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.

Download Full-text

Perceptions of Autism Spectrum Disorder (ASD) Etiology among Parents of Children with ASD

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph18136774 ◽

2021 ◽

Vol 18 (13) ◽

pp. 6774

Author(s):

Wei-Ju Chen ◽

Zihan Zhang ◽

Haocen Wang ◽

Tung-Sung Tseng ◽

Ping Ma ◽

...

Keyword(s):

Autism Spectrum Disorder ◽

Content Analysis ◽

Neurodevelopmental Disorder ◽

Autism Spectrum ◽

Parental Perceptions ◽

Repetitive Behaviors ◽

Spectrum Disorder ◽

Structured Interviews ◽

Children With Asd ◽

Religious Factors

Background: Autism spectrum disorder (ASD) is a neurodevelopmental disorder characterized by social communication deficits and restricted or repetitive behaviors. Parental perceptions of the etiology of their child’s ASD can affect provider–client relationships, bonding between parents and their children, and the prognosis, treatment, and management of children with ASD. Thus, this study sought to examine the perceptions of ASD etiology of parents of children with ASD. Methods: Forty-two parents of children diagnosed with ASD were recruited across Texas. Semi-structured interviews were conducted individually. All interviews were recorded and later transcribed verbatim for content analysis utilizing NVivo 12.0 (QSR International, Doncaster, Australia). Results: The content analysis identified the following themes regarding parental perceptions of ASD etiology: Genetic factors (40.5%), environmental factors (31.0%), problems that occurred during pregnancy or delivery (23.8%), vaccinations (16.7%), other health problems (7.1%), parental age at the time of pregnancy (4.8%), and spiritual or religious factors (2.4%). Conclusions: The parental perceptions of ASD etiology were diverse, but several views, such as vaccinations and spiritual or religious factors, were not based on scientific evidence. Health professionals and researchers can use these findings to develop and provide targeted education to parents who have children with ASD. Our findings also support policymakers in developing campaigns designed to increase parental ASD awareness and knowledge.

Download Full-text

Genotype-Based Deep Learning in Autism Spectrum Disorder: Diagnostic Classification and Prognostic Prediction Using Common Genetic Variants (Preprint)

10.2196/preprints.24754 ◽

2020 ◽

Author(s):

Haishuai Wang ◽

Paul Avillach

Keyword(s):

Machine Learning ◽

Autism Spectrum Disorder ◽

Deep Learning ◽

The United States ◽

Autism Spectrum ◽

Repetitive Behaviors ◽

Spectrum Disorder ◽

Screening Tools ◽

Common Variants ◽

Autism Screening

BACKGROUND In the United States, about 3 million people have autism spectrum disorder (ASD), and around 1 out of 59 children are diagnosed with ASD. People with ASD have characteristic social communication deficits and repetitive behaviors. The causes of this disorder remain unknown; however, in up to 25% of cases, a genetic cause can be identified. Detecting ASD as early as possible is desirable because early detection of ASD enables timely interventions in children with ASD. Identification of ASD based on objective pathogenic mutation screening is the major first step toward early intervention and effective treatment of affected children. OBJECTIVE Recent investigation interrogated genomics data for detecting and treating autism disorders, in addition to the conventional clinical interview as a diagnostic test. Since deep neural networks perform better than shallow machine learning models on complex and high-dimensional data, in this study, we sought to apply deep learning to genetic data obtained across thousands of simplex families at risk for ASD to identify contributory mutations and to create an advanced diagnostic classifier for autism screening. METHODS After preprocessing the genomics data from the Simons Simplex Collection, we extracted top ranking common variants that may be protective or pathogenic for autism based on a chi-square test. A convolutional neural network–based diagnostic classifier was then designed using the identified significant common variants to predict autism. The performance was then compared with shallow machine learning–based classifiers and randomly selected common variants. RESULTS The selected contributory common variants were significantly enriched in chromosome X while chromosome Y was also discriminatory in determining the identification of autistic from nonautistic individuals. The ARSD, MAGEB16, and MXRA5 genes had the largest effect in the contributory variants. Thus, screening algorithms were adapted to include these common variants. The deep learning model yielded an area under the receiver operating characteristic curve of 0.955 and an accuracy of 88% for identifying autistic from nonautistic individuals. Our classifier demonstrated a significant improvement over standard autism screening tools by average 13% in terms of classification accuracy. CONCLUSIONS Common variants are informative for autism identification. Our findings also suggest that the deep learning process is a reliable method for distinguishing the diseased group from the control group based on the common variants of autism.

