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

2018 ◽  
Vol 13 (6) ◽  
pp. 1689-1698 ◽  
Author(s):  
Bun Yamagata ◽  
Takashi Itahashi ◽  
Junya Fujino ◽  
Haruhisa Ohta ◽  
Motoaki Nakamura ◽  
...  
Keyword(s):  
Machine Learning ◽  
Autism Spectrum Disorder ◽  
Functional Connectivity ◽  
Resting State ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Connectivity Pattern ◽  
Learning Approach ◽  
Resting State Functional Connectivity ◽  
Machine Learning Approach

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

2018 ◽  
Author(s):  
Bun Yamagata ◽  
Takashi Itahashi ◽  
Junya Fujino ◽  
Haruhisa Ohta ◽  
Motoaki Nakamura ◽  
...  
Keyword(s):  
Machine Learning ◽  
Autism Spectrum Disorder ◽  
Resting State ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Connectivity Pattern ◽  
Learning Approach ◽  
Functional Connections ◽  
Communication Impairment ◽  
Machine Learning Approach

AbstractEndophenotype refers to a measurable and heritable component between genetics and diagnosis and exists in both individuals with a diagnosis and their unaffected siblings. We aimed to identify a pattern of endophenotype consisted of multiple connections. We enrolled adult male individuals with autism spectrum disorder (ASD) endophenotype (i.e., individuals with ASD and their unaffected siblings) and individuals without ASD endophenotype (i.e., pairs of typical development (TD) siblings) and utilized a machine learning approach to classify people with and without endophenotypes, based on resting-state functional connections (FCs). A sparse logistic regression successfully classified people as to the endophenotype (area under the curve=0.78, classification accuracy=75%), suggesting the existence of endophenotype pattern. A binomial test identified that nine FCs were consistently selected as inputs for the classifier. The least absolute shrinkage and selection operator with these nine FCs predicted severity of communication impairment among individuals with ASD (r=0.68, p=0.021). In addition, two of the nine FCs were statistically significantly correlated with the severity of communication impairment (r=0.81, p=0.0026 and r=-0.60, p=0.049). The current findings suggest that an ASD endophenotype pattern exists in FCs with a multivariate manner and is associated with clinical ASD phenotype.

Resting-State Functional Connectivity Underlying Costly Punishment: A Machine-Learning Approach

Neuroscience ◽  
2018 ◽  
Vol 385 ◽  
pp. 25-37 ◽  
Author(s):  
Chunliang Feng ◽  
Zhiyuan Zhu ◽  
Ruolei Gu ◽  
Xia Wu ◽  
Yue-Jia Luo ◽  
...  
Keyword(s):  
Machine Learning ◽  
Functional Connectivity ◽  
Resting State ◽  
Learning Approach ◽  
Resting State Functional Connectivity ◽  
Costly Punishment ◽  
Machine Learning Approach

scholarly journals Interpretable Learning Approaches in Resting-State Functional Connectivity Analysis: The Case of Autism Spectrum Disorder

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Jinlong Hu ◽  
Lijie Cao ◽  
Tenghui Li ◽  
Bin Liao ◽  
Shoubin Dong ◽  
...  
Keyword(s):  
Neural Network ◽  
Autism Spectrum Disorder ◽  
Functional Connectivity ◽  
Resting State ◽  
Piecewise Linear ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Fmri Data ◽  
Support Vector ◽  
Resting State Functional Connectivity

Deep neural networks have recently been applied to the study of brain disorders such as autism spectrum disorder (ASD) with great success. However, the internal logics of these networks are difficult to interpret, especially with regard to how specific network architecture decisions are made. In this paper, we study an interpretable neural network model as a method to identify ASD participants from functional magnetic resonance imaging (fMRI) data and interpret results of the model in a precise and consistent manner. First, we propose an interpretable fully connected neural network (FCNN) to classify two groups, ASD versus healthy controls (HC), based on input data from resting-state functional connectivity (rsFC) between regions of interests (ROIs). The proposed FCNN model is a piecewise linear neural network (PLNN) which uses piecewise linear function LeakyReLU as its activation function. We experimentally compared the FCNN model against widely used classification models including support vector machine (SVM), random forest, and two new classes of deep neural network models in a large dataset containing 871 subjects from ABIDE I database. The results show the proposed FCNN model achieves the highest classification accuracy. Second, we further propose an interpreting method which could explain the trained model precisely with a precise linear formula for each input sample and decision features which contributed most to the classification of ASD versus HC participants in the model. We also discuss the implications of our proposed approach for fMRI data classification and interpretation.

