Autism Spectrum Disorder and Childhood Apraxia of Speech: Early Language-Related Hallmarks across Structural MRI Study.

Autism Spectrum Disorder (ASD) and Childhood Apraxia of Speech (CAS) are developmental disorders with distinct diagnostic criteria and different epidemiology. However, a common genetic background as well as overlapping clinical features between ASD and CAS have been recently reported. To date, brain structural language-related abnormalities have been detected in both the conditions, but no study directly compared young children with ASD, CAS and typical development (TD). In the current work, we aim: (i) to test the hypothesis that ASD and CAS display neurostructural differences in comparison with TD through morphometric Magnetic Resonance Imaging (MRI)-based measures (ASD vs. TD and CAS vs. TD); (ii) to investigate early possible disease-specific brain structural patterns in the two clinical groups (ASD vs. CAS); (iii) to evaluate predictive power of machine-learning (ML) techniques in differentiating the three samples (ASD, CAS, TD). We retrospectively analyzed the T1-weighted brain MRI scans of 68 children (age range: 34-74 months) grouped into three cohorts: (1) 26 children with ASD (mean age ± standard deviation: 56 ± 11 months); (2) 24 children with CAS (57 ± 10 months); (3) 18 children with TD (55 ± 13 months). Furthermore, a ML analysis based on a linear-kernel Support Vector Machine (SVM) was performed. All but one brain structures displayed significant higher volumes in both ASD and CAS children than TD peers. Specifically, ASD alterations involved fronto-temporal regions together with basal ganglia and cerebellum, while CAS alterations are more focused and shifted to frontal regions, suggesting a possible speech-related anomalies distribution. Caudate, superior temporal and hippocampus volumes directly distinguished the two conditions in terms of greater values in ASD compared to CAS. The ML analysis identified significant differences in brain features between ASD and TD children, whereas only some trends in the ML classification capability were detected in CAS as compared to TD peers. Similarly, the MRI structural underpinnings of two clinical groups were not significantly different when evaluated with linear-kernel SVM. Our results may represent the first step towards understanding shared and specific neural substrate in ASD and CAS conditions, which subsequently may contribute to early differential diagnosis and tailoring specific early intervention.

Dealing with confounders and outliers in classification medical studies: The Autism Spectrum Disorders case study.

Machine learning (ML) approaches have been widely applied to medical data in order to find reliable classifiers to improve diagnosis and detect candidate biomarkers of a disease. However, as a powerful, multivariate, data-driven approach, ML can be misled by biases and outliers in the training set, finding sample-dependent classification patterns. This phenomenon often occurs in biomedical applications in which, due to the scarcity of the data, combined with their heterogeneous nature and complex acquisition process, outliers and biases are very common. In this work we present a new workflow for biomedical research based on ML approaches, that maximizes the generalizability of the classification. This workflow is based on the adoption of two data selection tools: an autoencoder to identify the outliers and the Confounding Index, to understand which characteristics of the sample can mislead classification. As a study-case we adopt the controversial research about extracting brain structural biomarkers of Autism Spectrum Disorders (ASD) from magnetic resonance images. A classifier trained on a dataset composed by 86 subjects, selected using this framework, obtained an area under the receiver operating characteristic curve of 0.79. The feature pattern identified by this classifier is still able to capture the mean differences between the ASD and Typically Developing Control classes on 1460 new subjects in the same age range of the training set, thus providing new insights on the brain characteristics of ASD. In this work, we show that the proposed workflow allows to find generalizable patterns even if the dataset is limited, while skipping the two mentioned steps and using a larger but not well designed training set would have produced a sample-dependent classifier.

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 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.