Download Full-text

Risk Factors for Unhealthy Weight Gain and Obesity among Children with Autism Spectrum Disorder

International Journal of Molecular Sciences ◽

10.3390/ijms20133285 ◽

2019 ◽

Vol 20 (13) ◽

pp. 3285 ◽

Cited By ~ 9

Author(s):

Khushmol K. Dhaliwal ◽

Camila E. Orsso ◽

Caroline Richard ◽

Andrea M. Haqq ◽

Lonnie Zwaigenbaum

Keyword(s):

Risk Factors ◽

Autism Spectrum Disorder ◽

Weight Gain ◽

Autism Spectrum ◽

Lifestyle Factors ◽

Repetitive Behaviors ◽

Spectrum Disorder ◽

Future Research ◽

Children With Asd ◽

Unhealthy Weight

Autism Spectrum Disorder (ASD) is a developmental disorder characterized by social and communication deficits and repetitive behaviors. Children with ASD are also at a higher risk for developing overweight or obesity than children with typical development (TD). Childhood obesity has been associated with adverse health outcomes, including insulin resistance, diabetes, heart disease, and certain cancers. Importantly some key factors that play a mediating role in these higher rates of obesity include lifestyle factors and biological influences, as well as secondary comorbidities and medications. This review summarizes current knowledge about behavioral and lifestyle factors that could contribute to unhealthy weight gain in children with ASD, as well as the current state of knowledge of emerging risk factors such as the possible influence of sleep problems, the gut microbiome, endocrine influences and maternal metabolic disorders. We also discuss some of the clinical implications of these risk factors and areas for future research.

Download Full-text

An Epigenetically Distinct Subset of Children With Autism Spectrum Disorder Resulting From Differences in Blood Cell Composition

Frontiers in Neurology ◽

10.3389/fneur.2021.612817 ◽

2021 ◽

Vol 12 ◽

Author(s):

Maryam Jangjoo ◽

Sarah J. Goodman ◽

Sanaa Choufani ◽

Brett Trost ◽

Stephen W. Scherer ◽

...

Keyword(s):

Autism Spectrum Disorder ◽

Blood Cell ◽

Autism Spectrum ◽

Differential Methylation ◽

Repetitive Behaviors ◽

Spectrum Disorder ◽

Risk Genes ◽

Immune Systems ◽

Cell Composition ◽

Children With Asd

Background: Autism spectrum disorder (ASD) is a complex neurodevelopmental disorder that often involves impaired cognition, communication difficulties and restrictive, repetitive behaviors. ASD is extremely heterogeneous both clinically and etiologically, which represents one of the greatest challenges in studying the molecular underpinnings of ASD. While hundreds of ASD-associated genes have been identified that confer varying degrees of risk, no single gene variant accounts for >1% of ASD cases. Notably, a large number of ASD-risk genes function as epigenetic regulators, indicating potential epigenetic dysregulation in ASD. As such, we compared genome-wide DNA methylation (DNAm) in the blood of children with ASD (n = 265) to samples from age- and sex-matched, neurotypical controls (n = 122) using the Illumina Infinium HumanMethylation450 arrays.Results: While DNAm patterns did not distinctly separate ASD cases from controls, our analysis identified an epigenetically unique subset of ASD cases (n = 32); these individuals exhibited significant differential methylation from both controls than the remaining ASD cases. The CpG sites at which this subset was differentially methylated mapped to known ASD risk genes that encode proteins of the nervous and immune systems. Moreover, the observed DNAm differences were attributable to altered blood cell composition, i.e., lower granulocyte proportion and granulocyte-to-lymphocyte ratio in the ASD subset, as compared to the remaining ASD cases and controls. This ASD subset did not differ from the rest of the ASD cases in the frequency or type of high-risk genomic variants.Conclusion: Within our ASD cohort, we identified a subset of individuals that exhibit differential methylation from both controls and the remaining ASD group tightly associated with shifts in immune cell type proportions. This is an important feature that should be assessed in all epigenetic studies of blood cells in ASD. This finding also builds on past reports of changes in the immune systems of children with ASD, supporting the potential role of altered immunological mechanisms in the complex pathophysiology of ASD. The discovery of significant molecular and immunological features in subgroups of individuals with ASD may allow clinicians to better stratify patients, facilitating personalized interventions and improved outcomes.

