Stimulus dependent neural oscillatory patterns show reliable statistical identification of autism spectrum disorder in a face perceptual decision task

Neuroanatomical Predictors of Transcranial Direct Current Stimulation (tDCS)-Induced Modifications in Neurocognitive Task Performance in Typically Developing Individuals

Transcranial direct current stimulation (tDCS) is a noninvasive neuromodulation technique gaining more attention in neurodevelopmental disorders (NDDs). Due to the phenotypic heterogeneity of NDDs, tDCS is unlikely to be equally effective in all individuals. The present study aimed to establish neuroanatomical markers in typically developing (TD) individuals that may be used for the prediction of individual responses to tDCS. Fifty-seven male and female children received 2 mA anodal and sham tDCS, targeting the left dorsolateral prefrontal cortex (DLPFCleft), right inferior frontal gyrus, and bilateral temporoparietal junction. Response to tDCS was assessed based on task performance differences between anodal and sham tDCS in different neurocognitive tasks (N-back, flanker, Mooney faces detection, attentional emotional recognition task). Measures of cortical thickness (CT) and surface area (SA) were derived from 3 Tesla structural MRI scans. Associations between neuroanatomy and task performance were assessed using general linear models (GLM). Machine learning (ML) algorithms were employed to predict responses to tDCS. Vertex-wise estimates of SA were more closely linked to differences in task performance than measures of CT. Across ML algorithms, highest accuracies were observed for the prediction of N-back task performance differences following stimulation of the DLPFCleft, where 65% of behavioral variance was explained by variability in SA. Lower accuracies were observed for all other tasks and stimulated regions. This suggests that it may be possible to predict individual responses to tDCS for some behavioral measures and target regions. In the future, these models might be extended to predict treatment outcome in individuals with NDDs.

Autistic traits specific to communication ability are associated with performance on a Mooney face detection task

Difficulties in global face processing have been associated with autism. However, autism is heterogenous, and it is not known which dimensions of autistic traits are implicated in face-processing difficulties. To address this gap in knowledge, we conducted two experiments to examine how identification of Mooney face stimuli (stylized, black-and-white images of faces without details) related to the six subscales of the Comprehensive Autistic Trait Inventory in young adults. In Experiment 1, regression analyses indicated that participants with poorer communication skills had lower task sensitivity when discriminating between face-present and face-absent images, whilst other autistic traits had no unique predictive value. Experiment 2 replicated these findings and additionally showed that autistic traits were linked to a reduced face inversion effect. Taken together, these results indicate autistic traits, especially communication difficulties, are associated with reduced configural processing of face stimuli. It follows that both reduced sensitivity for identifying upright faces amongst similar-looking distractors and reduced susceptibility to face inversion effects may be linked to relatively decreased reliance on configural processing of faces in autism. This study also reinforces the need to consider the different facets of autism independently.

Investigating the Face Inversion Effect in Autism Across Behavioral and Neural Measures of Face Processing: A Systematic Review and Bayesian Meta-Analysis

Importance

Face processing is foundational to human social cognition, is central to the hallmark features of autism spectrum disorder (ASD), and shapes neural systems and social behavior. Highly efficient and specialized, the face processing system is sensitive to inversion, demonstrated by reduced accuracy in recognition and altered neural response to inverted faces. Understanding at which mechanistic level the autistic face processing system may be particularly different, as measured by the face inversion effect, will improve overall understanding of brain functioning in autism.

Objective

To synthesize data from the extant literature to determine differences of the face processing system in ASD, as measured by the face inversion effect, across multiple mechanistic levels.

Data Sources

Systematic searches were conducted in the MEDLINE, Embase, Web of Science, and PubMed databases from inception to August 11, 2022.

Study Selection

Original research that reported performance-based measures of face recognition to upright and inverted faces in ASD and neurotypical samples were included for quantitative synthesis. All studies were screened by at least 2 reviewers.

Data Extraction and Synthesis

This systematic review and meta-analysis was conducted according to the 2020 Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) reporting guideline. Multiple effect sizes were extracted from studies to maximize information gain and statistical precision and used a random-effects, multilevel modeling framework to account for statistical dependencies within study samples.

Main Outcomes and Measures

Effect sizes were calculated as a standardized mean change score between ASD and neurotypical samples (ie, Hedges g). The primary outcome measure was performance difference between upright and inverted faces during face recognition tasks. Measurement modality, psychological construct, recognition demand, sample age, sample sex distribution, and study quality assessment scores were assessed as moderators.

Results

Of 1768 screened articles, 122 effect sizes from 38 empirical articles representing data from 1764 individual participants (899 ASD individuals and 865 neurotypical individuals) were included in the meta-analysis. Overall, face recognition performance differences between upright and inverted faces were reduced in autistic individuals compared with neurotypical individuals (g = -0.41; SE = 0.11; 95% credible interval [CrI], -0.63 to -0.18). However, there was considerable heterogeneity among effect sizes, which were explored with moderator analysis. The attenuated face inversion effect in autistic individuals was more prominent in emotion compared with identity recognition (b = 0.46; SE = 0.26; 95% CrI, -0.08 to 0.95) and in behavioral compared with electrophysiological measures (b = 0.23; SE = 0.24; 95% CrI, -0.25 to 0.70).

