Connectivity Analysis and Feature Classification in Attention Deficit Hyperactivity Disorder Sub-Types: A Task Functional Magnetic Resonance Imaging Study

Bo yong Park, Mansu Kim, Jongbum Seo, Jong min Lee, Hyunjin Park

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Attention deficit hyperactivity disorder (ADHD) is a pervasive neuropsychiatric disorder. Patients with different ADHD subtypes show different behaviors under different stimuli and thus might require differential approaches to treatment. This study explores connectivity differences between ADHD subtypes and attempts to classify these subtypes based on neuroimaging features. A total of 34 patients (13 ADHD-IA and 21 ADHD-C subtypes) underwent functional magnetic resonance imaging (fMRI) with six task paradigms. Connectivity differences between ADHD subtypes were assessed for the whole brain in each task paradigm. Connectivity measures of the identified regions were used as features for the support vector machine classifier to distinguish between ADHD subtypes. The effectiveness of connectivity measures of the regions were tested by predicting ADHD-related Diagnostic and Statistical Manual of Mental Disorders (DSM) scores. Significant connectivity differences between ADHD subtypes were identified mainly in the frontal, cingulate, and parietal cortices and partially in the temporal, occipital cortices and cerebellum. Classifier accuracy for distinguishing between ADHD subtypes was 91.18 % for both gambling punishment and emotion task paradigms. Linear prediction under the two task paradigms showed significant correlation with DSM hyperactive/impulsive score. Our study identified important brain regions from connectivity analysis based on an fMRI paradigm using gambling punishment and emotion task paradigms. The regions and associated connectivity measures could serve as features to distinguish between ADHD subtypes.

Original languageEnglish
Pages (from-to)429-439
Number of pages11
JournalBrain Topography
Volume29
Issue number3
DOIs
Publication statusPublished - 2016 May 1

Fingerprint

Attention Deficit Disorder with Hyperactivity
Magnetic Resonance Imaging
Gambling
Punishment
Emotions
Occipital Lobe
Parietal Lobe
Gyrus Cinguli
Brain
Frontal Lobe
Temporal Lobe
Neuroimaging
Diagnostic and Statistical Manual of Mental Disorders
Cerebellum

All Science Journal Classification (ASJC) codes

  • Anatomy
  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Neurology
  • Clinical Neurology

Cite this

@article{9d9ed011bc5c4ffa9f0a909c7f5c71d1,
title = "Connectivity Analysis and Feature Classification in Attention Deficit Hyperactivity Disorder Sub-Types: A Task Functional Magnetic Resonance Imaging Study",
abstract = "Attention deficit hyperactivity disorder (ADHD) is a pervasive neuropsychiatric disorder. Patients with different ADHD subtypes show different behaviors under different stimuli and thus might require differential approaches to treatment. This study explores connectivity differences between ADHD subtypes and attempts to classify these subtypes based on neuroimaging features. A total of 34 patients (13 ADHD-IA and 21 ADHD-C subtypes) underwent functional magnetic resonance imaging (fMRI) with six task paradigms. Connectivity differences between ADHD subtypes were assessed for the whole brain in each task paradigm. Connectivity measures of the identified regions were used as features for the support vector machine classifier to distinguish between ADHD subtypes. The effectiveness of connectivity measures of the regions were tested by predicting ADHD-related Diagnostic and Statistical Manual of Mental Disorders (DSM) scores. Significant connectivity differences between ADHD subtypes were identified mainly in the frontal, cingulate, and parietal cortices and partially in the temporal, occipital cortices and cerebellum. Classifier accuracy for distinguishing between ADHD subtypes was 91.18 {\%} for both gambling punishment and emotion task paradigms. Linear prediction under the two task paradigms showed significant correlation with DSM hyperactive/impulsive score. Our study identified important brain regions from connectivity analysis based on an fMRI paradigm using gambling punishment and emotion task paradigms. The regions and associated connectivity measures could serve as features to distinguish between ADHD subtypes.",
author = "Park, {Bo yong} and Mansu Kim and Jongbum Seo and Lee, {Jong min} and Hyunjin Park",
year = "2016",
month = "5",
day = "1",
doi = "10.1007/s10548-015-0463-1",
language = "English",
volume = "29",
pages = "429--439",
journal = "Brain Topography",
issn = "0896-0267",
publisher = "Kluwer Academic/Human Sciences Press Inc.",
number = "3",

}

Connectivity Analysis and Feature Classification in Attention Deficit Hyperactivity Disorder Sub-Types : A Task Functional Magnetic Resonance Imaging Study. / Park, Bo yong; Kim, Mansu; Seo, Jongbum; Lee, Jong min; Park, Hyunjin.

