Stimulus dependent neural oscillatory patterns show reliable statistical identification of Autism Spectrum Disorder in a face perceptual decision task

Publication date: Available online 20 February 2018
Source:Clinical Neurophysiology
Author(s): João Castelhano, Paula Tavares, Susana Mouga, Guiomar Oliveira, Miguel Castelo-Branco
ObjectiveElectroencephalographic biomarkers have been widely investigated in autism, in the search for diagnostic, prognostic and therapeutic outcome measures. Here we took advantage of the information available in temporal oscillatory patterns evoked by simple perceptual decisions to investigate whether stimulus dependent oscillatory signatures can be used as potential biomarkers in Autism spectrum disorder (ASD).MethodsWe studied an extensive set of stimuli (9 categories of faces) and performed data driven classification (Support vector machine, SVM) of ASD vs. Controls with features based on the EEG power responses. We carried out an extensive time-frequency and synchrony analysis of distinct face categories requiring different processing mechanisms in terms of non-holistic vs. holistic processing.ResultsWe found that the neuronal oscillatory responses of low gamma frequency band, locked to photographic and abstract two-tone (Mooney) face stimulus presentation are decreased in ASD vs. the control group. We also found decreased time-frequency (TF) responses in the beta band in ASD after 350ms, possibly related to motor preparation. On the other hand, synchrony in the 30-45Hz band showed a distinct spatial pattern in ASD. These power changes enabled accurate classification of ASD with an SVM approach. SVM accuracy was approximately 85%. ROC curves showed about 94% AUC (area under the curve). Combination of Mooney and Photographic face stimuli evoked features enabled a better separation between groups, reaching an AUC of 98.6%.ConclusionWe identified a relative decrease in EEG responses to face stimuli in ASD in the beta (15-30Hz; >350ms) and gamma (30-45Hz; 55-80Hz; 50-350ms) frequency ranges. These can be used as input of a machine learning approach to separate between groups with high accuracy.SignificanceFuture studies can use EEG time-frequency patterns evoked by particular types of faces as a diagnostic biomarker and potentially as outcome measures in therapeutic trials.



http://ift.tt/2EEfF5f