Use of Machine Learning to Identify Children with Autism and Their Motor Abnormalities

Autism spectrum disorders detection based on multi-task transformer neural network

Autism Spectrum Disorders (ASD) are neurodevelopmental disorders that cause people difficulties in social interaction and communication. Identifying ASD patients based on resting-state functional magnetic resonance imaging (rs-fMRI) data is a promising diagnostic tool, but challenging due to the complex and unclear etiology of autism. And it is difficult to effectively identify ASD patients with a single data source (single task). Therefore, to address this challenge, we propose a novel multi-task learning framework for ASD identification based on rs-fMRI data, which can leverage useful information from multiple related tasks to improve the generalization performance of the model. Meanwhile, we adopt an attention mechanism to extract ASD-related features from each rs-fMRI dataset, which can enhance the feature representation and interpretability of the model. The results show that our method outperforms state-of-the-art methods in terms of accuracy, sensitivity and specificity. This work provides a new perspective and solution for ASD identification based on rs-fMRI data using multi-task learning. It also demonstrates the potential and value of machine learning for advancing neuroscience research and clinical practice.

A Review on Autism Spectrum Disorder Screening by Artificial Intelligence Methods

PURPOSE

With the increasing prevalence of autism spectrum disorders (ASD), the importance of early screening and diagnosis has been subject to considerable discussion. Given the subtle differences between ASD children and typically developing children during the early stages of development, it is imperative to investigate the utilization of automatic recognition methods powered by artificial intelligence. We aim to summarize the research work on this topic and sort out the markers that can be used for identification.

METHODS

We searched the papers published in the Web of Science, PubMed, Scopus, Medline, SpringerLink, Wiley Online Library, and EBSCO databases from 1st January 2013 to 13th November 2023, and 43 articles were included.

RESULTS

These articles mainly divided recognition markers into five categories: gaze behaviors, facial expressions, motor movements, voice features, and task performance. Based on the above markers, the accuracy of artificial intelligence screening ranged from 62.13 to 100%, the sensitivity ranged from 69.67 to 100%, the specificity ranged from 54 to 100%.

CONCLUSION

Therefore, artificial intelligence recognition holds promise as a tool for identifying children with ASD. However, it still needs to continually enhance the screening model and improve accuracy through multimodal screening, thereby facilitating timely intervention and treatment.

Decreased wrist rotation imitation abilities in children with autism spectrum disorder

Introduction

While meaningless gross motor imitation (GMI) is a common challenge for children diagnosed with autism spectrum disorder (ASD), this topic has not attracted much attention and few appropriate test paradigms have been developed.

Methods

The current study proposed a wrist rotation imitation (WRI) task (a meaningless GMI assignment), and established a WRI ability evaluation system using low-cost wearable inertial sensors, which acquired the simultaneous data of acceleration and angular acceleration during the WRI task. Three metrics (i.e., total rotation time, rotation amplitude, and symmetry) were extracted from those data of acceleration and angular acceleration, and then were adopted to construct classifiers based on five machine learning (ML) algorithms, including k-nearest neighbors, linear discriminant analysis, naive Bayes, support vector machines, and random forests. To illustrate our technique, this study recruited 49 ASD children (aged 3.5-6.5 years) and 59 age-matched typically developing (TD) children.

Results

Findings showed that compared with TD children, those with ASD may exhibit shorter total rotation time, lower rotation amplitude, and weaker symmetry. This implies that children with ASD might exhibit decreased WRI abilities. The classifier with the naive Bayes algorithm outperformed than other four algorithms, and achieved a maximal classification accuracy of 88% and a maximal AUC value of 0.91. Two metrics (i.e., rotation amplitude and symmetry) had high correlations with the gross and fine motor skills [evaluated by Gesell Developmental Schedules-Third Edition and Psychoeducational Profile-3 (PEP-3)]. While, the three metrics had no significant correlation with the visual-motor imitation abilities (evaluated by the subdomain of PEP-3) and the ASD symptom severity [evaluated by the Childhood Autism Rating Scale (CARS)] .

Discussion

The strengths of this study are associated with the low-cost measurement system, correlation between the WRI metrics and clinical measures, decreased WRI abilities in ASD, and high classification accuracy.

Toward Generalizable Machine Learning Models in Speech, Language, and Hearing Sciences: Estimating Sample Size and Reducing Overfitting

PURPOSE

Many studies using machine learning (ML) in speech, language, and hearing sciences rely upon cross-validations with single data splitting. This study's first purpose is to provide quantitative evidence that would incentivize researchers to instead use the more robust data splitting method of nested k-fold cross-validation. The second purpose is to present methods and MATLAB code to perform power analysis for ML-based analysis during the design of a study.

METHOD

First, the significant impact of different cross-validations on ML outcomes was demonstrated using real-world clinical data. Then, Monte Carlo simulations were used to quantify the interactions among the employed cross-validation method, the discriminative power of features, the dimensionality of the feature space, the dimensionality of the model, and the sample size. Four different cross-validation methods (single holdout, 10-fold, train-validation-test, and nested 10-fold) were compared based on the statistical power and confidence of the resulting ML models. Distributions of the null and alternative hypotheses were used to determine the minimum required sample size for obtaining a statistically significant outcome (5% significance) with 80% power. Statistical confidence of the model was defined as the probability of correct features being selected for inclusion in the final model.

RESULTS

ML models generated based on the single holdout method had very low statistical power and confidence, leading to overestimation of classification accuracy. Conversely, the nested 10-fold cross-validation method resulted in the highest statistical confidence and power while also providing an unbiased estimate of accuracy. The required sample size using the single holdout method could be 50% higher than what would be needed if nested k-fold cross-validation were used. Statistical confidence in the model based on nested k-fold cross-validation was as much as four times higher than the confidence obtained with the single holdout-based model. A computational model, MATLAB code, and lookup tables are provided to assist researchers with estimating the minimum sample size needed during study design.

CONCLUSION

The adoption of nested k-fold cross-validation is critical for unbiased and robust ML studies in the speech, language, and hearing sciences.

SUPPLEMENTAL MATERIAL

https://doi.org/10.23641/asha.25237045.

The Promises and Possibilities of Artificial Intelligence in the Delivery of Behavior Analytic Services

Artificial intelligence (AI) has begun to affect nearly every aspect of our daily lives and nearly every industry and profession. Many readers of this journal likely work in one or more areas of behavioral health. For readers who work in behavioral health and who are interested in AI, the purpose of this article is to highlight the pervasiveness of AI research being conducted around many facets of behavioral health service delivery. To do this, we first provide a brief overview of some of the areas within AI and the types of problems each area of AI attempts to solve. We then outline the prototypical client journey in behavioral healthcare beginning with diagnosis/assessment and ending with intervention withdrawal or ongoing monitoring. Next, for each stage in the client journey, we highlight several areas that parallel existing behavior analytic practice where researchers have begun to use AI, often to improve the efficiency of service delivery or to learn new things that improve the effectiveness of behavioral health services. Finally, for those whose appetite has been whet for getting involved with AI, we close by describing three roles they might consider trying out and that parallel the three main domains of behavior analysis. These three roles are an AI tool designer (akin to EAB), AI tool implementer (akin to ABA), or AI tool supporter (akin to practice).