Download Full-text

A new machine learning model based on induction of rules for autism detection

Health Informatics Journal ◽

10.1177/1460458218824711 ◽

2019 ◽

Vol 26 (1) ◽

pp. 264-286 ◽

Cited By ~ 22

Author(s):

Fadi Thabtah ◽

David Peebles

Keyword(s):

Machine Learning ◽

Autism Spectrum Disorder ◽

Autism Spectrum ◽

Classification Systems ◽

Repetitive Behaviors ◽

Spectrum Disorder ◽

Medical Psychology ◽

Screening Methods ◽

Autism Spectrum Quotient ◽

New Machine

Autism spectrum disorder is a developmental disorder that describes certain challenges associated with communication (verbal and non-verbal), social skills, and repetitive behaviors. Typically, autism spectrum disorder is diagnosed in a clinical environment by licensed specialists using procedures which can be lengthy and cost-ineffective. Therefore, scholars in the medical, psychology, and applied behavioral science fields have in recent decades developed screening methods such as the Autism Spectrum Quotient and Modified Checklist for Autism in Toddlers for diagnosing autism and other pervasive developmental disorders. The accuracy and efficiency of these screening methods rely primarily on the experience and knowledge of the user, as well as the items designed in the screening method. One promising direction to improve the accuracy and efficiency of autism spectrum disorder detection is to build classification systems using intelligent technologies such as machine learning. Machine learning offers advanced techniques that construct automated classifiers that can be exploited by users and clinicians to significantly improve sensitivity, specificity, accuracy, and efficiency in diagnostic discovery. This article proposes a new machine learning method called Rules-Machine Learning that not only detects autistic traits of cases and controls but also offers users knowledge bases (rules) that can be utilized by domain experts in understanding the reasons behind the classification. Empirical results on three data sets related to children, adolescents, and adults show that Rules-Machine Learning offers classifiers with higher predictive accuracy, sensitivity, harmonic mean, and specificity than those of other machine learning approaches such as Boosting, Bagging, decision trees, and rule induction.

Download Full-text

A Systematic Literature Review on the Application of Machine-Learning Models in Behavioral Assessment of Autism Spectrum Disorder

Journal of Personalized Medicine ◽

10.3390/jpm11040299 ◽

2021 ◽

Vol 11 (4) ◽

pp. 299

Author(s):

Nadire Cavus ◽

Abdulmalik A. Lawan ◽

Zurki Ibrahim ◽

Abdullahi Dahiru ◽

Sadiya Tahir ◽

...

