Multivariate classification of autism spectrum disorder using frequency-specific resting-state functional connectivity-A multi-center study

Heng Chen, Xujun Duan, Feng Liu, Fengmei Lu, Xujing Ma, Youxue Zhang, Lucina Q Uddin, Huafu Chen

Research output: Contribution to journalArticle

46 Citations (Scopus)

Abstract

Background: Resting-state functional magnetic resonance imaging studies examining low frequency fluctuations (0.01-0.08. Hz) have revealed atypical whole brain functional connectivity patterns in adolescents with autism spectrum disorder (ASD), and these atypical patterns can be used to discriminate individuals with ASD from controls. However, at present it is unknown whether functional connectivity at specific frequency bands can be used to discriminate individuals with ASD from controls, and whether relationships with symptom severity are stronger in specific frequency bands. Methods: We selected 240 adolescent subjects (12-18. years old, 112 with autism spectrum disorder (101/11, males/females) and 128 healthy controls (104/24, males/females)) from 6 separate international sites in the Autism Brain Imaging Data Exchange database. Whole brain functional connectivity networks were constructed in the Slow-5 (0.01-0.027. Hz) and Slow-4 (0.027-0.073. Hz) frequency bands, which were then used as classification features. Results: An accuracy of 79.17% (p. <. 0.001) was obtained using support vector machine. Most of the discriminative features were concentrated on the Slow-4 band. In the Slow-4 band, atypical connections between the default mode network, fronto-parietal network and cingulo-opercular network were detected. A significant correlation was found between social and communication deficits as measured by the ADOS in individuals with ASD and the classification scores based on connectivity between the default mode network and the cingulo-opercular network. Connections of the thalamus were of the highest classification weight in the Slow-4 band. Conclusions: Our findings provide preliminary evidence for frequency-specific whole brain functional connectivity indices that may eventually be used to aid detection of ASD.

Original languageEnglish (US)
Pages (from-to)1-9
Number of pages9
JournalProgress in Neuro-Psychopharmacology and Biological Psychiatry
Volume64
DOIs
StatePublished - Jan 4 2016

Fingerprint

Brain
Autistic Disorder
Thalamus
Neuroimaging
Autism Spectrum Disorder
Communication
Magnetic Resonance Imaging
Databases
Weights and Measures
Support Vector Machine

Keywords

  • Autism spectrum disorder
  • Functional connectivity
  • Multivariate pattern analysis
  • Slow-4

ASJC Scopus subject areas

  • Biological Psychiatry
  • Pharmacology

Cite this

Multivariate classification of autism spectrum disorder using frequency-specific resting-state functional connectivity-A multi-center study. / Chen, Heng; Duan, Xujun; Liu, Feng; Lu, Fengmei; Ma, Xujing; Zhang, Youxue; Uddin, Lucina Q; Chen, Huafu.

In: Progress in Neuro-Psychopharmacology and Biological Psychiatry, Vol. 64, 04.01.2016, p. 1-9.

Research output: Contribution to journalArticle

@article{d571d21886da486dae0deff159f41bb8,
title = "Multivariate classification of autism spectrum disorder using frequency-specific resting-state functional connectivity-A multi-center study",
abstract = "Background: Resting-state functional magnetic resonance imaging studies examining low frequency fluctuations (0.01-0.08. Hz) have revealed atypical whole brain functional connectivity patterns in adolescents with autism spectrum disorder (ASD), and these atypical patterns can be used to discriminate individuals with ASD from controls. However, at present it is unknown whether functional connectivity at specific frequency bands can be used to discriminate individuals with ASD from controls, and whether relationships with symptom severity are stronger in specific frequency bands. Methods: We selected 240 adolescent subjects (12-18. years old, 112 with autism spectrum disorder (101/11, males/females) and 128 healthy controls (104/24, males/females)) from 6 separate international sites in the Autism Brain Imaging Data Exchange database. Whole brain functional connectivity networks were constructed in the Slow-5 (0.01-0.027. Hz) and Slow-4 (0.027-0.073. Hz) frequency bands, which were then used as classification features. Results: An accuracy of 79.17{\%} (p. <. 0.001) was obtained using support vector machine. Most of the discriminative features were concentrated on the Slow-4 band. In the Slow-4 band, atypical connections between the default mode network, fronto-parietal network and cingulo-opercular network were detected. A significant correlation was found between social and communication deficits as measured by the ADOS in individuals with ASD and the classification scores based on connectivity between the default mode network and the cingulo-opercular network. Connections of the thalamus were of the highest classification weight in the Slow-4 band. Conclusions: Our findings provide preliminary evidence for frequency-specific whole brain functional connectivity indices that may eventually be used to aid detection of ASD.",
keywords = "Autism spectrum disorder, Functional connectivity, Multivariate pattern analysis, Slow-4",
author = "Heng Chen and Xujun Duan and Feng Liu and Fengmei Lu and Xujing Ma and Youxue Zhang and Uddin, {Lucina Q} and Huafu Chen",
year = "2016",
month = "1",
day = "4",
doi = "10.1016/j.pnpbp.2015.06.014",
language = "English (US)",
volume = "64",
pages = "1--9",
journal = "Progress in Neuro-Psychopharmacology and Biological Psychiatry",
issn = "0278-5846",
publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - Multivariate classification of autism spectrum disorder using frequency-specific resting-state functional connectivity-A multi-center study