[Differential diagnosis of autism spectrum disorder and global developmental delay based on machine learning and Children Neuropsychological and Behavioral Scale]

OBJECTIVES

To investigate the efficacy and required indicators of Children Neuropsychological and Behavioral Scale-Revision 2016 (CNBS-R2016) in the differential diagnosis of autism spectrum disorder (ASD) and global developmental delay (GDD).

METHODS

A total of 277 children with ASD and 415 children with GDD, aged 18-48 months, were enrolled as subjects. CNBS-R2016 was used to assess the developmental levels of six domains, i.e., gross motor, fine motor, adaptive ability, language, social behavior, and warning behavior, and a total of 13 indicators on intelligence age and developmental quotient (DQ) were obtained as the input features. Five commonly used machine learning classifiers were used for training to calculate the classification accuracy, sensitivity, and specificity of each classifier.

RESULTS

DQ of warning behavior was selected as the first feature in all five classifiers, and the use of this indicator alone had a classification accuracy of 78.90%. When the DQ of warning behavior was used in combination with the intelligence age of warning behavior, gross motor, and language, it had the highest classification accuracy of 86.71%.

CONCLUSIONS

Machine learning combined with CNBS-R2016 can effectively distinguish children with ASD from those with GDD. The DQ of warning behavior plays an important role in machine learning, and its combination with other features can improve classification accuracy, providing a basis for the efficient and accurate differential diagnosis of ASD and GDD in clinical practice.

Graph fusion prediction of autism based on attentional mechanisms

Autism spectrum disorder (ASD) is a pervasive developmental disorder, and the earlier detection and timely intervention for treatment positively affect the prognosis of patients. Deep learning algorithms based on graph structure have achieved good results in autism prediction in recent years. However, there are problems with standardized operations in extracting features and combining neighborhood node features with the structure of the graph dependent, which limits the generalization ability of the trained model to other graph structures. In this paper, we propose a graph fusion autism prediction model based on attentional mechanisms(AGF) to address the above problems. The AGF model represents the overall population (patients or healthy controls) as a sparse graph, where nodes are subjects, and non-imaging features are integrated as edge weights. Different weights can be defined for different nodes in the neighborhood through the attention mechanism without relying on prior knowledge of the graph structure. The model is also able to dynamically fuse multiple sparse graphs obtained from different non-imaging features by way of training weight assignment. Its performance is also compared with several other models (e.g., S-AGF, GCN, etc.), and the results show that it has superior prediction accuracy compared to the baseline model. The results show that this improvement of graph fusion works better on the ABIDE databases, and the classification accuracy can reach 73.9%. The datasets and source code are freely available at https://github.com/chengyu-github1012/Graph-Fusion.git. Strengths and limitations of this study: graph fusion; disease prediction; noise.

A multimodal approach can identify specific motor profiles in autism and attention-deficit/hyperactivity disorder

It is still unclear whether and to what extent the motor difficulties are specific to autism. This study aimed to determine whether a multimodal assessment of motor skills could accurately discriminate autistic children from attention-deficit/hyperactivity disorder (ADHD) and typically developing (TD) peers. Seventy-five children, aged 7-13, equally divided into three groups, were assessed with the developmental coordination disorder questionnaire (DCDQ), the movement assessment battery for children 2 (MABC2), the sensorimotor subtests of NEPSY-II, and the kinematic analysis of a reach-to-drop task. Principal component analysis (PCA) on DCDQ subscales revealed one factor-Caregiver Report-, whereas MABC2/NEPSY-II scores identified three factors-namely, Object Interception and Balance, Motor Imitation, and Fine-Motor Skills-. Lastly, PCA on kinematic variables identified four factors: PC1, loaded by the parameters of velocity and acceleration throughout the task, PC2 and PC3 involved the temporal parameters of the two submovements, and PC4 accounted for the wrist inclination at ball drop. When comparing autistic and TD children, Caregiver Report and Motor Imitation factors predicted membership with 87.2% of accuracy. In the model comparing ADHD and TD groups, Caregiver Report and Fine-Motor Skills predicted membership with an accuracy of 73.5%. In the last model, the Object Interception and Balance factor differentiated autistic children from ADHD with an accuracy of 73.5%. In line with our previous findings, kinematics did not differentiate school-aged autistic children from ADHD and TD peers. The present findings show that specific motor profiles in autism and ADHD can be isolated with a multimodal investigation of motor skills.

Neonatal Seizure Detection Using a Wearable Multi-Sensor System

Neonatal seizure is an important clinical symptom of brain dysfunction, which is more common in infancy than in childhood. At present, video electroencephalogram (VEEG) technology is widely used in clinical practice. However, video electroencephalogram technology has several disadvantages. For example, the wires connecting the medical instruments may interfere with the infant's movement and the gel patch electrode or disk electrode commonly used to monitor EEG may cause skin allergies or even tears. For the above reasons, we developed a wearable multi-sensor platform for newborns to collect physiological and movement signals. In this study, we designed a second-generation multi-sensor platform and developed an automatic detection algorithm for neonatal seizures based on ECG, respiration and acceleration. Data for 38 neonates were recorded at the Children's Hospital of Fudan University in Shanghai. The total recording time was approximately 300 h. Four of the patients had seizures during data collection. The total recording time for the four patients was approximately 34 h, with 30 seizure episodes recorded. These data were evaluated by the algorithm. To evaluate the effectiveness of combining ECG, respiration and movement, we compared the performance of three types of seizure detectors. The first detector included features from ECG, respiration and acceleration records; the second detector incorporated features based on respiratory movement from respiration and acceleration records; and the third detector used only ECG-based features from ECG records. Our study illustrated that, compared with the detector utilizing individual modal features, multi-modal feature detectors could achieve favorable overall performance, reduce false alarm rates and give higher F-measures.

The whole-body motor skills of children with autism spectrum disorder taking goal-directed actions in virtual reality

Many symptoms of the autism spectrum disorder (ASD) are evident in early infancy, but ASD is usually diagnosed much later by procedures lacking objective measurements. It is necessary to anticipate the identification of ASD by improving the objectivity of the procedure and the use of ecological settings. In this context, atypical motor skills are reaching consensus as a promising ASD biomarker, regardless of the level of symptom severity. This study aimed to assess differences in the whole-body motor skills between 20 children with ASD and 20 children with typical development during the execution of three tasks resembling regular activities presented in virtual reality. The virtual tasks asked to perform precise and goal-directed actions with different limbs vary in their degree of freedom of movement. Parametric and non-parametric statistical methods were applied to analyze differences in children's motor skills. The findings endorsed the hypothesis that when particular goal-directed movements are required, the type of action could modulate the presence of motor abnormalities in ASD. In particular, the ASD motor abnormalities emerged in the task requiring to take with the upper limbs goal-directed actions with low degree of freedom. The motor abnormalities covered (1) the body part mainly involved in the action, and (2) further body parts not directly involved in the movement. Findings were discussed against the background of atypical prospective control of movements and visuomotor discoordination in ASD. These findings contribute to advance the understanding of motor skills in ASD while deepening ecological and objective assessment procedures based on VR.