Keyword(s):

Machine Learning ◽

Autism Spectrum Disorder ◽

Social Communication ◽

Behavioral Assessment ◽

Real Life ◽

Autism Spectrum ◽

Spectrum Disorder ◽

Diagnostic Tools ◽

Diagnostic Systems ◽

Behavioral Challenges

Autism spectrum disorder (ASD) is associated with significant social, communication, and behavioral challenges. The insufficient number of trained clinicians coupled with limited accessibility to quick and accurate diagnostic tools resulted in overlooking early symptoms of ASD in children around the world. Several studies have utilized behavioral data in developing and evaluating the performance of machine learning (ML) models toward quick and intelligent ASD assessment systems. However, despite the good evaluation metrics achieved by the ML models, there is not enough evidence on the readiness of the models for clinical use. Specifically, none of the existing studies reported the real-life application of the ML-based models. This might be related to numerous challenges associated with the data-centric techniques utilized and their misalignment with the conceptual basis upon which professionals diagnose ASD. The present work systematically reviewed recent articles on the application of ML in the behavioral assessment of ASD, and highlighted common challenges in the studies, and proposed vital considerations for real-life implementation of ML-based ASD screening and diagnostic systems. This review will serve as a guide for researchers, neuropsychiatrists, psychologists, and relevant stakeholders on the advances in ASD screening and diagnosis using ML.

Download Full-text

The Role of Vitamin D Supplementation in Children with Autism Spectrum Disorder: A Narrative Review

Nutrients ◽

10.3390/nu14010026 ◽

2021 ◽

Vol 14 (1) ◽

pp. 26

Author(s):

Monia Kittana ◽

Asma Ahmadani ◽

Lily Stojanovska ◽

Amita Attlee

Keyword(s):

Autism Spectrum Disorder ◽

Vitamin D ◽

Vitamin D Deficiency ◽

Children With Autism ◽

Autism Spectrum ◽

Vitamin D Supplementation ◽

Repetitive Behaviors ◽

Spectrum Disorder ◽

Cochrane Library ◽

Children With Asd

Children with autism spectrum disorder (ASD) present with persistent deficits in both social communication and interactions, along with the presence of restricted and repetitive behaviors, resulting in significant impairment in significant areas of functioning. Children with ASD consistently reported significantly lower vitamin D levels than typically developing children. Moreover, vitamin D deficiency was found to be strongly correlated with ASD severity. Theoretically, vitamin D can affect neurodevelopment in children with ASD through its anti-inflammatory properties, stimulating the production of neurotrophins, decreasing the risk of seizures, and regulating glutathione and serotonin levels. A Title/Abstract specific search for publications on Vitamin D supplementation trials up to June 2021 was performed using two databases: PubMed and Cochrane Library. Twelve experimental studies were included in the synthesis of this review. Children with ASD reported a high prevalence of vitamin D deficiency or insufficiency. In general, it was observed that improved vitamin D status significantly reduced the ASD severity, however, this effect was not consistently different between the treatment and control groups. The variations in vitamin D dose protocols and the presence of concurrent interventions might provide an explanation for the variability of results. The age of the child for introducing vitamin D intervention was identified as a possible factor determining the effectiveness of the treatment. Common limitations included a small number of participants and a short duration of follow-ups in the selected studies. Long-term, well-designed randomized controlled trials are warranted to confirm the effect of vitamin D on severity in children with ASD.

Download Full-text

Improving communication for children with ASD using AAC

10.54455/mcn.18.05.902282 ◽

2021 ◽

Vol 6 (18) ◽

Author(s):

Soojin Jang

Keyword(s):

Autism Spectrum Disorder ◽

Nonverbal Communication ◽

Children With Autism ◽

Autism Spectrum ◽

Repetitive Behaviors ◽

Spectrum Disorder ◽

Great Range ◽

Children With Asd ◽

Developmental Condition ◽

Over Time

Autism spectrum disorder (ASD) is a complex developmental condition that involves persistent challenges in social interaction, speech and nonverbal communication, and restricted/repetitive behaviors. The effects of ASD and the severity of symptoms are different in each person. Autism differs from person to person in severity and combinations of symptoms. There is a great range of abilities and characteristics of children with autism spectrum disorder — no two children appear or behave the same way. Symptoms can range from mild to severe and often change over time .