Conclusions and Relevance

This study found that on average, face recognition in autism is less impacted by inversion. These findings suggest less specialization or expertise of the face processing system in autism, particularly in recognizing emotion from faces as measured in behavioral paradigms.

Evaluation of interpretability for deep learning algorithms in EEG emotion recognition: A case study in autism

Current models on Explainable Artificial Intelligence (XAI) have shown a lack of reliability when evaluating feature-relevance for deep neural biomarker classifiers. The inclusion of reliable saliency-maps for obtaining trustworthy and interpretable neural activity is still insufficiently mature for practical applications. These limitations impede the development of clinical applications of Deep Learning. To address, these limitations we propose the RemOve-And-Retrain (ROAR) algorithm which supports the recovery of highly relevant features from any pre-trained deep neural network. In this study we evaluated the ROAR methodology and algorithm for the Face Emotion Recognition (FER) task, which is clinically applicable in the study of Autism Spectrum Disorder (ASD). We trained a Convolutional Neural Network (CNN) from electroencephalography (EEG) signals and assessed the relevance of FER-elicited EEG features from individuals diagnosed with and without ASD. Specifically, we compared the ROAR reliability from well-known relevance maps such as Layer-Wise Relevance Propagation, PatternNet, Pattern-Attribution, and Smooth-Grad Squared. This study is the first to bridge previous neuroscience and ASD research findings to feature-relevance calculation for EEG-based emotion recognition with CNN in typically-development (TD) and in ASD individuals.

A randomized cross-over trial investigating the neurocognitive effects of acute exercise on face recognition in children with autism spectrum disorder

Difficulties in face recognition contribute to social-cognitive problems in autistic children. Evidence on behavioral interventions targeting this cognitive domain is limited. In non-autistic individuals, a single exercise session is known to elicit temporary benefits for several cognitive functions. Our study investigates whether acute aerobic exercise influences face recognition in autistic children. In a randomized order, 29 participants completed a 20-min moderately-intense cycling bout on an ergometer and a control condition. Before and after each condition, participants categorized Mooney faces and instruments during a computerized cognitive task. Simultaneously, the N170 component of event-related potentials and pupil size were recorded using electroencephalography and eyetracking, respectively. As indicated by a greater increase of reaction time in the exercise compared to the control condition, the results revealed impaired face recognition following aerobic exercise. This effect was accompanied by a lower decrease of the positive N170 amplitude and a trend towards a greater constriction of the pupil size in the exercise compared to the control condition. Our findings highlight the interplay of the physiological state and face recognition in autistic children. Exercise-induced impairments in this social-cognitive ability may be due to an interference with the learning effect that is typically seen for the structural encoding of faces.

Machine learning approaches for electroencephalography and magnetoencephalography analyses in autism spectrum disorder: A systematic review

There are growing application of machine learning models to study the intricacies of non-linear and non-stationary characteristics of electroencephalography (EEG) and magnetoencephalography (MEG) data in neurobiologically complex and heterogeneous conditions such as autism spectrum disorder (ASD). Such tools have potential diagnostic applications, and given the highly heterogeneous presentation of ASD, might prove fruitful in early detection and therefore could facilitate very early intervention. We conducted a systematic review (PROSPERO ID#CRD42021257438) by searching PubMed, EMBASE, and PsychINFO for machine learning approaches for EEG and MEG analyses in ASD. Thirty-nine studies were identified, of which the majority (18) used support vector machines for classification; other successful methods included deep learning. Thirty-seven studies were found to employ EEG and two were found to employ MEG. This systematic review indicate that machine learning methods can be used to classify ASD, predict ASD diagnosis in high-risk infants as early as 3 months of age, predict ASD symptom severity, and classify states of cognition in ASD with high accuracy. Replication studies testing validity, reproducibility and generalizability in tandem with randomized controlled trials in ASD populations will likely benefit the field.

Effects of anodal multichannel transcranial direct current stimulation (tDCS) on social-cognitive performance in healthy subjects: A randomized sham-controlled crossover pilot study