Use of Oculomotor Behavior to Classify Children with Autism and Typical Development: A Novel Implementation of the Machine Learning Approach

This study segmented the time series of gaze behavior from nineteen children with autism spectrum disorder (ASD) and 20 children with typical development in a face-to-face conversation. A machine learning approach showed that behavior segments produced by these two groups of participants could be classified with the highest accuracy of 74.15%. These results were further used to classify children using a threshold classifier. A maximum classification accuracy of 87.18% was achieved, under the condition that a participant was considered as 'ASD' if over 46% of the child's 7-s behavior segments were classified as ASD-like behaviors. The idea of combining the behavior segmentation technique and the threshold classifier could maximally preserve participants' data, and promote the automatic screening of ASD.

Superstorm Sandy exposure in utero is associated with neurobehavioral phenotypes and brain structure alterations in childhood: A machine learning approach

Introduction

Prenatal maternal stress (PNMS), including exposure to natural disasters, has been shown to serve as a risk factor for future child psychopathology and suboptimal brain development, particularly among brain regions shown to be sensitive to stress and trauma exposure. However, statistical approaches deployed in most studies are usually constrained by a limited number of variables for the sake of statistical power. Explainable machine learning, on the other hand, enables the study of high data dimension and offers novel insights into the prominent subset of behavioral phenotypes and brain regions most susceptible to PNMS. In the present study, we aimed to identify the most important child neurobehavioral and brain features associated with in utero exposure to Superstorm Sandy (SS).

Methods

By leveraging an explainable machine learning technique, the Shapley additive explanations method, we tested the marginal feature effect on SS exposures and examined the individual variable effects on disaster exposure.

Results

Results show that certain brain regions are especially sensitive to in utero exposure to SS. Specifically, in utero SS exposure was associated with larger gray matter volume (GMV) in the right caudate, right hippocampus, and left amygdala and smaller GMV in the right parahippocampal gyrus. Additionally, higher aggression scores at age 5 distinctly correlated with SS exposure.

Discussion

These findings suggest in utero SS exposure may be associated with greater aggression and suboptimal developmental alterations among various limbic and basal ganglia brain regions.

Digitally assisted diagnostics of autism spectrum disorder

Digital technologies have the potential to support psychiatric diagnostics and, in particular, differential diagnostics of autism spectrum disorder in the near future, making clinical decisions more objective, reliable and evidence-based while reducing clinical resources. Multimodal automatized measurement of symptoms at cognitive, behavioral, and neuronal levels combined with artificial intelligence applications offer promising strides toward personalized prognostics and treatment strategies. In addition, these new technologies could enable systematic and continuous assessment of longitudinal symptom development, beyond the usual scope of clinical practice. Early recognition of exacerbation and simplified, as well as detailed, progression control would become possible. Ultimately, digitally assisted diagnostics will advance early recognition. Nonetheless, digital technologies cannot and should not substitute clinical decision making that takes the comprehensive complexity of individual longitudinal and cross-section presentation of autism spectrum disorder into account. Yet, they might aid the clinician by objectifying decision processes and provide a welcome relief to resources in the clinical setting.

Machine Learning-Based Blood RNA Signature for Diagnosis of Autism Spectrum Disorder

Early diagnosis of autism spectrum disorder (ASD) is crucial for providing appropriate treatments and parental guidance from an early age. Yet, ASD diagnosis is a lengthy process, in part due to the lack of reliable biomarkers. We recently applied RNA-sequencing of peripheral blood samples from 73 American and Israeli children with ASD and 26 neurotypically developing (NT) children to identify 10 genes with dysregulated blood expression levels in children with ASD. Machine learning (ML) analyzes data by computerized analytical model building and may be applied to building diagnostic tools based on the optimization of large datasets. Here, we present several ML-generated models, based on RNA expression datasets collected during our recently published RNA-seq study, as tentative tools for ASD diagnosis. Using the random forest classifier, two of our proposed models yield an accuracy of 82% in distinguishing children with ASD and NT children. Our proof-of-concept study requires refinement and independent validation by studies with far larger cohorts of children with ASD and NT children and should thus be perceived as starting point for building more accurate ML-based tools. Eventually, such tools may potentially provide an unbiased means to support the early diagnosis of ASD.

A multimodal machine learning system in early screening for toddlers with autism spectrum disorders based on the response to name

BACKGROUND

Reduced or absence of the response to name (RTN) has been widely reported as an early specific indicator for autism spectrum disorder (ASD), while few studies have quantified the RTN of toddlers with ASD in an automatic way. The present study aims to apply a multimodal machine learning system (MMLS) in early screening for toddlers with ASD based on the RTN.

METHODS

A total of 125 toddlers were recruited, including ASD (n = 61), developmental delay (DD, n = 31), and typical developmental (TD, n = 33). Procedures of RTN were, respectively, performed by the evaluator and caregiver. Behavioral data were collected by eight-definition tripod-mounted cameras and coded by the MMLS. Response score, response time, and response duration time were accurately calculated to evaluate RTN.

RESULTS

Total accuracy of RTN scores rated by computers was 0.92. In both evaluator and caregiver procedures, toddlers with ASD had significant differences in response score, response time, and response duration time, compared to toddlers with DD and TD (all P-values < 0.05). The area under the curve (AUC) was 0.81 for the computer-rated results, and the AUC was 0.91 for the human-rated results. The accuracy in the identification of ASD based on the computer- and human-rated results was, respectively, 74.8 and 82.9%. There was a significant difference between the AUC of the human-rated results and computer-rated results (Z = 2.71, P-value = 0.007).

CONCLUSION

The multimodal machine learning system can accurately quantify behaviors in RTN procedures and may effectively distinguish toddlers with ASD from the non-ASD group. This novel system may provide a low-cost approach to early screening and identifying toddlers with ASD. However, machine learning is not as accurate as a human observer, and the detection of a single symptom like RTN is not sufficient enough to detect ASD.

