered functional connections in male children with autism spectrum disorders on multiple-site data optimized with machine learning",
abstract = "No univocal and reliable brain-based biomarkers have been detected to date in Autism Spectrum Disorders (ASD). Neuroimaging studies have consistently revealed alterations in brain structure and function of individuals with ASD; however, it remains difficult to ascertain the extent and localization of affected brain networks. In this context, the application of Machine Learning (ML) classification methods to neuroimaging data has the potential to contribute to a better distinction between subjects with ASD and typical development controls (TD). This study is focused on the analysis of resting-state fMRI data of individuals with ASD and matched TD, available within the ABIDE collection. To reduce the multiple sources of heterogeneity that impact on understanding the neural underpinnings of autistic condition, we selected a subgroup of 190 subjects (102 with ASD and 88 TD) according to the following criteria: male children (age range: 6.5–13 years); rs-fMRI data acquired with open eyes; data from the University sites that provided the largest number of scans (KKI, NYU, UCLA, UM). Connectivity values were evaluated as the linear correlation between pairs of time series of brain areas; then, a Linear kernel Support Vector Machine (L-SVM) classification, with an inter-site cross-validation scheme, was carried out. A permutation test was conducted to identify over-connectivity and under-connectivity alterations in the ASD group. The mean L-SVM classification performance, in terms of the area under the ROC curve (AUC), was 0.75 ± 0.05. The highest performance was obtained using data from KKI, NYU and UCLA sites in training and data from UM as testing set (AUC = 0.83). Specifically, stronger functional connectivity (FC) in ASD with respect to TD involve (p < 0.001) the angular gyrus with the precuneus in the right (R) hemisphere, and the R frontal operculum cortex with the pars opercularis of the left (L) inferior frontal gyrus. Weaker connections in ASD group with respect to TD are the intra-hemispheric R temporal fusiform cortex with the R hippocampus, and the L supramarginal gyrus with L planum polare. The results indicate that both under-and over-FC occurred in a selected cohort of ASD children relative to TD controls, and that these functional alterations are spread in different brain networks.",
keywords = "ABIDE, Autism spectrum disorders, Children, Functional connectivity, Machine learning, Resting-state fMRI",
author = "Giovanna Spera and Alessandra Retico and Paolo Bosco and Elisa Ferrari and Letizia Palumbo and Piernicola Oliva and Filippo Muratori and Sara Calderoni",
year = "2019",
month = "1",
day = "1",
doi = "10.3389/fpsyt.2019.00620",
language = "English",
volume = "10",
journal = "Frontiers in Psychiatry",
issn = "1664-0640",
publisher = "Frontiers Research Foundation",

}

TY - JOUR

T1 - Evaluation of altered functional connections in male children with autism spectrum disorders on multiple-site data optimized with machine learning

AU - Spera, Giovanna

AU - Retico, Alessandra

AU - Bosco, Paolo

AU - Ferrari, Elisa

AU - Palumbo, Letizia

AU - Oliva, Piernicola

AU - Muratori, Filippo

AU - Calderoni, Sara

PY - 2019/1/1

Y1 - 2019/1/1

N2 - No univocal and reliable brain-based biomarkers have been detected to date in Autism Spectrum Disorders (ASD). Neuroimaging studies have consistently revealed alterations in brain structure and function of individuals with ASD; however, it remains difficult to ascertain the extent and localization of affected brain networks. In this context, the application of Machine Learning (ML) classification methods to neuroimaging data has the potential to contribute to a better distinction between subjects with ASD and typical development controls (TD). This study is focused on the analysis of resting-state fMRI data of individuals with ASD and matched TD, available within the ABIDE collection. To reduce the multiple sources of heterogeneity that impact on understanding the neural underpinnings of autistic condition, we selected a subgroup of 190 subjects (102 with ASD and 88 TD) according to the following criteria: male children (age range: 6.5–13 years); rs-fMRI data acquired with open eyes; data from the University sites that provided the largest number of scans (KKI, NYU, UCLA, UM). Connectivity values were evaluated as the linear correlation between pairs of time series of brain areas; then, a Linear kernel Support Vector Machine (L-SVM) classification, with an inter-site cross-validation scheme, was carried out. A permutation test was conducted to identify over-connectivity and under-connectivity alterations in the ASD group. The mean L-SVM classification performance, in terms of the area under the ROC curve (AUC), was 0.75 ± 0.05. The highest performance was obtained using data from KKI, NYU and UCLA sites in training and data from UM as testing set (AUC = 0.83). Specifically, stronger functional connectivity (FC) in ASD with respect to TD involve (p < 0.001) the angular gyrus with the precuneus in the right (R) hemisphere, and the R frontal operculum cortex with the pars opercularis of the left (L) inferior frontal gyrus. Weaker connections in ASD group with respect to TD are the intra-hemispheric R temporal fusiform cortex with the R hippocampus, and the L supramarginal gyrus with L planum polare. The results indicate that both under-and over-FC occurred in a selected cohort of ASD children relative to TD controls, and that these functional alterations are spread in different brain networks.

AB - No univocal and reliable brain-based biomarkers have been detected to date in Autism Spectrum Disorders (ASD). Neuroimaging studies have consistently revealed alterations in brain structure and function of individuals with ASD; however, it remains difficult to ascertain the extent and localization of affected brain networks. In this context, the application of Machine Learning (ML) classification methods to neuroimaging data has the potential to contribute to a better distinction between subjects with ASD and typical development controls (TD). This study is focused on the analysis of resting-state fMRI data of individuals with ASD and matched TD, available within the ABIDE collection. To reduce the multiple sources of heterogeneity that impact on understanding the neural underpinnings of autistic condition, we selected a subgroup of 190 subjects (102 with ASD and 88 TD) according to the following criteria: male children (age range: 6.5–13 years); rs-fMRI data acquired with open eyes; data from the University sites that provided the largest number of scans (KKI, NYU, UCLA, UM). Connectivity values were evaluated as the linear correlation between pairs of time series of brain areas; then, a Linear kernel Support Vector Machine (L-SVM) classification, with an inter-site cross-validation scheme, was carried out. A permutation test was conducted to identify over-connectivity and under-connectivity alterations in the ASD group. The mean L-SVM classification performance, in terms of the area under the ROC curve (AUC), was 0.75 ± 0.05. The highest performance was obtained using data from KKI, NYU and UCLA sites in training and data from UM as testing set (AUC = 0.83). Specifically, stronger functional connectivity (FC) in ASD with respect to TD involve (p < 0.001) the angular gyrus with the precuneus in the right (R) hemisphere, and the R frontal operculum cortex with the pars opercularis of the left (L) inferior frontal gyrus. Weaker connections in ASD group with respect to TD are the intra-hemispheric R temporal fusiform cortex with the R hippocampus, and the L supramarginal gyrus with L planum polare. The results indicate that both under-and over-FC occurred in a selected cohort of ASD children relative to TD controls, and that these functional alterations are spread in different brain networks.

KW - ABIDE

KW - Autism spectrum disorders

KW - Children

KW - Functional connectivity

KW - Machine learning

KW - Resting-state fMRI

UR - http://www.scopus.com/inward/record.url?scp=85072963860&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072963860&partnerID=8YFLogxK

U2 - 10.3389/fpsyt.2019.00620

DO - 10.3389/fpsyt.2019.00620

M3 - Article

AN - SCOPUS:85072963860

VL - 10

JO - Frontiers in Psychiatry

JF - Frontiers in Psychiatry

SN - 1664-0640

M1 - 620

ER -