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, Xiaoli; Zhang, Youxue; Uddin, Lucina Q.; Chen, Huafu

doi:10.1016/j.pnpbp.2015.06.014

Cited by 173 publications

(140 citation statements)

References 98 publications

Supporting

Mentioning

129

Contrasting

Order By: Relevance

“…Due to their lower complexity, linear classifiers are also less prone to overfitting than some non-linear classifiers. This might explain the success of linear classifiers for RS-fMRI-based ASD prediction (13, 14, 36). In the remainder of this section, we discuss several linear classifiers [(regularized) logistic regression, linear SVMs, and linear discriminant analysis (LDA)], as well as several non-linear classifiers (Figure 4B), including Gaussian naïve Bayes (GNB), kernel SVMs, and probabilistic neural networks.…”

Section: Classifiersmentioning

confidence: 94%

“…All presented classifiers are pre-implemented, easy-to-use, and commonly used for the classification of RS-fMRI data (13, 14, 36). We refer to James et al (24), Hastie et al (38), and Bishop (39) for more details on the presented classifiers.…”

Section: Classifiersmentioning

confidence: 99%

“…Previous RS-fMRI ASD classification studies have seen a considerable drop in classification accuracy when switching from single-site to multisite data (11, 12). Nevertheless, recent multisite ASD classification studies based on RS-fMRI have shown that the disorder can be predicted with accuracies between 60 and 79% (12–14). …”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Promises, Pitfalls, and Basic Guidelines for Applying Machine Learning Classifiers to Psychiatric Imaging Data, with Autism as an Example

et al. 2016

View full text Add to dashboard Cite

Most psychiatric disorders are associated with subtle alterations in brain function and are subject to large interindividual differences. Typically, the diagnosis of these disorders requires time-consuming behavioral assessments administered by a multidisciplinary team with extensive experience. While the application of Machine Learning classification methods (ML classifiers) to neuroimaging data has the potential to speed and simplify diagnosis of psychiatric disorders, the methods, assumptions, and analytical steps are currently opaque and not accessible to researchers and clinicians outside the field. In this paper, we describe potential classification pipelines for autism spectrum disorder, as an example of a psychiatric disorder. The analyses are based on resting-state fMRI data derived from a multisite data repository (ABIDE). We compare several popular ML classifiers such as support vector machines, neural networks, and regression approaches, among others. In a tutorial style, written to be equally accessible for researchers and clinicians, we explain the rationale of each classification approach, clarify the underlying assumptions, and discuss possible pitfalls and challenges. We also provide the data as well as the MATLAB code we used to achieve our results. We show that out-of-the-box ML classifiers can yield classification accuracies of about 60–70%. Finally, we discuss how classification accuracy can be further improved, and we mention methodological developments that are needed to pave the way for the use of ML classifiers in clinical practice.

show abstract

Section: Classifiersmentioning

confidence: 94%

Section: Classifiersmentioning

confidence: 99%

See 1 more Smart Citation

Promises, Pitfalls, and Basic Guidelines for Applying Machine Learning Classifiers to Psychiatric Imaging Data, with Autism as an Example

et al. 2016

View full text Add to dashboard Cite

show abstract

“…It has been reported to occur in about 1% of children, resulting in immense suffering to patients and also burden to their families (Kim et al, ; Lai, Lombardo, & Baron‐Cohen, ). Recent machine learning based studies advanced the discovery of new neuroimaging‐based biomarkers for computer‐aided ASD diagnosis (Chen et al, ; Chen, Duan, et al, ; Cheng et al, ; Guo et al, ; Iidaka, ; Nielsen, Zielinski, Fletcher, Alexander, Lange, Bigler, Lainhart, & Anderson, ; Plitt, Barnes, & Martin, ; Price, Wee, Gao, & Shen, ; Wee, Yap, & Shen, ).…”

Section: Introductionmentioning

confidence: 99%

Enhancing the representation of functional connectivity networks by fusing multi‐view information for autism spectrum disorder diagnosis