Identifying Visual Attention Features Accurately Discerning Between Autism and Typically Developing: a Deep Learning Framework

Atypical visual attention is a hallmark of autism spectrum disorder (ASD). Identifying the attention features accurately discerning between people with ASD and typically developing (TD) at the individual level remains a challenge. In this study, we developed a new systematic framework combining high accuracy deep learning classification, deep learning segmentation, image ablation and a direct measurement of classification ability to identify the discriminative features for autism identification. Our two-stream model achieved the state-of-the-art performance with a classification accuracy of 0.95. Using this framework, two new categories of features, Food & drink and Outdoor-objects, were identified as discriminative attention features, in addition to the previously reported features including Center-object and Human-faces, etc. Altered attention to the new categories helps to understand related atypical behaviors in ASD. Importantly, the area under curve (AUC) based on the combined top-9 features identified in this study was 0.92, allowing an accurate classification at the individual level. We also obtained a small but informative dataset of 12 images with an AUC of 0.86, suggesting a potentially efficient approach for the clinical diagnosis of ASD. Together, our deep learning framework based on VGG-16 provides a novel and powerful tool to recognize and understand abnormal visual attention in ASD, which will, in turn, facilitate the identification of biomarkers for ASD.

Motor signature of autism spectrum disorder in adults without intellectual impairment

Motor signs such as dyspraxia and abnormal gait are characteristic features of autism spectrum disorder (ASD). However, motor behavior in adults with ASD has scarcely been quantitatively characterized. In this pilot study, we aim to quantitatively examine motor signature of adults with ASD without intellectual impairment using marker-less visual-perceptive motion capture. 82 individuals (37 ASD and 45 healthy controls, HC) with an IQ > 85 and aged 18 to 65 years performed nine movement tasks and were filmed by a 3D-infrared camera. Anatomical models were quantified via custom-made software and resulting kinematic parameters were compared between individuals with ASD and HCs. Furthermore, the association between specific motor behaviour and severity of autistic symptoms (Autism Diagnostic Observation Schedule 2, Autism Spectrum Quotient) was explored. Adults with ASD showed a greater mediolateral deviation while walking, greater sway during normal, tandem and single leg stance, a reduced walking speed and cadence, a greater arrhythmicity during jumping jack tasks and an impaired manual dexterity during finger tapping tasks (p < 0.05 and |D|> 0.48) compared to HC. Furthermore, in the ASD group, some of these parameters correlated moderately to severity of ASD symptoms. Adults with ASD seem to display a specific motor signature in this disorder affecting movement timing and aspects of balance. The data appear to reinforce knowledge about motor signs reported in children and adolescents with ASD. Also, quantitative motor assessment via visual-perceptive computing may be a feasible instrument to detect subtle motor signs in ASD and perhaps suitable in the diagnosis of ASD in the future.

Classifying Autism From Crowdsourced Semistructured Speech Recordings: Machine Learning Model Comparison Study

BACKGROUND

Autism spectrum disorder (ASD) is a neurodevelopmental disorder that results in altered behavior, social development, and communication patterns. In recent years, autism prevalence has tripled, with 1 in 44 children now affected. Given that traditional diagnosis is a lengthy, labor-intensive process that requires the work of trained physicians, significant attention has been given to developing systems that automatically detect autism. We work toward this goal by analyzing audio data, as prosody abnormalities are a signal of autism, with affected children displaying speech idiosyncrasies such as echolalia, monotonous intonation, atypical pitch, and irregular linguistic stress patterns.

OBJECTIVE

We aimed to test the ability for machine learning approaches to aid in detection of autism in self-recorded speech audio captured from children with ASD and neurotypical (NT) children in their home environments.

METHODS

We considered three methods to detect autism in child speech: (1) random forests trained on extracted audio features (including Mel-frequency cepstral coefficients); (2) convolutional neural networks trained on spectrograms; and (3) fine-tuned wav2vec 2.0-a state-of-the-art transformer-based speech recognition model. We trained our classifiers on our novel data set of cellphone-recorded child speech audio curated from the Guess What? mobile game, an app designed to crowdsource videos of children with ASD and NT children in a natural home environment.

RESULTS

The random forest classifier achieved 70% accuracy, the fine-tuned wav2vec 2.0 model achieved 77% accuracy, and the convolutional neural network achieved 79% accuracy when classifying children's audio as either ASD or NT. We used 5-fold cross-validation to evaluate model performance.

CONCLUSIONS

Our models were able to predict autism status when trained on a varied selection of home audio clips with inconsistent recording qualities, which may be more representative of real-world conditions. The results demonstrate that machine learning methods offer promise in detecting autism automatically from speech without specialized equipment.

Discriminative Dictionary Learning for Autism Spectrum Disorder Identification

Autism Spectrum Disorder (ASD) is a group of lifelong neurodevelopmental disorders with complicated causes. A key symptom of ASD patients is their impaired interpersonal communication ability. Recent study shows that face scanning patterns of individuals with ASD are often different from those of typical developing (TD) ones. Such abnormality motivates us to study the feasibility of identifying ASD children based on their face scanning patterns with machine learning methods. In this paper, we consider using the bag-of-words (BoW) model to encode the face scanning patterns, and propose a novel dictionary learning method based on dual mode seeking for better BoW representation. Unlike k-means which is broadly used in conventional BoW models to learn dictionaries, the proposed method captures discriminative information by finding atoms which maximizes both the purity and coverage of belonging samples within one class. Compared to the rich literature of ASD studies from psychology and neural science, our work marks one of the relatively few attempts to directly identify high-functioning ASD children with machine learning methods. Experiments demonstrate the superior performance of our method with considerable gain over several baselines. Although the proposed work is yet too preliminary to directly replace existing autism diagnostic observation schedules in the clinical practice, it shed light on future applications of machine learning methods in early screening of ASD.

Applications of Pose Estimation in Human Health and Performance across the Lifespan

The emergence of pose estimation algorithms represents a potential paradigm shift in the study and assessment of human movement. Human pose estimation algorithms leverage advances in computer vision to track human movement automatically from simple videos recorded using common household devices with relatively low-cost cameras (e.g., smartphones, tablets, laptop computers). In our view, these technologies offer clear and exciting potential to make measurement of human movement substantially more accessible; for example, a clinician could perform a quantitative motor assessment directly in a patient's home, a researcher without access to expensive motion capture equipment could analyze movement kinematics using a smartphone video, and a coach could evaluate player performance with video recordings directly from the field. In this review, we combine expertise and perspectives from physical therapy, speech-language pathology, movement science, and engineering to provide insight into applications of pose estimation in human health and performance. We focus specifically on applications in areas of human development, performance optimization, injury prevention, and motor assessment of persons with neurologic damage or disease. We review relevant literature, share interdisciplinary viewpoints on future applications of these technologies to improve human health and performance, and discuss perceived limitations.

Classification of Children With Autism and Typical Development Using Eye-Tracking Data From Face-to-Face Conversations: Machine Learning Model Development and Performance Evaluation

BACKGROUND

Previous studies have shown promising results in identifying individuals with autism spectrum disorder (ASD) by applying machine learning (ML) to eye-tracking data collected while participants viewed varying images (ie, pictures, videos, and web pages). Although gaze behavior is known to differ between face-to-face interaction and image-viewing tasks, no study has investigated whether eye-tracking data from face-to-face conversations can also accurately identify individuals with ASD.