In: Brain Topography, Vol. 29, No. 3, 01.05.2016, p. 429-439.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Connectivity Analysis and Feature Classification in Attention Deficit Hyperactivity Disorder Sub-Types

T2 - A Task Functional Magnetic Resonance Imaging Study

AU - Park, Bo yong

AU - Kim, Mansu

AU - Seo, Jongbum

AU - Lee, Jong min

AU - Park, Hyunjin

PY - 2016/5/1

Y1 - 2016/5/1

N2 - Attention deficit hyperactivity disorder (ADHD) is a pervasive neuropsychiatric disorder. Patients with different ADHD subtypes show different behaviors under different stimuli and thus might require differential approaches to treatment. This study explores connectivity differences between ADHD subtypes and attempts to classify these subtypes based on neuroimaging features. A total of 34 patients (13 ADHD-IA and 21 ADHD-C subtypes) underwent functional magnetic resonance imaging (fMRI) with six task paradigms. Connectivity differences between ADHD subtypes were assessed for the whole brain in each task paradigm. Connectivity measures of the identified regions were used as features for the support vector machine classifier to distinguish between ADHD subtypes. The effectiveness of connectivity measures of the regions were tested by predicting ADHD-related Diagnostic and Statistical Manual of Mental Disorders (DSM) scores. Significant connectivity differences between ADHD subtypes were identified mainly in the frontal, cingulate, and parietal cortices and partially in the temporal, occipital cortices and cerebellum. Classifier accuracy for distinguishing between ADHD subtypes was 91.18 % for both gambling punishment and emotion task paradigms. Linear prediction under the two task paradigms showed significant correlation with DSM hyperactive/impulsive score. Our study identified important brain regions from connectivity analysis based on an fMRI paradigm using gambling punishment and emotion task paradigms. The regions and associated connectivity measures could serve as features to distinguish between ADHD subtypes.

AB - Attention deficit hyperactivity disorder (ADHD) is a pervasive neuropsychiatric disorder. Patients with different ADHD subtypes show different behaviors under different stimuli and thus might require differential approaches to treatment. This study explores connectivity differences between ADHD subtypes and attempts to classify these subtypes based on neuroimaging features. A total of 34 patients (13 ADHD-IA and 21 ADHD-C subtypes) underwent functional magnetic resonance imaging (fMRI) with six task paradigms. Connectivity differences between ADHD subtypes were assessed for the whole brain in each task paradigm. Connectivity measures of the identified regions were used as features for the support vector machine classifier to distinguish between ADHD subtypes. The effectiveness of connectivity measures of the regions were tested by predicting ADHD-related Diagnostic and Statistical Manual of Mental Disorders (DSM) scores. Significant connectivity differences between ADHD subtypes were identified mainly in the frontal, cingulate, and parietal cortices and partially in the temporal, occipital cortices and cerebellum. Classifier accuracy for distinguishing between ADHD subtypes was 91.18 % for both gambling punishment and emotion task paradigms. Linear prediction under the two task paradigms showed significant correlation with DSM hyperactive/impulsive score. Our study identified important brain regions from connectivity analysis based on an fMRI paradigm using gambling punishment and emotion task paradigms. The regions and associated connectivity measures could serve as features to distinguish between ADHD subtypes.

UR - http://www.scopus.com/inward/record.url?scp=84948156131&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84948156131&partnerID=8YFLogxK

U2 - 10.1007/s10548-015-0463-1

DO - 10.1007/s10548-015-0463-1

M3 - Article

C2 - 26602102

AN - SCOPUS:84948156131

VL - 29

SP - 429

EP - 439

JO - Brain Topography

JF - Brain Topography

SN - 0896-0267

IS - 3

ER -