Dataset Information

Evaluation of Altered Functional Connections in Male Children With Autism Spectrum Disorders on Multiple-Site Data Optimized With Machine Learning.

ABSTRACT: No univocal and reliable brain-based biomarkers have been detected to date in Autism Spectrum Disorders (ASD). Neuroimaging studies have consistently revealed alterations in brain structure and function of individuals with ASD; however, it remains difficult to ascertain the extent and localization of affected brain networks. In this context, the application of Machine Learning (ML) classification methods to neuroimaging data has the potential to contribute to a better distinction between subjects with ASD and typical development controls (TD). This study is focused on the analysis of resting-state fMRI data of individuals with ASD and matched TD, available within the ABIDE collection. To reduce the multiple sources of heterogeneity that impact on understanding the neural underpinnings of autistic condition, we selected a subgroup of 190 subjects (102 with ASD and 88 TD) according to the following criteria: male children (age range: 6.5-13 years); rs-fMRI data acquired with open eyes; data from the University sites that provided the largest number of scans (KKI, NYU, UCLA, UM). Connectivity values were evaluated as the linear correlation between pairs of time series of brain areas; then, a Linear kernel Support Vector Machine (L-SVM) classification, with an inter-site cross-validation scheme, was carried out. A permutation test was conducted to identify over-connectivity and under-connectivity alterations in the ASD group. The mean L-SVM classification performance, in terms of the area under the ROC curve (AUC), was 0.75 ± 0.05. The highest performance was obtained using data from KKI, NYU and UCLA sites in training and data from UM as testing set (AUC = 0.83). Specifically, stronger functional connectivity (FC) in ASD with respect to TD involve (p < 0.001) the angular gyrus with the precuneus in the right (R) hemisphere, and the R frontal operculum cortex with the pars opercularis of the left (L) inferior frontal gyrus. Weaker connections in ASD group with respect to TD are the intra-hemispheric R temporal fusiform cortex with the R hippocampus, and the L supramarginal gyrus with L planum polare. The results indicate that both under- and over-FC occurred in a selected cohort of ASD children relative to TD controls, and that these functional alterations are spread in different brain networks.

SUBMITTER: Spera G

PROVIDER: S-EPMC6763745 | biostudies-literature | 2019

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Evaluation of Altered Functional Connections in Male Children With Autism Spectrum Disorders on Multiple-Site Data Optimized With Machine Learning.

Spera Giovanna G Retico Alessandra A Bosco Paolo P Ferrari Elisa E Palumbo Letizia L Oliva Piernicola P Muratori Filippo F Calderoni Sara S

Frontiers in psychiatry 20190920

No univocal and reliable brain-based biomarkers have been detected to date in Autism Spectrum Disorders (ASD). Neuroimaging studies have consistently revealed alterations in brain structure and function of individuals with ASD; however, it remains difficult to ascertain the extent and localization of affected brain networks. In this context, the application of Machine Learning (ML) classification methods to neuroimaging data has the potential to contribute to a better distinction between subject ...[more]

PMID: 31616322

Similar Datasets

Project description:Although emerging evidence has implicated structural/functional abnormalities of patients with Autism Spectrum Disorder(ASD), definitive neuroimaging markers remain obscured due to inconsistent or incompatible findings, especially for structural imaging. Furthermore, brain differences defined by statistical analysis are difficult to implement individual prediction. The present study has employed the machine learning techniques under the unified framework in neuroimaging to identify the neuroimaging markers of patients with ASD and distinguish them from typically developing controls(TDC). To enhance the interpretability of the machine learning model, the study has processed three levels of assessments including model-level assessment, feature-level assessment, and biology-level assessment. According to these three levels assessment, the study has identified neuroimaging markers of ASD including the opercular part of bilateral inferior frontal gyrus, the orbital part of right inferior frontal gyrus, right rolandic operculum, right olfactory cortex, right gyrus rectus, right insula, left inferior parietal gyrus, bilateral supramarginal gyrus, bilateral angular gyrus, bilateral superior temporal gyrus, bilateral middle temporal gyrus, and left inferior temporal gyrus. In addition, negative correlations between the communication skill score in the Autism Diagnostic Observation Schedule (ADOS_G) and regional gray matter (GM) volume in the gyrus rectus, left middle temporal gyrus, and inferior temporal gyrus have been detected. A significant negative correlation has been found between the communication skill score in ADOS_G and the orbital part of the left inferior frontal gyrus. A negative correlation between verbal skill score and right angular gyrus and a significant negative correlation between non-verbal communication skill and right angular gyrus have been found. These findings in the study have suggested the GM alteration of ASD and correlated with the clinical severity of ASD disease symptoms. The interpretable machine learning framework gives sight to the pathophysiological mechanism of ASD but can also be extended to other diseases.

