Machine learning approach to identify a resting-state functional connectivity pattern serving as an endophenotype of autism spectrum disorder

Bun Yamagata, Takashi Itahashi, Junya Fujino, Haruhisa Ohta, Motoaki Nakamura, Nobumasa Kato, Masaru Mimura, Ryu ichiro Hashimoto, Yuta Aoki

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Endophenotype refers to a measurable and heritable component between genetics and diagnosis, and the same endophenotype is present in both individuals with a diagnosis and their unaffected siblings. Determination of the neural correlates of an endophenotype and diagnosis is important in autism spectrum disorder (ASD). However, prior studies enrolling individuals with ASD and their unaffected siblings have generally included only one group of typically developing (TD) subjects; they have not accounted for differences between TD siblings. Thus, they could not differentiate the neural correlates for endophenotype from the clinical diagnosis. In this context, we enrolled pairs of siblings with an ASD endophenotype (individuals with ASD and their unaffected siblings) and pairs of siblings without this endophenotype (pairs of TD siblings). Using resting-state functional MRI, we first aimed to identify an endophenotype pattern consisting of multiple functional connections (FCs) then examined the neural correlates of FCs for ASD diagnosis, controlling for differences between TD siblings. Sparse logistic regression successfully classified subjects as to the endophenotype (area under the curve = 0.78, classification accuracy = 75%). Then, a bootstrapping approach controlling for differences between TD siblings revealed that an FC between the right middle temporal gyrus and right anterior cingulate cortex was substantially different between individuals with ASD and their unaffected siblings, suggesting that this FC may be a neural correlate for the diagnosis, while the other FCs represent the endophenotype. The current findings suggest that an ASD endophenotype pattern exists in FCs, and a neural correlate for ASD diagnosis is dissociable from this endophenotype. (250 words).

Original languageEnglish
JournalBrain Imaging and Behavior
DOIs
Publication statusAccepted/In press - 2018 Jan 1

Fingerprint

Endophenotypes
Autism Spectrum Disorder
Machine Learning
Gyrus Cinguli
Temporal Lobe
Area Under Curve
Logistic Models

Keywords

  • Autism spectrum disorder
  • Endophenotype
  • Machine learning
  • Resting state
  • Unaffected siblings

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Neurology
  • Cognitive Neuroscience
  • Clinical Neurology
  • Cellular and Molecular Neuroscience
  • Psychiatry and Mental health
  • Behavioral Neuroscience

Cite this

Machine learning approach to identify a resting-state functional connectivity pattern serving as an endophenotype of autism spectrum disorder. / Yamagata, Bun; Itahashi, Takashi; Fujino, Junya; Ohta, Haruhisa; Nakamura, Motoaki; Kato, Nobumasa; Mimura, Masaru; Hashimoto, Ryu ichiro; Aoki, Yuta.

In: Brain Imaging and Behavior, 01.01.2018.

Research output: Contribution to journalArticle

Yamagata, Bun ; Itahashi, Takashi ; Fujino, Junya ; Ohta, Haruhisa ; Nakamura, Motoaki ; Kato, Nobumasa ; Mimura, Masaru ; Hashimoto, Ryu ichiro ; Aoki, Yuta. / Machine learning approach to identify a resting-state functional connectivity pattern serving as an endophenotype of autism spectrum disorder. In: Brain Imaging and Behavior. 2018.
@article{cb35187825604217997dc305d2a55aaa,
title = "Machine learning approach to identify a resting-state functional connectivity pattern serving as an endophenotype of autism spectrum disorder",
abstract = "Endophenotype refers to a measurable and heritable component between genetics and diagnosis, and the same endophenotype is present in both individuals with a diagnosis and their unaffected siblings. Determination of the neural correlates of an endophenotype and diagnosis is important in autism spectrum disorder (ASD). However, prior studies enrolling individuals with ASD and their unaffected siblings have generally included only one group of typically developing (TD) subjects; they have not accounted for differences between TD siblings. Thus, they could not differentiate the neural correlates for endophenotype from the clinical diagnosis. In this context, we enrolled pairs of siblings with an ASD endophenotype (individuals with ASD and their unaffected siblings) and pairs of siblings without this endophenotype (pairs of TD siblings). Using resting-state functional MRI, we first aimed to identify an endophenotype pattern consisting of multiple functional connections (FCs) then examined the neural correlates of FCs for ASD diagnosis, controlling for differences between TD siblings. Sparse logistic regression successfully classified subjects as to the endophenotype (area under the curve = 0.78, classification accuracy = 75{\%}). Then, a bootstrapping approach controlling for differences between TD siblings revealed that an FC between the right middle temporal gyrus and right anterior cingulate cortex was substantially different between individuals with ASD and their unaffected siblings, suggesting that this FC may be a neural correlate for the diagnosis, while the other FCs represent the endophenotype. The current findings suggest that an ASD endophenotype pattern exists in FCs, and a neural correlate for ASD diagnosis is dissociable from this endophenotype. (250 words).",
keywords = "Autism spectrum disorder, Endophenotype, Machine learning, Resting state, Unaffected siblings",
author = "Bun Yamagata and Takashi Itahashi and Junya Fujino and Haruhisa Ohta and Motoaki Nakamura and Nobumasa Kato and Masaru Mimura and Hashimoto, {Ryu ichiro} and Yuta Aoki",
year = "2018",
month = "1",
day = "1",
doi = "10.1007/s11682-018-9973-2",
language = "English",
journal = "Brain Imaging and Behavior",
issn = "1931-7557",
publisher = "Springer New York",

