Evaluation of Altered Functional Connections in Male Children With Autism Spectrum Disorders on Multiple-Site Data Optimized With Machine Learning
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 o...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2019-09-01
|
| Series: | Frontiers in Psychiatry |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/article/10.3389/fpsyt.2019.00620/full |
| _version_ | 1818096830155587584 |
|---|---|
| author | Giovanna Spera Alessandra Retico Paolo Bosco Elisa Ferrari Elisa Ferrari Letizia Palumbo Piernicola Oliva Piernicola Oliva Filippo Muratori Filippo Muratori Sara Calderoni Sara Calderoni |
| author_facet | Giovanna Spera Alessandra Retico Paolo Bosco Elisa Ferrari Elisa Ferrari Letizia Palumbo Piernicola Oliva Piernicola Oliva Filippo Muratori Filippo Muratori Sara Calderoni Sara Calderoni |
| author_sort | Giovanna Spera |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-10T23:10:51Z |
| format | Article |
| id | doaj.art-fb091dd2d7a9490bb4b3e695f97e637b |
| institution | Directory Open Access Journal |
| issn | 1664-0640 |
| language | English |
| last_indexed | 2024-12-10T23:10:51Z |
| publishDate | 2019-09-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Psychiatry |
| spelling | doaj.art-fb091dd2d7a9490bb4b3e695f97e637b2022-12-22T01:29:57ZengFrontiers Media S.A.Frontiers in Psychiatry1664-06402019-09-011010.3389/fpsyt.2019.00620459067Evaluation of Altered Functional Connections in Male Children With Autism Spectrum Disorders on Multiple-Site Data Optimized With Machine LearningGiovanna Spera0Alessandra Retico1Paolo Bosco2Elisa Ferrari3Elisa Ferrari4Letizia Palumbo5Piernicola Oliva6Piernicola Oliva7Filippo Muratori8Filippo Muratori9Sara Calderoni10Sara Calderoni11National Institute for Nuclear Physics (INFN), Pisa Division, Pisa, ItalyNational Institute for Nuclear Physics (INFN), Pisa Division, Pisa, ItalyIRCCS Stella Maris Foundation, Pisa, ItalyNational Institute for Nuclear Physics (INFN), Pisa Division, Pisa, ItalyScuola Normale Superiore, Faculty of Sciences, Pisa, ItalyNational Institute for Nuclear Physics (INFN), Pisa Division, Pisa, ItalyDepartment of Chemistry, and Pharmacy, University of Sassari, Sassari, ItalyNational Institute for Nuclear Physics (INFN), Cagliari Division, Cagliari, ItalyIRCCS Stella Maris Foundation, Pisa, ItalyDepartment of Clinical and Experimental Medicine, University of Pisa, Pisa, ItalyIRCCS Stella Maris Foundation, Pisa, ItalyDepartment of Clinical and Experimental Medicine, University of Pisa, Pisa, ItalyNo 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.https://www.frontiersin.org/article/10.3389/fpsyt.2019.00620/fullautism spectrum disorderschildrenresting-state fMRIfunctional connectivitymachine learningABIDE |
| spellingShingle | Giovanna Spera Alessandra Retico Paolo Bosco Elisa Ferrari Elisa Ferrari Letizia Palumbo Piernicola Oliva Piernicola Oliva Filippo Muratori Filippo Muratori Sara Calderoni Sara Calderoni Evaluation of Altered Functional Connections in Male Children With Autism Spectrum Disorders on Multiple-Site Data Optimized With Machine Learning Frontiers in Psychiatry autism spectrum disorders children resting-state fMRI functional connectivity machine learning ABIDE |
| title | Evaluation of Altered Functional Connections in Male Children With Autism Spectrum Disorders on Multiple-Site Data Optimized With Machine Learning |
| title_full | Evaluation of Altered Functional Connections in Male Children With Autism Spectrum Disorders on Multiple-Site Data Optimized With Machine Learning |
| title_fullStr | Evaluation of Altered Functional Connections in Male Children With Autism Spectrum Disorders on Multiple-Site Data Optimized With Machine Learning |
| title_full_unstemmed | Evaluation of Altered Functional Connections in Male Children With Autism Spectrum Disorders on Multiple-Site Data Optimized With Machine Learning |
| title_short | Evaluation of Altered Functional Connections in Male Children With Autism Spectrum Disorders on Multiple-Site Data Optimized With Machine Learning |
| title_sort | evaluation of altered functional connections in male children with autism spectrum disorders on multiple site data optimized with machine learning |
| topic | autism spectrum disorders children resting-state fMRI functional connectivity machine learning ABIDE |
| url | https://www.frontiersin.org/article/10.3389/fpsyt.2019.00620/full |
| work_keys_str_mv | AT giovannaspera evaluationofalteredfunctionalconnectionsinmalechildrenwithautismspectrumdisordersonmultiplesitedataoptimizedwithmachinelearning AT alessandraretico evaluationofalteredfunctionalconnectionsinmalechildrenwithautismspectrumdisordersonmultiplesitedataoptimizedwithmachinelearning AT paolobosco evaluationofalteredfunctionalconnectionsinmalechildrenwithautismspectrumdisordersonmultiplesitedataoptimizedwithmachinelearning AT elisaferrari evaluationofalteredfunctionalconnectionsinmalechildrenwithautismspectrumdisordersonmultiplesitedataoptimizedwithmachinelearning AT elisaferrari evaluationofalteredfunctionalconnectionsinmalechildrenwithautismspectrumdisordersonmultiplesitedataoptimizedwithmachinelearning AT letiziapalumbo evaluationofalteredfunctionalconnectionsinmalechildrenwithautismspectrumdisordersonmultiplesitedataoptimizedwithmachinelearning AT piernicolaoliva evaluationofalteredfunctionalconnectionsinmalechildrenwithautismspectrumdisordersonmultiplesitedataoptimizedwithmachinelearning AT piernicolaoliva evaluationofalteredfunctionalconnectionsinmalechildrenwithautismspectrumdisordersonmultiplesitedataoptimizedwithmachinelearning AT filippomuratori evaluationofalteredfunctionalconnectionsinmalechildrenwithautismspectrumdisordersonmultiplesitedataoptimizedwithmachinelearning AT filippomuratori evaluationofalteredfunctionalconnectionsinmalechildrenwithautismspectrumdisordersonmultiplesitedataoptimizedwithmachinelearning AT saracalderoni evaluationofalteredfunctionalconnectionsinmalechildrenwithautismspectrumdisordersonmultiplesitedataoptimizedwithmachinelearning AT saracalderoni evaluationofalteredfunctionalconnectionsinmalechildrenwithautismspectrumdisordersonmultiplesitedataoptimizedwithmachinelearning |