Project description:Autism spectrum disorders (ASD) affect 1% of children. Although there is no cure, early diagnosis and behavioral intervention can relieve the symptoms. The clinical heterogeneity of ASD has created a need for improved sensitive and specific laboratory diagnostic methods. Liquid chromatography-tandem mass spectrometry (LC-MS/MS)-based analysis of the metabolome has shown great potential to uncover biomarkers for complex diseases such as ASD. Here, we used a two-step discovery-validation approach to identify potential novel metabolic biomarkers for ASD. Urine samples from 57 children with ASD and 81 matched children with typical development (TD) were analyzed by LS-MS/MS to assess differences in urinary amino acids and their metabolites (referred to as UAA indicators). A total of 63 UAA indicators were identified, of which 21 were present at significantly different levels in the urine of ASD children compared with TD children. Of these 21, the concentrations of 19 and 10 were higher and lower, respectively, in the urine of ASD children compared with TD children. Using support vector machine modeling and receiver operating characteristic curve analysis, we identified a panel of 7 UAA indicators that discriminated between the samples from ASD and TD children (lysine, 2-aminoisobutyric acid, 5-hydroxytryptamine, proline, aspartate, arginine/ornithine, and 4-hydroxyproline). Among the significantly changed pathways in ASD children were the ornithine/urea cycle (decreased levels of the excitatory amino acid aspartate [p = 2.15 × 10-10] and increased arginine/ornithine [p = 5.21 × 10-9]), tryptophan metabolism (increased levels of inhibitory 5-hydroxytryptamine p = 3.62 × 10-9), the methionine cycle (increased methionine sulfoxide [p = 1.46 × 10-10] and decreased homocysteine [p = 2.73 × 10-7]), and lysine metabolism (reduced lysine [p = 7.8 × 10-9], α-aminoadipic acid [p = 1.16 × 10-9], and 5-aminovaleric acid [p = 1.05 × 10-5]). Collectively, the data presented here identify a possible imbalance between excitatory and inhibitory amino acid metabolism in ASD children. The significantly altered UAA indicators could therefore be potential diagnostic biomarkers for ASD.

Project description:Many individuals with autism spectrum disorders have comorbid epilepsy. Even in the absence of observable seizures, interictal epileptiform discharges are common in individuals with autism spectrum disorders. However, how these interictal epileptiform discharges are related to autistic symptomatology remains unclear. This study used magnetoencephalography to investigate the relation between interictal epileptiform discharges and altered functional brain networks in children with autism spectrum disorders. Instead of particularly addressing individual brain regions, we specifically examine network properties. For this case-control study, we analysed 70 children with autism spectrum disorders (52 boys, 18 girls, 38-92 months old) and 19 typically developing children (16 boys, 3 girls, 48-88 months old). After assessing the participants' social reciprocity using the Social Responsiveness Scale, we constructed graphs of functional brain networks from frequency band separated task-free magnetoencephalography recordings. Nodes corresponded to Desikan-Killiany atlas-based 68 brain regions. Edges corresponded to phase lag index values between pairs of brain regions. To elucidate the effects of the existence of interictal epileptiform discharges on graph metrics, we matched each of three pairs from three groups (typically developing children, children with autism spectrum disorders who had interictal epileptiform discharges and those who did not) in terms of age and sex. We used a coarsened exact matching algorithm and applied adjusted regression analysis. We also investigated the relation between social reciprocity and the graph metric. Results show that, in children with autism spectrum disorders, the average clustering coefficient in the theta band was significantly higher in children who had interictal epileptiform discharges. Moreover, children with autism spectrum disorders who had no interictal epileptiform discharges had a significantly lower average clustering coefficient in the theta band than typically developing children had. However, the difference between typically developing children and children with autism spectrum disorder who had interictal epileptiform discharges was not significant. Furthermore, the higher average clustering coefficient in the theta band corresponded to severe autistic symptoms in children with autism spectrum disorder who had interictal epileptiform discharges. However, the association was not significant in children with autism spectrum disorders who had no interictal epileptiform discharge. In conclusion, results demonstrate that alteration of functional brain networks in children with autism spectrum disorders depends on the existence of interictal epileptiform discharges. Interictal epileptiform discharges might 'normalize' the deviation of altered brain networks in autism spectrum disorders, increasing the clustering coefficient. However, when the effect exceeds tolerance, it actually exacerbates autistic symptoms.

Dataset Information

Evaluation of Altered Functional Connections in Male Children With Autism Spectrum Disorders on Multiple-Site Data Optimized With Machine Learning.

Publications

Evaluation of Altered Functional Connections in Male Children With Autism Spectrum Disorders on Multiple-Site Data Optimized With Machine Learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets