ADHD classification within and cross cohort using an ensembled feature selection framework

Dongren Yao, Hailun Sun, Xiaojie Guo, Vince D. Calhoun, Li Sun, Jing Sui

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Attention-deficit/hyperactivity disorder (ADHD) is a childhood-onset neurodevelopmental disorder that often persists into adulthood. However, as lacking objective measures, several studies have questioned the stability in diagnosing of ADHD from childhood to adulthood. In this study, we propose a novel feature selection framework based on functional connectivity (FCs) pattern, the so-called 'FS-RIWEL,' which could classify ADHD from age-matched healthy controls (HCs) with \sim 80% accuracy (both for children and adults). More importantly, the feature space learned from child ADHD dataset can discriminate adult ADHD from HCs at \sim 70% accuracy. To the best of our knowledge, this is the first attempt to perform a cross-cohort prediction between the adult and child ADHD using FC features. In addition, the most frequently selected FCs indicate that ADHD exhibit widely-impaired FC patterns in frontoparietal, basal ganglia, cerebellum network and so on suggesting that FCs may serve as potential biomarkers for ADHD diagnosis.

Original languageEnglish (US)
Title of host publicationISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging
PublisherIEEE Computer Society
Pages1265-1269
Number of pages5
ISBN (Electronic)9781538636411
DOIs
StatePublished - Apr 2019
Externally publishedYes
Event16th IEEE International Symposium on Biomedical Imaging, ISBI 2019 - Venice, Italy
Duration: Apr 8 2019Apr 11 2019

Publication series

NameProceedings - International Symposium on Biomedical Imaging
Volume2019-April
ISSN (Print)1945-7928
ISSN (Electronic)1945-8452

Conference

Conference16th IEEE International Symposium on Biomedical Imaging, ISBI 2019
CountryItaly
CityVenice
Period4/8/194/11/19

Fingerprint

Attention Deficit Disorder with Hyperactivity
Feature extraction
Biomarkers
Basal Ganglia
Cerebellum

Keywords

  • ADHD
  • Classification
  • Ensemble
  • Feature selection
  • Functional connectivity

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Yao, D., Sun, H., Guo, X., Calhoun, V. D., Sun, L., & Sui, J. (2019). ADHD classification within and cross cohort using an ensembled feature selection framework. In ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging (pp. 1265-1269). [8759533] (Proceedings - International Symposium on Biomedical Imaging; Vol. 2019-April). IEEE Computer Society. https://doi.org/10.1109/ISBI.2019.8759533

ADHD classification within and cross cohort using an ensembled feature selection framework. / Yao, Dongren; Sun, Hailun; Guo, Xiaojie; Calhoun, Vince D.; Sun, Li; Sui, Jing.

ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging. IEEE Computer Society, 2019. p. 1265-1269 8759533 (Proceedings - International Symposium on Biomedical Imaging; Vol. 2019-April).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yao, D, Sun, H, Guo, X, Calhoun, VD, Sun, L & Sui, J 2019, ADHD classification within and cross cohort using an ensembled feature selection framework. in ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging., 8759533, Proceedings - International Symposium on Biomedical Imaging, vol. 2019-April, IEEE Computer Society, pp. 1265-1269, 16th IEEE International Symposium on Biomedical Imaging, ISBI 2019, Venice, Italy, 4/8/19. https://doi.org/10.1109/ISBI.2019.8759533
Yao D, Sun H, Guo X, Calhoun VD, Sun L, Sui J. ADHD classification within and cross cohort using an ensembled feature selection framework. In ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging. IEEE Computer Society. 2019. p. 1265-1269. 8759533. (Proceedings - International Symposium on Biomedical Imaging). https://doi.org/10.1109/ISBI.2019.8759533
Yao, Dongren ; Sun, Hailun ; Guo, Xiaojie ; Calhoun, Vince D. ; Sun, Li ; Sui, Jing. / ADHD classification within and cross cohort using an ensembled feature selection framework. ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging. IEEE Computer Society, 2019. pp. 1265-1269 (Proceedings - International Symposium on Biomedical Imaging).
@inproceedings{63a399e4f980498eb536868288414199,
title = "ADHD classification within and cross cohort using an ensembled feature selection framework",
abstract = "Attention-deficit/hyperactivity disorder (ADHD) is a childhood-onset neurodevelopmental disorder that often persists into adulthood. However, as lacking objective measures, several studies have questioned the stability in diagnosing of ADHD from childhood to adulthood. In this study, we propose a novel feature selection framework based on functional connectivity (FCs) pattern, the so-called 'FS-RIWEL,' which could classify ADHD from age-matched healthy controls (HCs) with \sim 80{\%} accuracy (both for children and adults). More importantly, the feature space learned from child ADHD dataset can discriminate adult ADHD from HCs at \sim 70{\%} accuracy. To the best of our knowledge, this is the first attempt to perform a cross-cohort prediction between the adult and child ADHD using FC features. In addition, the most frequently selected FCs indicate that ADHD exhibit widely-impaired FC patterns in frontoparietal, basal ganglia, cerebellum network and so on suggesting that FCs may serve as potential biomarkers for ADHD diagnosis.",
keywords = "ADHD, Classification, Ensemble, Feature selection, Functional connectivity",
author = "Dongren Yao and Hailun Sun and Xiaojie Guo and Calhoun, {Vince D.} and Li Sun and Jing Sui",
year = "2019",
month = "4",
doi = "10.1109/ISBI.2019.8759533",
language = "English (US)",
series = "Proceedings - International Symposium on Biomedical Imaging",
publisher = "IEEE Computer Society",
pages = "1265--1269",
booktitle = "ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging",

}

TY - GEN

T1 - ADHD classification within and cross cohort using an ensembled feature selection framework

AU - Yao, Dongren

AU - Sun, Hailun

AU - Guo, Xiaojie

AU - Calhoun, Vince D.

AU - Sun, Li

AU - Sui, Jing

PY - 2019/4

Y1 - 2019/4

N2 - Attention-deficit/hyperactivity disorder (ADHD) is a childhood-onset neurodevelopmental disorder that often persists into adulthood. However, as lacking objective measures, several studies have questioned the stability in diagnosing of ADHD from childhood to adulthood. In this study, we propose a novel feature selection framework based on functional connectivity (FCs) pattern, the so-called 'FS-RIWEL,' which could classify ADHD from age-matched healthy controls (HCs) with \sim 80% accuracy (both for children and adults). More importantly, the feature space learned from child ADHD dataset can discriminate adult ADHD from HCs at \sim 70% accuracy. To the best of our knowledge, this is the first attempt to perform a cross-cohort prediction between the adult and child ADHD using FC features. In addition, the most frequently selected FCs indicate that ADHD exhibit widely-impaired FC patterns in frontoparietal, basal ganglia, cerebellum network and so on suggesting that FCs may serve as potential biomarkers for ADHD diagnosis.

AB - Attention-deficit/hyperactivity disorder (ADHD) is a childhood-onset neurodevelopmental disorder that often persists into adulthood. However, as lacking objective measures, several studies have questioned the stability in diagnosing of ADHD from childhood to adulthood. In this study, we propose a novel feature selection framework based on functional connectivity (FCs) pattern, the so-called 'FS-RIWEL,' which could classify ADHD from age-matched healthy controls (HCs) with \sim 80% accuracy (both for children and adults). More importantly, the feature space learned from child ADHD dataset can discriminate adult ADHD from HCs at \sim 70% accuracy. To the best of our knowledge, this is the first attempt to perform a cross-cohort prediction between the adult and child ADHD using FC features. In addition, the most frequently selected FCs indicate that ADHD exhibit widely-impaired FC patterns in frontoparietal, basal ganglia, cerebellum network and so on suggesting that FCs may serve as potential biomarkers for ADHD diagnosis.

KW - ADHD

KW - Classification

KW - Ensemble

KW - Feature selection

KW - Functional connectivity

UR - http://www.scopus.com/inward/record.url?scp=85073901823&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073901823&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2019.8759533

DO - 10.1109/ISBI.2019.8759533

M3 - Conference contribution

AN - SCOPUS:85073901823

T3 - Proceedings - International Symposium on Biomedical Imaging

SP - 1265

EP - 1269

BT - ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging

PB - IEEE Computer Society

ER -