Recent studies suggest that temporoparietal junction (TPJ) modulation can influence attention and social cognition performance. Nevertheless, no studies have used multichannel transcranial direct current stimulation (tDCS) over bilateral TPJ to estimate the effects on these neuropsychological functions. The project STIPED is using optimized multichannel stimulation as an innovative treatment approach for chronic pediatric neurodevelopmental disorders, namely in children/adolescents with Autism Spectrum Disorder (ASD). In this pilot study, we aim to explore whether anodal multichannel tDCS coupled with a Joint Attention Task (JAT) influences social-cognitive task performance relative to sham stimulation, both in an Emotion Recognition Task (ERT) and in a Mooney Faces Detection Task (MFDT), as well as to evaluate this technique's safety and tolerability. Twenty healthy adults were enrolled in a randomized, single-blinded, sham-controlled, crossover study. During two sessions, participants completed the ERT and the MFDT before and after 20min of sham or anodal tDCS over bilateral TPJ. No significant differences on performance accuracy and reaction time were found between stimulation conditions for all tasks, including the JAT. A significant main time effect for overall accuracy and reaction time was found for the MFDT. Itching was the most common side effect and stimulation conditions detection was at chance level. Results suggest that multichannel tDCS over bilateral TPJ does not affect performance of low-level emotional recognition tasks in healthy adults. Although preliminary safety and tolerability are demonstrated, further studies over longer periods will be pursued to investigate the clinical efficacy in children/adolescents with ASD, where social cognition impairments are preponderant.

Virulence factor-related gut microbiota genes and immunoglobulin A levels as novel markers for machine learning-based classification of autism spectrum disorder

Autism spectrum disorder (ASD) is a neurodevelopmental condition for which early identification and intervention is crucial for optimum prognosis. Our previous work showed gut Immunoglobulin A (IgA) to be significantly elevated in the gut lumen of children with ASD compared to typically developing (TD) children. Gut microbiota variations have been reported in ASD, yet not much is known about virulence factor-related gut microbiota (VFGM) genes. Upon determining the VFGM genes distinguishing ASD from TD, this study is the first to utilize VFGM genes and IgA levels for a machine learning-based classification of ASD. Sequence comparisons were performed of metagenome datasets from children with ASD (n = 43) and TD children (n = 31) against genes in the virulence factor database. VFGM gene composition was associated with ASD phenotype. VFGM gene diversity was higher in children with ASD and positively correlated with IgA content. As Group B streptococcus (GBS) genes account for the highest proportion of 24 different VFGMs between ASD and TD and positively correlate with gut IgA, GBS genes were used in combination with IgA and VFGMs diversity to distinguish ASD from TD. Given that VFGM diversity, increases in IgA, and ASD-enriched VFGM genes were independent of sex and gastrointestinal symptoms, a classification method utilizing them will not pertain only to a specific subgroup of ASD. By introducing the classification value of VFGM genes and considering that VFs can be isolated in pregnant women and newborns, these findings provide a novel machine learning-based early risk identification method for ASD.

Resting state EEG-based diagnosis of Autism via elliptic area of continuous wavelet transform complex plot

Autism is a developmental disorder that influences social communication skills. It is currently diagnosed only by behavioral assessment. The assessment is susceptible to the experience of the examiner as well as to the descriptive scaling standard. This paper presents a computer aided approach to discrimination between neuro-typical and autistic children. A new method- based on the computing of the elliptic area of the Continuous Wavelet Transform complex plot of resting state EEG- is presented. First, the complex values of CWT, as a function of both time and frequency, are calculated for every EEG channel. Second, the CWT complex plot is obtained by plotting the real parts of the resulted CWT values versus the related imaginary components. Third, the 95% confidence value of the elliptic area of the complex plot is computed for every channel for both autistic and healthy subjects; and the obtained values are considered as the first set of features. Fourth, three additional features are computed for every channel: the average CWT, the maximum EEG amplitude, and the maximum real part of CWT. The classification of those features is realized through artificial neural network (ANN). The obtained accuracy, sensitivity and specificity values are: 95.9%, 96.7%, and 95.1% respectively.

A Novel Biomarker of Compensatory Recruitment of Face Emotional Imagery Networks in Autism Spectrum Disorder

Imagery of facial expressions in Autism Spectrum Disorder (ASD) is likely impaired but has been very difficult to capture at a neurophysiological level. We developed an approach that allowed to directly link observation of emotional expressions and imagery in ASD, and to derive biomarkers that are able to classify abnormal imagery in ASD. To provide a handle between perception and action imagery cycles it is important to use visual stimuli exploring the dynamical nature of emotion representation. We conducted a case-control study providing a link between both visualization and mental imagery of dynamic facial expressions and investigated source responses to pure face-expression contrasts. We were able to replicate the same highly group discriminative neural signatures during action observation (dynamical face expressions) and imagery, in the precuneus. Larger activation in regions involved in imagery for the ASD group suggests that this effect is compensatory. We conducted a machine learning procedure to automatically identify these group differences, based on the EEG activity during mental imagery of facial expressions. We compared two classifiers and achieved an accuracy of 81% using 15 features (both linear and non-linear) of the signal from theta, high-beta and gamma bands extracted from right-parietal locations (matching the precuneus region), further confirming the findings regarding standard statistical analysis. This robust classification of signals resulting from imagery of dynamical expressions in ASD is surprising because it far and significantly exceeds the good classification already achieved with observation of neutral face expressions (74%). This novel neural correlate of emotional imagery in autism could potentially serve as a clinical interventional target for studies designed to improve facial expression recognition, or at least as an intervention biomarker.