OBJECTIVE

The objective of this study was to examine whether eye-tracking data from face-to-face conversations could classify children with ASD and typical development (TD). We further investigated whether combining features on visual fixation and length of conversation would achieve better classification performance.

METHODS

Eye tracking was performed on children with ASD and TD while they were engaged in face-to-face conversations (including 4 conversational sessions) with an interviewer. By implementing forward feature selection, four ML classifiers were used to determine the maximum classification accuracy and the corresponding features: support vector machine (SVM), linear discriminant analysis, decision tree, and random forest.

RESULTS

A maximum classification accuracy of 92.31% was achieved with the SVM classifier by combining features on both visual fixation and session length. The classification accuracy of combined features was higher than that obtained using visual fixation features (maximum classification accuracy 84.62%) or session length (maximum classification accuracy 84.62%) alone.

CONCLUSIONS

Eye-tracking data from face-to-face conversations could accurately classify children with ASD and TD, suggesting that ASD might be objectively screened in everyday social interactions. However, these results will need to be validated with a larger sample of individuals with ASD (varying in severity and balanced sex ratio) using data collected from different modalities (eg, eye tracking, kinematic, electroencephalogram, and neuroimaging). In addition, individuals with other clinical conditions (eg, developmental delay and attention deficit hyperactivity disorder) should be included in similar ML studies for detecting ASD.

Augmented Reality for Autistic Children to Enhance Their Understanding of Facial Expressions

Difficulty in understanding the feelings and behavior of other people is considered one of the main symptoms of autism. Computer technology has increasingly been used in interventions with Autism Spectrum Disorder (ASD), especially augmented reality, to either treat or alleviate ASD symptomatology. Augmented reality is an engaging type of technology that helps children interact easily and understand and remember information, and it is not limited to one age group or level of education. This study utilized AR to display faces with six different basic facial expressions—happiness, sadness, surprise, fear, disgust, and anger—to help children to recognize facial features and associate facial expressions with a simultaneous human condition. The most important point of this system is that children can interact with the system in a friendly and safe way. Additionally, our results showed the system enhanced social interactions, talking, and facial expressions for both autistic and typical children. Therefore, AR might have a significant upcoming role in talking about the therapeutic necessities of children with ASD. This paper presents evidence for the feasibility of one of the specialized AR systems.

Automatic classification of autism spectrum disorder in children using cortical thickness and support vector machine

OBJECTIVE

Autism spectrum disorder (ASD) is a neurodevelopmental condition with a heterogeneous phenotype. The role of biomarkers in ASD diagnosis has been highlighted; cortical thickness has proved to be involved in the etiopathogenesis of ASD core symptoms. We apply support vector machine, a supervised machine learning method, in order to identify specific cortical thickness alterations in ASD subjects.

METHODS

A sample of 76 subjects (9.5 ± 3.4 years old) has been selected, 40 diagnosed with ASD and 36 typically developed subjects. All children underwent a magnetic resonance imaging (MRI) examination; T1-MPRAGE sequences were analyzed to extract features for the characterization and parcellation of regions of interests (ROI); average cortical thickness (CT) has been measured for each ROI. For the classification process, the extracted features were used as input for a classifier to identify ASD subjects through a "learning by example" procedure; the features with best performance was then selected by "greedy forward-feature selection." Finally, this model underwent a leave-one-out cross-validation approach.

RESULTS

From the training set of 68 ROIs, five ROIs reached accuracies of over 70%. After this phase, we used a recursive feature selection process in order to identify the eight features with the best accuracy (84.2%). CT resulted higher in ASD compared to controls in all the ROIs identified at the end of the process.

CONCLUSION

We found increased CT in various brain regions in ASD subjects, confirming their role in the pathogenesis of this condition. Considering the brain development curve during ages, these changes in CT may normalize during development. Further validation on a larger sample is required.

A low-cost stand-alone platform for measuring motor behavior across developmental applications

Motion tracking provides unique insights into motor, cognitive, and social development by capturing subtle variations into how movements are planned and controlled. Here, we present a low-cost, wearable movement measurement platform, KiD, specifically designed for tracking the movements of infants and children in a variety of natural settings. KiD consists of a small, lightweight sensor containing a nine-axis inertial measurement unit plus an integrated processor for computing rotations. Measurements of three-dimensional acceleration using KiD compare well with those of current state-of-the-art optical motion capture systems. As a proof of concept, we demonstrate successful classification of different types of sinusoidal right arm movements using KiD.

Identifying Autism with Head Movement Features by Implementing Machine Learning Algorithms

Our study investigated the feasibility of using head movement features to identify individuals with autism spectrum disorder (ASD). Children with ASD and typical development (TD) were required to answer ten yes-no questions, and they were encouraged to nod/shake head while doing so. The head rotation range (RR) and the amount of rotation per minute (ARPM) in the pitch (head nodding direction), yaw (head shaking direction) and roll (lateral head inclination) directions were computed, and further fed into machine learning classifiers as the input features. The maximum classification accuracy of 92.11% was achieved with the decision tree classifier with two features (i.e., RR_Pitch and ARPM_Yaw). Our study suggests that head movement dynamics contain objective biomarkers that could identify ASD.

Assessment of the Autism Spectrum Disorder Based on Machine Learning and Social Visual Attention: A Systematic Review

The assessment of autism spectrum disorder (ASD) is based on semi-structured procedures addressed to children and caregivers. Such methods rely on the evaluation of behavioural symptoms rather than on the objective evaluation of psychophysiological underpinnings. Advances in research provided evidence of modern procedures for the early assessment of ASD, involving both machine learning (ML) techniques and biomarkers, as eye movements (EM) towards social stimuli. This systematic review provides a comprehensive discussion of 11 papers regarding the early assessment of ASD based on ML techniques and children's social visual attention (SVA). Evidences suggest ML as a relevant technique for the early assessment of ASD, which might represent a valid biomarker-based procedure to objectively make diagnosis. Limitations and future directions are discussed.

Using Technology to Identify Children With Autism Through Motor Abnormalities

Autism is a neurodevelopmental disorder typically assessed and diagnosed through observational analysis of behavior. Assessment exclusively based on behavioral observation sessions requires a lot of time for the diagnosis. In recent years, there is a growing need to make assessment processes more motivating and capable to provide objective measures of the disorder. New evidence showed that motor abnormalities may underpin the disorder and provide a computational marker to enhance assessment and diagnostic processes. Thus, a measure of motor patterns could provide a means to assess young children with autism and a new starting point for rehabilitation treatments. In this study, we propose to use a software tool that through a smart tablet device and touch screen sensor technologies could be able to capture detailed information about children's motor patterns. We compared movement trajectories of autistic children and typically developing children, with the aim to identify autism motor signatures analyzing their coordinates of movements. We used a smart tablet device to record coordinates of dragging movements carried out by 60 children (30 autistic children and 30 typically developing children) during a cognitive task. Machine learning analysis of children's motor patterns identified autism with 93% accuracy, demonstrating that autism can be computationally identified. The analysis of the features that most affect the prediction reveals and describes the differences between the groups, confirming that motor abnormalities are a core feature of autism.