AU - Chen, Heng

AU - Duan, Xujun

AU - Liu, Feng

AU - Lu, Fengmei

AU - Ma, Xujing

AU - Zhang, Youxue

AU - Uddin, Lucina Q

AU - Chen, Huafu

PY - 2016/1/4

Y1 - 2016/1/4

N2 - Background: Resting-state functional magnetic resonance imaging studies examining low frequency fluctuations (0.01-0.08. Hz) have revealed atypical whole brain functional connectivity patterns in adolescents with autism spectrum disorder (ASD), and these atypical patterns can be used to discriminate individuals with ASD from controls. However, at present it is unknown whether functional connectivity at specific frequency bands can be used to discriminate individuals with ASD from controls, and whether relationships with symptom severity are stronger in specific frequency bands. Methods: We selected 240 adolescent subjects (12-18. years old, 112 with autism spectrum disorder (101/11, males/females) and 128 healthy controls (104/24, males/females)) from 6 separate international sites in the Autism Brain Imaging Data Exchange database. Whole brain functional connectivity networks were constructed in the Slow-5 (0.01-0.027. Hz) and Slow-4 (0.027-0.073. Hz) frequency bands, which were then used as classification features. Results: An accuracy of 79.17% (p. <. 0.001) was obtained using support vector machine. Most of the discriminative features were concentrated on the Slow-4 band. In the Slow-4 band, atypical connections between the default mode network, fronto-parietal network and cingulo-opercular network were detected. A significant correlation was found between social and communication deficits as measured by the ADOS in individuals with ASD and the classification scores based on connectivity between the default mode network and the cingulo-opercular network. Connections of the thalamus were of the highest classification weight in the Slow-4 band. Conclusions: Our findings provide preliminary evidence for frequency-specific whole brain functional connectivity indices that may eventually be used to aid detection of ASD.

AB - Background: Resting-state functional magnetic resonance imaging studies examining low frequency fluctuations (0.01-0.08. Hz) have revealed atypical whole brain functional connectivity patterns in adolescents with autism spectrum disorder (ASD), and these atypical patterns can be used to discriminate individuals with ASD from controls. However, at present it is unknown whether functional connectivity at specific frequency bands can be used to discriminate individuals with ASD from controls, and whether relationships with symptom severity are stronger in specific frequency bands. Methods: We selected 240 adolescent subjects (12-18. years old, 112 with autism spectrum disorder (101/11, males/females) and 128 healthy controls (104/24, males/females)) from 6 separate international sites in the Autism Brain Imaging Data Exchange database. Whole brain functional connectivity networks were constructed in the Slow-5 (0.01-0.027. Hz) and Slow-4 (0.027-0.073. Hz) frequency bands, which were then used as classification features. Results: An accuracy of 79.17% (p. <. 0.001) was obtained using support vector machine. Most of the discriminative features were concentrated on the Slow-4 band. In the Slow-4 band, atypical connections between the default mode network, fronto-parietal network and cingulo-opercular network were detected. A significant correlation was found between social and communication deficits as measured by the ADOS in individuals with ASD and the classification scores based on connectivity between the default mode network and the cingulo-opercular network. Connections of the thalamus were of the highest classification weight in the Slow-4 band. Conclusions: Our findings provide preliminary evidence for frequency-specific whole brain functional connectivity indices that may eventually be used to aid detection of ASD.

KW - Autism spectrum disorder

KW - Functional connectivity

KW - Multivariate pattern analysis

KW - Slow-4

UR - http://www.scopus.com/inward/record.url?scp=84936804387&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84936804387&partnerID=8YFLogxK

U2 - 10.1016/j.pnpbp.2015.06.014

DO - 10.1016/j.pnpbp.2015.06.014

M3 - Article

C2 - 26148789

AN - SCOPUS:84936804387

VL - 64

SP - 1

EP - 9

JO - Progress in Neuro-Psychopharmacology and Biological Psychiatry

JF - Progress in Neuro-Psychopharmacology and Biological Psychiatry

SN - 0278-5846

ER -