Huang

Liu

Jin

et al. 2018

Human Brain Mapping

View full text Add to dashboard Cite

Functional connectivity network provides novel insights on how distributed brain regions are functionally integrated, and its deviations from healthy brain have recently been employed to identify biomarkers for neuropsychiatric disorders. However, most of brain network analysis methods utilized features extracted only from one functional connectivity network for brain disease detection and cannot provide a comprehensive representation on the subtle disruptions of brain functional organization induced by neuropsychiatric disorders. Inspired by the principles of multi‐view learning which utilizes information from multiple views to enhance object representation, we propose a novel multiple network based framework to enhance the representation of functional connectivity networks by fusing the common and complementary information conveyed in multiple networks. Specifically, four functional connectivity networks corresponding to the four adjacent values of regularization parameter are generated via a sparse regression model with group constraint ( l2,1‐norm), to enhance the common intrinsic topological structure and limit the error rate caused by different views. To obtain a set of more meaningful and discriminative features, we propose using a modified version of weighted clustering coefficients to quantify the subtle differences of each group‐sparse network at local level. We then linearly fuse the selected features from each individual network via a multi‐kernel support vector machine for autism spectrum disorder (ASD) diagnosis. The proposed framework achieves an accuracy of 79.35%, outperforming all the compared single network methods for at least 7% improvement. Moreover, compared with other multiple network methods, our method also achieves the best performance, that is, with at least 11% improvement in accuracy.

show abstract

“…In recent years, resting-state functional magnetic resonance imaging (rsfMRI), which examines the spontaneous low-frequency fluctuations (LFF) in blood oxygenation level dependent (BOLD) signals15, has emerged as a new avenue to explore the pathophysiology underlying neurologic and psychiatric diseases1617. LFF has been validated to reflect the spontaneous neural activity (SNA)1819 and has been consistently reported to be correlated with electroneurophysiological activity, such as local filed potentials1820, indicating that LFF might serve as a meaningful indicator for SNA in the brain2122.…”

mentioning

confidence: 99%

Atypical developmental trajectory of local spontaneous brain activity in autism spectrum disorder

Guo

Chen

Long

et al. 2017

Sci Rep

Self Cite

View full text Add to dashboard Cite

Autism spectrum disorder (ASD) is marked by atypical trajectory of brain maturation, yet the developmental abnormalities in brain function remain unclear. The current study examined the effect of age on amplitude of low-frequency fluctuations (ALFF) in ASD and typical controls (TC) using a cross-sectional design. We classified all the participants into three age cohorts: child (<11 years, 18ASD/20TC), adolescent (11–18 years, 28ASD/26TC) and adult (≥18 years, 18ASD/18TC). Two-way analysis of variance (ANOVA) was performed to ascertain main effects and interaction effects on whole brain ALFF maps. Results exhibited significant main effect of diagnosis in ASD with decreased ALFF in the right precuneus and left middle occipital gyrus during all developmental stages. Significant diagnosis-by-age interaction was observed in the medial prefrontal cortex (mPFC) with ALFF lowered in autistic children but highered in autistic adolescents and adults. Specifically, remarkable quadratic change of ALFF with increasing age in mPFC presented in TC group was absent in ASD. Additionally, abnormal ALFF values in diagnosis-related brain regions predicted the social deficits in ASD. Our findings indicated aberrant developmental patterns of spontaneous brain activity associated with social deficits in ASD and highlight the crucial role of the default mode network in the development of disease.

show abstract

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

Cited by 173 publications

References 98 publications

Promises, Pitfalls, and Basic Guidelines for Applying Machine Learning Classifiers to Psychiatric Imaging Data, with Autism as an Example

Promises, Pitfalls, and Basic Guidelines for Applying Machine Learning Classifiers to Psychiatric Imaging Data, with Autism as an Example

Enhancing the representation of functional connectivity networks by fusing multi‐view information for autism spectrum disorder diagnosis

Atypical developmental trajectory of local spontaneous brain activity in autism spectrum disorder

Contact Info

Product

Resources

About