Q-CHAT-NAO: A robotic approach to autism screening in toddlers

The use of humanoid robots as assistants in therapy processes is not new. Several projects in the past several years have achieved promising results when combining human-robot interaction with standard techniques. Moreover, there are multiple screening systems for autism; one of the most used systems is the Quantitative Checklist for Autism in Toddlers (Q-CHAT-10), which includes ten questions to be answered by the parents or caregivers of a child. We present Q-CHAT-NAO, an observation-based autism screening system supported by a NAO robot. It includes the six questions of the Q-CHAT-10 that can be adapted to work in a robotic context; unlike the original system, it obtains information from the toddler instead of from an indirect source. The detection results obtained after applying machine learning models to the six questions in the Autistic Spectrum Disorder Screening Data for Toddlers dataset were almost equivalent to those of the original version with ten questions. These findings indicate that the Q-CHAT-NAO could be a screening option that would exploit all the benefits related to human-robot interaction.

Characterization of Autism Spectrum Disorder (ASD) subtypes based on the relationship between motor skills and social communication abilities

Motor abnormalities are generally observed in autism spectrum disorder (ASD), and motor difficulties are certainly evident during the early years of life and may thus precede social-communication impairments. The main aim of the present study was to examine ASD subtypes based on the relationship between motor skills and social communication abilities. Motor skills and social communication abilities were evaluated through the Movement Assessment Battery for Children-Second Edition, the Autism Diagnostic Observation Schedule-Second Version and the Psychoeducational Profile-Third Edition. In addition, social communication abilities were classified according to the Autism Classification System of Functioning: Social Communication-ACSF:SC criteria. We found that children with ASD presented poorer motor skills than their TD peers, and motor impairments correlated with poorer social communication abilities in children with ASD. In addition, children with lower social and communication functioning showed a more prominent impairment in manual dexterity and fine motor skills than children with better social and communication functioning. In conclusion, we suggest that stratifying children with ASD based on motor and social endophenotypes may be useful to understand the neurobiological mechanisms of ASD and lead to new types of treatment.

Automatic classification of children with autism spectrum disorder by using a computerized visual-orienting task

Early screening and diagnosis of autism spectrum disorder (ASD) primarily rely on behavioral observations by qualified clinicians whose decision process can benefit from the combination of machine learning algorithms and sensor data. We designed a computerized visual-orienting task with gaze-related or non-gaze-related directional cues, which triggered participants' gaze-following behavior. Based on their eye-movement data registered by an eye tracker, we applied the machine learning algorithms to classify high-functioning children with ASD (HFA), low-functioning children with ASD (LFA), and typically developing children (TD). We found that TD children had higher success rates in obtaining rewards than HFA children, and HFA children had higher rates than LFA children. Based on raw eye-tracking data, our machine learning algorithm could classify the three groups with an accuracy of 81.1% and relatively high sensitivity and specificity. Classification became worse if only data from the gaze or nongaze conditions were used, suggesting that "less-social" directional cues also carry useful information for distinguishing these groups. Our findings not only provide insights about visual-orienting deficits among children with ASD but also demonstrate the promise of combining classical behavioral paradigms with machine learning algorithms for aiding the screening for individuals with ASD.

Could Gait Biomechanics Become a Marker of Atypical Neuronal Circuitry in Human Development?-The Example of Autism Spectrum Disorder

This perspective paper presents converging recent knowledge in neurosciences (motor neurophysiology, neuroimaging and neuro cognition) and biomechanics to outline the relationships between maturing neuronal network, behavior, and gait in human development. Autism Spectrum Disorder (ASD) represents a particularly relevant neurodevelopmental disorder (NDD) to study these convergences, as an early life condition presenting with sensorimotor and social behavioral alterations. ASD diagnosis relies solely on behavioral criteria. The absence of biological marker in ASD is a main challenge, and hampers correlations between behavioral development and standardized data such as brain structure alterations, brain connectivity, or genetic profile. Gait, as a way to study motor system development, represents a well-studied, early life ability that can be characterized through standardized biomechanical analysis. Therefore, developmental gait biomechanics might appear as a possible motor phenotype and biomarker, solid enough to be correlated to neuronal network maturation, in normal and atypical developmental trajectories—like in ASD.

Computerized Assessment of Motor Imitation as a Scalable Method for Distinguishing Children With Autism

BACKGROUND

Imitation deficits are prevalent in autism spectrum conditions (ASCs) and are associated with core autistic traits. Imitating others' actions is central to the development of social skills in typically developing populations, as it facilitates social learning and bond formation. We present a Computerized Assessment of Motor Imitation (CAMI) using a brief (1-min), highly engaging video game task.

METHODS

Using Kinect Xbox motion tracking technology, we recorded 48 children (27 with ASCs, 21 typically developing) as they imitated a model's dance movements. We implemented an algorithm based on metric learning and dynamic time warping that automatically detects and evaluates the important joints and returns a score considering spatial position and timing differences between the child and the model. To establish construct validity and reliability, we compared imitation performance measured by the CAMI method to the more traditional human observation coding (HOC) method across repeated trials and two different movement sequences.

RESULTS

Results revealed poorer imitation in children with ASCs than in typically developing children (ps < .005), with poorer imitation being associated with increased core autism symptoms. While strong correlations between the CAMI and HOC methods (rs = .69-.87) confirmed the CAMI's construct validity, CAMI scores classified the children into diagnostic groups better than the HOC scores (accuracyCAMI = 87.2%, accuracyHOC = 74.4%). Finally, by comparing repeated movement trials, we demonstrated high test-retest reliability of CAMI (rs = .73-.86).

CONCLUSIONS

Findings support the CAMI as an objective, highly scalable, directly interpretable method for assessing motor imitation differences, providing a promising biomarker for defining biologically meaningful ASC subtypes and guiding intervention.

Identifying the signature of prospective motor control in children with autism

Failure to develop prospective motor control has been proposed to be a core phenotypic marker of autism spectrum disorders (ASD). However, whether genuine differences in prospective motor control permit discriminating between ASD and non-ASD profiles over and above individual differences in motor output remains unclear. Here, we combined high precision measures of hand movement kinematics and rigorous machine learning analyses to determine the true power of prospective movement data to differentiate children with autism and typically developing children. Our results show that while movement is unique to each individual, variations in the kinematic patterning of sequential grasping movements genuinely differentiate children with autism from typically developing children. These findings provide quantitative evidence for a prospective motor control impairment in autism and indicate the potential to draw inferences about autism on the basis of movement kinematics.