scholarly journals Sex-dependent and sex-independent brain resting-state functional connectivity in children with autism spectrum disorder

2016 ◽  
Author(s):  
Xin Di ◽  
Bharat B Biswal
Keyword(s):  
Autism Spectrum Disorder ◽  
Functional Connectivity ◽  
Resting State ◽  
Data Exchange ◽  
Brain Regions ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Imaging Data ◽  
Resting State Functional Connectivity ◽  
Main Effects

Background: Males are more likely to suffer from autism spectrum disorder (ASD) than females. As to whether females with ASD have similar brain alterations remain an open question. The current study aimed to examine sex-dependent as well as sex-independent alterations in resting-state functional connectivity in individuals with ASD compared with typically developing (TD) individuals. Method: Resting-state functional MRI data were acquired from the Autism Brain Imaging Data Exchange (ABIDE). Subjects between 6 to 20 years of age were included for analysis. After matching the intelligence quotient between groups for each dataset, and removing subjects due to excessive head motion, the resulting effective sample contained 28 females with ASD, 49 TD females, 129 males with ASD, and 141 TD males, with a two (diagnosis) by two (sex) design. Functional connectivity among 153 regions of interest (ROIs) comprising the whole brain was computed. Two by two analysis of variance was used to identify connectivity that showed diagnosis by sex interaction or main effects of diagnosis. Results: The main effects of diagnosis were found mainly between visual cortex and other brain regions, indicating sex-independent connectivity alterations. We also observed two connections whose connectivity showed diagnosis by sex interaction between the precuneus and medial cerebellum as well as the precunes and dorsal frontal cortex. While males with ASD showed higher connectivity in these connections compared with TD males, females with ASD had lower connectivity than their counterparts. Conclusions: Both sex-dependent and sex-independent functional connectivity alterations are present in ASD.

scholarly journals Hypo- and hyper-connectivity in default mode network related to social impairment in tweens with autism spectrum disorder

2016 ◽  
Author(s):  
Wilma Matthysen ◽  
Daniele Marinazzo ◽  
Roma Siugzdaite
Keyword(s):  
Autism Spectrum Disorder ◽  
Functional Connectivity ◽  
Default Mode Network ◽  
Social Communication ◽  
Resting State ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Connectivity Pattern ◽  
Resting State Networks ◽  
Default Mode

Background. Autism spectrum disorder is a neurodevelopmental disorder, marked by impairment in social communication and restricted, repetitive patterns of behavior, interests, or activities. Accumulating data suggests that alterations in functional connectivity might contribute to these deficits. Whereas functional connectivity in resting state fMRI is expressed by several resting-state networks, for this study we examined several of them, but our particular interest was in the default mode network (DMN), given its age dependent alteration of functional connectivity and its relation to social communication. Methods. Since the studies investigating young children (6-8 years) with autism have found hypo-connectivity in DMN and studies on adolescents (12-16 years old) with autism have found hyper-connectivity in the DMN, we were interested in connectivity pattern during the age of 8 to 12, so we investigated the role of altered intrinsic connectivity in 16 children (mean age 9.75 ±1.6 years) with autism spectrum disorder compared to 16 typically developing controls in the DMN and other resting-state networks. Results. Results show that, compared to controls, the group with autism spectrum disorder showed signs of both hypo- and hyper-connectivity in different regions of the resting-state networks related to social communication. Conclusion. That suggests that transition period from childhood to adolescence carries the complexity of functional connectivity from both age groups. Regions that showed differences in functional connectivity were discussed in relation to social communication difficulties.

Resting-State Functional Connectivity in Youth With Co-Occurring Autism Spectrum Disorder and Psychotic-Like Symptoms

2020 ◽  
Vol 87 (9) ◽  
pp. S118
Author(s):  
Amandeep Jutla ◽  
Meghan Rose Donohue ◽  
Jeremy Veenstra-Vanderweele ◽  
Jennifer Foss-Feig
Keyword(s):  
Autism Spectrum Disorder ◽  
Functional Connectivity ◽  
Resting State ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Resting State Functional Connectivity
Sign in / Sign up

Export Citation Format

Share Document