}

TY - JOUR

T1 - Machine learning approach to identify a resting-state functional connectivity pattern serving as an endophenotype of autism spectrum disorder

AU - Yamagata, Bun

AU - Itahashi, Takashi

AU - Fujino, Junya

AU - Ohta, Haruhisa

AU - Nakamura, Motoaki

AU - Kato, Nobumasa

AU - Mimura, Masaru

AU - Hashimoto, Ryu ichiro

AU - Aoki, Yuta

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Endophenotype refers to a measurable and heritable component between genetics and diagnosis, and the same endophenotype is present in both individuals with a diagnosis and their unaffected siblings. Determination of the neural correlates of an endophenotype and diagnosis is important in autism spectrum disorder (ASD). However, prior studies enrolling individuals with ASD and their unaffected siblings have generally included only one group of typically developing (TD) subjects; they have not accounted for differences between TD siblings. Thus, they could not differentiate the neural correlates for endophenotype from the clinical diagnosis. In this context, we enrolled pairs of siblings with an ASD endophenotype (individuals with ASD and their unaffected siblings) and pairs of siblings without this endophenotype (pairs of TD siblings). Using resting-state functional MRI, we first aimed to identify an endophenotype pattern consisting of multiple functional connections (FCs) then examined the neural correlates of FCs for ASD diagnosis, controlling for differences between TD siblings. Sparse logistic regression successfully classified subjects as to the endophenotype (area under the curve = 0.78, classification accuracy = 75%). Then, a bootstrapping approach controlling for differences between TD siblings revealed that an FC between the right middle temporal gyrus and right anterior cingulate cortex was substantially different between individuals with ASD and their unaffected siblings, suggesting that this FC may be a neural correlate for the diagnosis, while the other FCs represent the endophenotype. The current findings suggest that an ASD endophenotype pattern exists in FCs, and a neural correlate for ASD diagnosis is dissociable from this endophenotype. (250 words).

AB - Endophenotype refers to a measurable and heritable component between genetics and diagnosis, and the same endophenotype is present in both individuals with a diagnosis and their unaffected siblings. Determination of the neural correlates of an endophenotype and diagnosis is important in autism spectrum disorder (ASD). However, prior studies enrolling individuals with ASD and their unaffected siblings have generally included only one group of typically developing (TD) subjects; they have not accounted for differences between TD siblings. Thus, they could not differentiate the neural correlates for endophenotype from the clinical diagnosis. In this context, we enrolled pairs of siblings with an ASD endophenotype (individuals with ASD and their unaffected siblings) and pairs of siblings without this endophenotype (pairs of TD siblings). Using resting-state functional MRI, we first aimed to identify an endophenotype pattern consisting of multiple functional connections (FCs) then examined the neural correlates of FCs for ASD diagnosis, controlling for differences between TD siblings. Sparse logistic regression successfully classified subjects as to the endophenotype (area under the curve = 0.78, classification accuracy = 75%). Then, a bootstrapping approach controlling for differences between TD siblings revealed that an FC between the right middle temporal gyrus and right anterior cingulate cortex was substantially different between individuals with ASD and their unaffected siblings, suggesting that this FC may be a neural correlate for the diagnosis, while the other FCs represent the endophenotype. The current findings suggest that an ASD endophenotype pattern exists in FCs, and a neural correlate for ASD diagnosis is dissociable from this endophenotype. (250 words).

KW - Autism spectrum disorder

KW - Endophenotype

KW - Machine learning

KW - Resting state

KW - Unaffected siblings

UR - http://www.scopus.com/inward/record.url?scp=85054513501&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054513501&partnerID=8YFLogxK

U2 - 10.1007/s11682-018-9973-2

DO - 10.1007/s11682-018-9973-2

M3 - Article

JO - Brain Imaging and Behavior

JF - Brain Imaging and Behavior

SN - 1931-7557

ER -