Atypical Head Movement during Face-to-Face Interaction in Children with Autism Spectrum Disorder

The present study implemented an objective head pose tracking technique-OpenFace 2.0 to quantify the three dimensional head movement. Children with autism spectrum disorder (ASD) and typical development (TD) were engaged in a structured conversation with an interlocutress while wearing an eye tracker. We computed the head movement stereotypy with multiscale entropy analysis. In addition, the head rotation range (RR) and the amount of rotation per minute (ARPM) were calculated to quantify the extent of head movement. Results demonstrated that the ASD group had significantly higher level of movement stereotypy, RR and ARPM in all the three directions of head movement. Further analyses revealed that the extent of head movement could be significantly explained by movement stereotypy, but not by the amount of visual fixation to the interlocutress. These results demonstrated the atypical head movement dynamics in children with ASD during live interaction. It is proposed that head movement might potentially provide novel objective biomarkers of ASD. LAY SUMMARY: Our study used an objective tool to quantify head movement in children with autism. Results showed that children with autism had more stereotyped and greater head movement. We suggest that head movement tracking technique be widely used in autism research.

Information and Communication Technologies to Support Early Screening of Autism Spectrum Disorder: A Systematic Review

&nbsp;The aim of this systematic review is to identify recent digital technologies used to detect early signs of autism spectrum disorder (ASD) in preschool children (i.e., up to six years of age). A systematic literature search was performed for English language articles and conference papers indexed in Pubmed, PsycInfo, ERIC, CINAHL, WoS, IEEE, and ACM digital libraries up until January 2020. A follow-up search was conducted to cover the literature published until December 2020 for the usefulness and interest in this area of research during the Covid-19 emergency. In total, 2427 articles were initially retrieved from databases search. Additional 481 articles were retrieved from follow-up search. Finally, 28 articles met the inclusion criteria and were included in the review. The studies included involved four main interface modalities: Natural User Interface (e.g., eye trackers), PC or mobile, Wearable, and Robotics. Most of the papers included (n = 20) involved the use of Level 1 screening tools. Notwithstanding the variability of the solutions identified, psychometric information points to considering available technologies as promising supports in clinical practice to detect early sign of ASD in young children. Further research is needed to understand the acceptability and increase use rates of technology-based screenings in clinical settings.&nbsp.

Application of Skeleton Data and Long Short-Term Memory in Action Recognition of Children with Autism Spectrum Disorder

The recognition of stereotyped action is one of the core diagnostic criteria of Autism Spectrum Disorder (ASD). However, it mainly relies on parent interviews and clinical observations, which lead to a long diagnosis cycle and prevents the ASD children from timely treatment. To speed up the recognition process of stereotyped actions, a method based on skeleton data and Long Short-Term Memory (LSTM) is proposed in this paper. In the first stage of our method, the OpenPose algorithm is used to obtain the initial skeleton data from the video of ASD children. Furthermore, four denoising methods are proposed to eliminate the noise of the initial skeleton data. In the second stage, we track multiple ASD children in the same scene by matching distance between current skeletons and previous skeletons. In the last stage, the neural network based on LSTM is proposed to classify the ASD children's actions. The performed experiments show that our proposed method is effective for ASD children's action recognition. Compared to the previous traditional schemes, our scheme has higher accuracy and is almost non-invasive for ASD children.

A Review of Machine Learning Methods of Feature Selection and Classification for Autism Spectrum Disorder

Autism Spectrum Disorder (ASD), according to DSM-5 in the American Psychiatric Association, is a neurodevelopmental disorder that includes deficits of social communication and social interaction with the presence of restricted and repetitive behaviors. Children with ASD have difficulties in joint attention and social reciprocity, using non-verbal and verbal behavior for communication. Due to these deficits, children with autism are often socially isolated. Researchers have emphasized the importance of early identification and early intervention to improve the level of functioning in language, communication, and well-being of children with autism. However, due to limited local assessment tools to diagnose these children, limited speech-language therapy services in rural areas, etc., these children do not get the rehabilitation they need until they get into compulsory schooling at the age of seven years old. Hence, efficient approaches towards early identification and intervention through speedy diagnostic procedures for ASD are required. In recent years, advanced technologies like machine learning have been used to analyze and investigate ASD to improve diagnostic accuracy, time, and quality without complexity. These machine learning methods include artificial neural networks, support vector machines, a priori algorithms, and decision trees, most of which have been applied to datasets connected with autism to construct predictive models. Meanwhile, the selection of features remains an essential task before developing a predictive model for ASD classification. This review mainly investigates and analyzes up-to-date studies on machine learning methods for feature selection and classification of ASD. We recommend methods to enhance machine learning's speedy execution for processing complex data for conceptualization and implementation in ASD diagnostic research. This study can significantly benefit future research in autism using a machine learning approach for feature selection, classification, and processing imbalanced data.

The study of the differences between low-functioning autistic children and typically developing children in the processing of the own-race and other-race faces by the machine learning approach

OBJECTIVE

Autism spectrum disorder (ASD) is a heterogeneous neurodevelopmental disorder which affects the developmental trajectory in several behavioral domains, including impairments of social communication and stereotyped behavior. Unlike typically developing children who can successfully obtain the detailed facial information to decode the mental status with ease, autistic children cannot infer instant feelings and thoughts of other people due to their abnormal face processing. In the present study, we tested the other-race face, the own-race strange face and the own-race familiar face as stimuli material to explore whether ASD children would display different face fixation patterns for the different types of face compared to TD children. We used a machine learning approach based on eye tracking data to classify autistic children and TD children.

METHODS

Seventy-seven low-functioning autistic children and eighty typically developing children were recruited. They were required to watch a series face photos in a random order. According to the coordinate frequency distribution, the K-means clustering algorithm divided the image into 64 Area Of Interest (AOI) and selected the features using the minimal redundancy and maximal relevance (mRMR) algorithm. The Support Vector Machine (SVM) was used to classify to determine whether the scan patterns of different faces can be used to identify ASD, and to evaluate classification models from both accuracy and reliability.

RESULTS

The results showed that the maximum classification accuracy was 72.50% (AUC = 0.77) when 32 of the 64 features of unfamiliar other-race faces were selected; the maximum classification accuracy was 70.63% (AUC = 0.76) when 18 features of own-race strange faces were selected; the maximum classification accuracy was 78.33% (AUC = 0.84) when 48 features of own-race familiar faces were selected; The classification accuracy of combining three types of faces reached a maximum of 84.17% and AUC = 0.89 when 120 features were selected.

CONCLUSIONS

There are some differences between low-functioning autistic children and typically developing children in the processing of the own-race and other-race faces by the machine learning approach, which might be a useful tool for classifying low-functioning autistic children and TD children.