Download Full-text

Health care providers’ awareness on medical management of children with autism spectrum disorder: cross-sectional study in Russia

BMC Medical Education ◽

10.1186/s12909-021-03095-8 ◽

2022 ◽

Vol 22 (1) ◽

Author(s):

Y. O. Mukhamedshina ◽

R. A. Fayzullina ◽

I. A. Nigmatullina ◽

C. S. Rutland ◽

V. V. Vasina

Keyword(s):

Health Care ◽

Autism Spectrum Disorder ◽

Health Care Providers ◽

Medical Management ◽

Autism Spectrum ◽

Repetitive Behaviors ◽

Spectrum Disorder ◽

Care Providers ◽

Positive Effects ◽

Children With Asd

Abstract Background Autism spectrum disorder (ASD) is a complex developmental range of conditions that involves difficulties with social interaction and restricted/repetitive behaviors. Unfortunately, health care providers often experience difficulties in diagnosis and management of individuals with ASD, and may have no knowledge about possible ways to overcome barriers in ASD patient interactions in healthcare settings. At the same time, the provision of appropriate medical services can have positive effects on habilitative progress, functional outcome, life expectancy and quality of life for individuals with ASD. Methods This online survey research study evaluated the awareness and experience of students/residents (n = 247) and physicians (n = 100) in the medical management of children with ASD. It also gathered the views and experiences of caregivers to children with ASD (n = 158), all based in Russia. Results We have established that the Russian medical community has limited ASD knowledge among providers, and have suggested possible reasons for this. Based on results from online surveys completed by students/residents, non-psychiatric physicians, and caregivers of children diagnosed with ASD, the main problems pertaining to medical management of individuals with ASD were identified. Possible problem solving solutions within medical practice were proposed. Conclusions The results from this study should be considered when implementing measures to improve healthcare practices, and when developing models for effective medical management, due to start not only in Russia but also in a number of other countries.

Download Full-text

Reaction and Learning Evaluation of a Non-immersive Virtual Reality Application for Children with Autism Spectrum Disorder

F1000Research ◽

10.12688/f1000research.73386.1 ◽

2021 ◽

Vol 10 ◽

pp. 1020

Author(s):

Muhamad Irfan Rosli ◽

Zarina Embi ◽

Junaidi Abdullah ◽

Mohd Ali Samsudin ◽

Mohamad Izani Zainal Abidin ◽

...

Keyword(s):

Autism Spectrum Disorder ◽

Virtual Reality ◽

Autism Spectrum ◽

Spectrum Disorder ◽

Positive Trend ◽

Immersive Virtual Reality ◽

Children With Asd ◽

Post Test ◽

Level 1 ◽

Level 2

Background: Autism Spectrum Disorder (ASD) is a complex developmental condition that involves persistent challenges in social interaction, speech, and nonverbal communication, in addition to repetitive or restrictive behaviours. For decades, children with ASD have been familiarising themselves with information and communication technologies (ICT) in their training and diagnosis. One of the ICT areas, namely non-immersive virtual reality (NIVR), has become a noticeable tool to help ASD children in their social training. It provides extensive virtual interaction, a safe environment, and is affordable. An NIVR application is developed to assist the intervention on ASD children. However, the whole experiences of the training need to be validated to conclude its effectiveness. Methods: A case study was employed as the research method. An evaluation of NIVR application using multiple sources of evidence was guided by Kirkpatrick Model of Evaluation (KME) which was executed via questionnaires, pre- and post-test. The main objectives of this research were to evaluate level 1 and 2 of KME. The target for Level 1 is to assess the reactions to the NIVR application. Level 2 is to gauge the knowledge, confidence, or mindset of participants. Level 2 covers the evaluation prior to the training (pre-test) and after the training (post-test). Results: On average the ASD children had good experiences and were able to improve their social skills with the NIVR application. Therefore, the combination of serious game, analytics and specific VR type provides good data assessment, facilitate comfortable training, and can be an effective intervention for children with ASD. Conclusion: The positive trend on both levels shows that the application has a good potential to be used in ASD training. The results could be improved in a higher number of participants. Currently, only a limited number of research participants could be obtained due to the COVID-19 pandemic.

Download Full-text