Classification of ADHD Individuals and Neurotypicals Using Reliable RELIEF: A Resting-State Study

B. Miao; L. L. Zhang; J. L. Guan; Q. F. Meng; Y. L. Zhang

doi:10.1109/ACCESS.2019.2915988

Classification of ADHD Individuals and Neurotypicals Using Reliable RELIEF: A Resting-State Study

B. Miao, L. L. Zhang, J. L. Guan, Q. F. Meng, Y. L. Zhang

Research output: Contribution to journal › Article › peer-review

35 Citations (Scopus)

Abstract

Fractional amplitude of low-frequency fluctuation (fALFF) can reflect the intensity of spontaneous neuronal activity. Feature selection on functional magnetic resonance imaging (fMRI) data combined with fALFF can be well used to study the pathology of attention deficit hyperactivity disorder (ADHD) and assist in its diagnosis. However, the unsatisfactory effect of feature selection limits the study of ADHD. In this study, a novel method is proposed to classify ADHD individuals and neurotypicals. This work introduces multiple linear regressions for reduction of confounding effects. After that, fALFF combined with principal component analysis (PCA), Shannon entropy (ShEn), and sample entropy (SampEn) are used to construct features, and a reliable RELIEF (R-RELIEF) algorithm is proposed to find the most prominent features. Public ADHD-200 dataset is used in this study to evaluate our method. The results in this study suggest that fALFF is a reliable fMRI marker for investigation of ADHD, and R-RELIEF shows good performance compared with RELIEF algorithm. Moreover, fALFF of many brain regions are found to differ between ADHD and neurotypicals, thus coinciding with the results of previous studies.

Original language	English
Article number	8710305
Pages (from-to)	62163-62171
Number of pages	9
Journal	IEEE Access
Volume	7
DOIs	https://doi.org/10.1109/ACCESS.2019.2915988
Publication status	Published - 9 May 2019
Externally published	Yes

Access to Document

10.1109/ACCESS.2019.2915988

Cite this

@article{afb8ebd7f6f44d2e905def51c6e21dec,

title = "Classification of ADHD Individuals and Neurotypicals Using Reliable RELIEF: A Resting-State Study",

abstract = "Fractional amplitude of low-frequency fluctuation (fALFF) can reflect the intensity of spontaneous neuronal activity. Feature selection on functional magnetic resonance imaging (fMRI) data combined with fALFF can be well used to study the pathology of attention deficit hyperactivity disorder (ADHD) and assist in its diagnosis. However, the unsatisfactory effect of feature selection limits the study of ADHD. In this study, a novel method is proposed to classify ADHD individuals and neurotypicals. This work introduces multiple linear regressions for reduction of confounding effects. After that, fALFF combined with principal component analysis (PCA), Shannon entropy (ShEn), and sample entropy (SampEn) are used to construct features, and a reliable RELIEF (R-RELIEF) algorithm is proposed to find the most prominent features. Public ADHD-200 dataset is used in this study to evaluate our method. The results in this study suggest that fALFF is a reliable fMRI marker for investigation of ADHD, and R-RELIEF shows good performance compared with RELIEF algorithm. Moreover, fALFF of many brain regions are found to differ between ADHD and neurotypicals, thus coinciding with the results of previous studies.",

keywords = "Functional magnetic resonance imaging, Feature extraction, Principal component analysis, Reliability, Linear regression, Entropy, Deep learning",

author = "B. Miao and Zhang, {L. L.} and Guan, {J. L.} and Meng, {Q. F.} and Zhang, {Y. L.}",

year = "2019",

month = may,

day = "9",

doi = "10.1109/ACCESS.2019.2915988",

language = "English",

volume = "7",

pages = "62163--62171",

journal = "IEEE Access",

issn = "2169-3536",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

}

TY - JOUR

T1 - Classification of ADHD Individuals and Neurotypicals Using Reliable RELIEF: A Resting-State Study

AU - Miao, B.

AU - Zhang, L. L.

AU - Guan, J. L.

AU - Meng, Q. F.

AU - Zhang, Y. L.

PY - 2019/5/9

Y1 - 2019/5/9

N2 - Fractional amplitude of low-frequency fluctuation (fALFF) can reflect the intensity of spontaneous neuronal activity. Feature selection on functional magnetic resonance imaging (fMRI) data combined with fALFF can be well used to study the pathology of attention deficit hyperactivity disorder (ADHD) and assist in its diagnosis. However, the unsatisfactory effect of feature selection limits the study of ADHD. In this study, a novel method is proposed to classify ADHD individuals and neurotypicals. This work introduces multiple linear regressions for reduction of confounding effects. After that, fALFF combined with principal component analysis (PCA), Shannon entropy (ShEn), and sample entropy (SampEn) are used to construct features, and a reliable RELIEF (R-RELIEF) algorithm is proposed to find the most prominent features. Public ADHD-200 dataset is used in this study to evaluate our method. The results in this study suggest that fALFF is a reliable fMRI marker for investigation of ADHD, and R-RELIEF shows good performance compared with RELIEF algorithm. Moreover, fALFF of many brain regions are found to differ between ADHD and neurotypicals, thus coinciding with the results of previous studies.

AB - Fractional amplitude of low-frequency fluctuation (fALFF) can reflect the intensity of spontaneous neuronal activity. Feature selection on functional magnetic resonance imaging (fMRI) data combined with fALFF can be well used to study the pathology of attention deficit hyperactivity disorder (ADHD) and assist in its diagnosis. However, the unsatisfactory effect of feature selection limits the study of ADHD. In this study, a novel method is proposed to classify ADHD individuals and neurotypicals. This work introduces multiple linear regressions for reduction of confounding effects. After that, fALFF combined with principal component analysis (PCA), Shannon entropy (ShEn), and sample entropy (SampEn) are used to construct features, and a reliable RELIEF (R-RELIEF) algorithm is proposed to find the most prominent features. Public ADHD-200 dataset is used in this study to evaluate our method. The results in this study suggest that fALFF is a reliable fMRI marker for investigation of ADHD, and R-RELIEF shows good performance compared with RELIEF algorithm. Moreover, fALFF of many brain regions are found to differ between ADHD and neurotypicals, thus coinciding with the results of previous studies.

KW - Functional magnetic resonance imaging

KW - Feature extraction

KW - Principal component analysis

KW - Reliability

KW - Linear regression

KW - Entropy

KW - Deep learning

UR - http://www.scopus.com/inward/record.url?scp=85066847515&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2019.2915988

DO - 10.1109/ACCESS.2019.2915988

M3 - Article

SN - 2169-3536

VL - 7

SP - 62163

EP - 62171

JO - IEEE Access

JF - IEEE Access

M1 - 8710305

ER -

Classification of ADHD Individuals and Neurotypicals Using Reliable RELIEF: A Resting-State Study

Abstract

Access to Document

Other files and links

Fingerprint

Cite this