Role of Artificial Intelligence in Fighting Antimicrobial Resistance in Pediatrics

Artificial intelligence (AI) is a field of science and engineering concerned with the computational understanding of what is commonly called intelligent behavior. AI is extremely useful in many human activities including medicine. The aim of our narrative review is to show the potential role of AI in fighting antimicrobial resistance in pediatric patients. We searched for PubMed articles published from April 2010 to April 2020 containing the keywords “artificial intelligence”, “machine learning”, “antimicrobial resistance”, “antimicrobial stewardship”, “pediatric”, and “children”, and we described the different strategies for the application of AI in these fields. Literature analysis showed that the applications of AI in health care are potentially endless, contributing to a reduction in the development time of new antimicrobial agents, greater diagnostic and therapeutic appropriateness, and, simultaneously, a reduction in costs. Most of the proposed AI solutions for medicine are not intended to replace the doctor’s opinion or expertise, but to provide a useful tool for easing their work. Considering pediatric infectious diseases, AI could play a primary role in fighting antibiotic resistance. In the pediatric field, a greater willingness to invest in this field could help antimicrobial stewardship reach levels of effectiveness that were unthinkable a few years ago.

Creating a Learning Televillage and Automated Digital Child Health Ecosystem

This article explores the impact of digital technologies, including telehealth, teleconsultations, wireless devices, and chatbots, in pediatrics. Automated digital health with the Internet of things will allow better collection of real-world data for generation of real-world evidence to improve child health. Artificial intelligence with predictive analytics in turn will drive evidence-based decision-support systems and deliver personalized care to children. This technology creates building blocks for a learning child health and health care ecosystem.

Machine Learning Applied to Diagnosis of Human Diseases: A Systematic Review

Human healthcare is one of the most important topics for society. It tries to find the correct effective and robust disease detection as soon as possible to patients receipt the appropriate cares. Because this detection is often a difficult task, it becomes necessary medicine field searches support from other fields such as statistics and computer science. These disciplines are facing the challenge of exploring new techniques, going beyond the traditional ones. The large number of techniques that are emerging makes it necessary to provide a comprehensive overview that avoids very particular aspects. To this end, we propose a systematic review dealing with the Machine Learning applied to the diagnosis of human diseases. This review focuses on modern techniques related to the development of Machine Learning applied to diagnosis of human diseases in the medical field, in order to discover interesting patterns, making non-trivial predictions and useful in decision-making. In this way, this work can help researchers to discover and, if necessary, determine the applicability of the machine learning techniques in their particular specialties. We provide some examples of the algorithms used in medicine, analysing some trends that are focused on the goal searched, the algorithm used, and the area of applications. We detail the advantages and disadvantages of each technique to help choose the most appropriate in each real-life situation, as several authors have reported. The authors searched Scopus, Journal Citation Reports (JCR), Google Scholar, and MedLine databases from the last decades (from 1980s approximately) up to the present, with English language restrictions, for studies according to the objectives mentioned above. Based on a protocol for data extraction defined and evaluated by all authors using PRISMA methodology, 141 papers were included in this advanced review.

Towards a Multivariate Biomarker-Based Diagnosis of Autism Spectrum Disorder: Review and Discussion of Recent Advancements

An ever-evolving understanding of autism spectrum disorder (ASD) pathophysiology necessitates that diagnostic standards also evolve from being observation-based to include quantifiable clinical measurements. The multisystem nature of ASD motivates the use of multivariate methods of statistical analysis over common univariate approaches for discovering clinical biomarkers relevant to this goal. In addition to characterization of important behavioral patterns for improving current diagnostic instruments, multivariate analyses to date have allowed for thorough investigation of neuroimaging-based, genetic, and metabolic abnormalities in individuals with ASD. This review highlights current research using multivariate statistical analyses to quantify the value of these behavioral and physiological markers for ASD diagnosis. A detailed discussion of a blood-based diagnostic test for ASD using specific metabolite concentrations is also provided. The advancement of ASD biomarker research promises to provide earlier and more accurate diagnoses of the disorder.

Applying Machine Learning to Kinematic and Eye Movement Features of a Movement Imitation Task to Predict Autism Diagnosis

Autism is a developmental condition currently identified by experts using observation, interview, and questionnaire techniques and primarily assessing social and communication deficits. Motor function and movement imitation are also altered in autism and can be measured more objectively. In this study, motion and eye tracking data from a movement imitation task were combined with supervised machine learning methods to classify 22 autistic and 22 non-autistic adults. The focus was on a reliable machine learning application. We have used nested validation to develop models and further tested the models with an independent data sample. Feature selection was aimed at selection stability to assure result interpretability. Our models predicted diagnosis with 73% accuracy from kinematic features, 70% accuracy from eye movement features and 78% accuracy from combined features. We further explored features which were most important for predictions to better understand movement imitation differences in autism. Consistent with the behavioural results, most discriminative features were from the experimental condition in which non-autistic individuals tended to successfully imitate unusual movement kinematics while autistic individuals tended to fail. Machine learning results show promise that future work could aid in the diagnosis process by providing quantitative tests to supplement current qualitative ones.

Machine Learning and Virtual Reality on Body Movements' Behaviors to Classify Children with Autism Spectrum Disorder

Autism spectrum disorder (ASD) is mostly diagnosed according to behavioral symptoms in sensory, social, and motor domains. Improper motor functioning, during diagnosis, involves the qualitative evaluation of stereotyped and repetitive behaviors, while quantitative methods that classify body movements' frequencies of children with ASD are less addressed. Recent advances in neuroscience, technology, and data analysis techniques are improving the quantitative and ecological validity methods to measure specific functioning in ASD children. On one side, cutting-edge technologies, such as cameras, sensors, and virtual reality can accurately detect and classify behavioral biomarkers, as body movements in real-life simulations. On the other, machine-learning techniques are showing the potential for identifying and classifying patients' subgroups. Starting from these premises, three real-simulated imitation tasks have been implemented in a virtual reality system whose aim is to investigate if machine-learning methods on movement features and frequency could be useful in discriminating ASD children from children with typical neurodevelopment. In this experiment, 24 children with ASD and 25 children with typical neurodevelopment participated in a multimodal virtual reality experience, and changes in their body movements were tracked by a depth sensor camera during the presentation of visual, auditive, and olfactive stimuli. The main results showed that ASD children presented larger body movements than TD children, and that head, trunk, and feet represent the maximum classification with an accuracy of 82.98%. Regarding stimuli, visual condition showed the highest accuracy (89.36%), followed by the visual-auditive stimuli (74.47%), and visual-auditive-olfactory stimuli (70.21%). Finally, the head showed the most consistent performance along with the stimuli, from 80.85% in visual to 89.36% in visual-auditive-olfactory condition. The findings showed the feasibility of applying machine learning and virtual reality to identify body movements' biomarkers that could contribute to improving ASD diagnosis.