Deep Classifier Model for Autism Spectrum Disorder Prediction

2020 ◽  
Author(s):  
Raouia Mokni ◽  
Mariem Haoues
Keyword(s):  
Autism Spectrum Disorder ◽  
Prediction Models ◽  
Disease Diagnosis ◽  
Research Area ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Human Communication ◽  
Machine Learning Classification ◽  
Proposed Model ◽  
And Behavior

Autism Spectrum Disorder (ASD) is a neurological and developmental disorder that affects human communication and behavior. ASD is associated with significant healthcare costs for diagnosis as well as for treatment. Disease diagnosis using deep learning model has become a wide research area. This paper proposes a deep classifier model for ASD prediction. The evaluation of the proposed model is performed over three datasets involving child, adolescent, and adult provided by ASDTest database. The obtained results showed that deep classifier model provides better results than other common machine learning classification techniques, with an accuracy of 99.50%, 99.23% and 99.42% for respectively adult, adolescent, and child datasets. Practical experiments conducted over these datasets report encouraging performances which are competitive to other existing ASD prediction models.

scholarly journals Individuals with Autism Spectrum Disorder: A Review of Human Factors Considerations and Usability Testing Guidelines

2019 ◽  
Vol 63 (1) ◽  
pp. 1575-1579
Author(s):  
McKenna K. Tornblad ◽  
Keith S. Jones ◽  
Fethi A. Inan
Keyword(s):  
Autism Spectrum Disorder ◽  
Human Factors ◽  
Special Needs ◽  
Usability Testing ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Design Considerations ◽  
Proposed Model ◽  
Wide Range ◽  
And Behavior

Individuals with autism spectrum disorder (ASD) display an interest in and affinity for technology; however this population’s wide range of special needs is not often taken into account in technology design or usability testing. To assist human factors professionals in understanding this user population, we present a description of three domains of special needs for those with ASD: information processing, communication, and behavior. We then present a proposed model that human factors professionals could employ to understand the unique characteristics of individuals with ASD. We also synthesize research on design considerations for these users and present a composite list of recommendations for usability testing. Thus, this paper is intended to inform the human factors community of the unique characteristics of this user group, and provide guidelines for both design and usability testing.

scholarly journals A Deep Learning Approach to Predict Autism Spectrum Disorder Using Multisite Resting-State fMRI

2021 ◽  
Vol 11 (8) ◽  
pp. 3636
Author(s):  
Faria Zarin Subah ◽  
Kaushik Deb ◽  
Pranab Kumar Dhar ◽  
Takeshi Koshiba
Keyword(s):  
Autism Spectrum Disorder ◽  
Resting State ◽  
State Of The Art ◽  
Resting State Fmri ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Bootstrap Analysis ◽  
Proposed Model ◽  
Art Methods ◽  
The Mean

Autism spectrum disorder (ASD) is a complex and degenerative neuro-developmental disorder. Most of the existing methods utilize functional magnetic resonance imaging (fMRI) to detect ASD with a very limited dataset which provides high accuracy but results in poor generalization. To overcome this limitation and to enhance the performance of the automated autism diagnosis model, in this paper, we propose an ASD detection model using functional connectivity features of resting-state fMRI data. Our proposed model utilizes two commonly used brain atlases, Craddock 200 (CC200) and Automated Anatomical Labelling (AAL), and two rarely used atlases Bootstrap Analysis of Stable Clusters (BASC) and Power. A deep neural network (DNN) classifier is used to perform the classification task. Simulation results indicate that the proposed model outperforms state-of-the-art methods in terms of accuracy. The mean accuracy of the proposed model was 88%, whereas the mean accuracy of the state-of-the-art methods ranged from 67% to 85%. The sensitivity, F1-score, and area under receiver operating characteristic curve (AUC) score of the proposed model were 90%, 87%, and 96%, respectively. Comparative analysis on various scoring strategies show the superiority of BASC atlas over other aforementioned atlases in classifying ASD and control.

scholarly journals Evaluation of circulating miRNAs and mRNAs expression patterns in autism spectrum disorder

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Amany H. Abdelrahman ◽  
Ola M. Eid ◽  
Mona H. Ibrahim ◽  
Safa N. Abd El-Fattah ◽  
Maha M. Eid ◽  
...  
Keyword(s):  
Autism Spectrum Disorder ◽  
Gene Family ◽  
Complex Disease ◽  
Expression Patterns ◽  
Normal Volunteer ◽  
Disease Diagnosis ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Expression Levels ◽  
Significant Difference

Abstract Background Autism spectrum disorder is a condition related to brain development that affects a person’s perception and socialization, resulting in problems in social interaction and communication. It has no single known cause, yet several different genes appear to be involved in autism. As a genetically complex disease, dysregulation of miRNA expression and miRNA–mRNA interactions might be a feature of autism spectrum disorder. The aim of the current study was to investigate the expression profile of circulating miRNA-128, miRNA-7 and SHANK gene family in ASD patients and to assess the possible influence of miRNA-128 and miRNA-7 on SHANK genes, which might provide an insight into the pathogenic mechanisms of ASD and introduce noninvasive molecular biomarkers for the disease diagnosis and prognosis. Quantitative real-time PCR technique was employed to determine expression levels of miRNA-128, miRNA-7 and SHANK gene family in blood samples of 40 autistic cases along with 30 age- and sex-matched normal volunteer subjects. Results Our study revealed a statistical significant upregulation of miRNA-128 expression levels in ASD cases compared to controls (p value < 0.001). A statistical significant difference in SHANK-3 expression was encountered on comparing cases to controls (p value < 0.001). However, miRNA-7 expression showed no significant difference between the studied groups. Conclusions MiRNA-128 and SHANK-3 gene are emerging players in the field of ASD. They are promising candidates as noninvasive biomarkers in autism. Future studies are needed to emphasize their pivotal role.

scholarly journals The relationship between sleep and behavior in autism spectrum disorder (ASD): a review

2014 ◽  
Vol 6 (1) ◽  
Author(s):  
Simonne Cohen ◽  
Russell Conduit ◽  
Steven W Lockley ◽  
Shantha MW Rajaratnam ◽  
Kim M Cornish
Keyword(s):  
Autism Spectrum Disorder ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
And Behavior ◽  
The Relationship

Screening and Diagnosis of Autism Spectrum Disorder via Assistive Tools

2022 ◽  
pp. 1-21
Author(s):  
Gurkan Tuna ◽  
Ayşe Tuna
Keyword(s):  
Autism Spectrum Disorder ◽  
Random Forest ◽  
Performance Metrics ◽  
Autism Spectrum ◽  
Repetitive Behaviors ◽  
Spectrum Disorder ◽  
K Nearest Neighbors ◽  
Medical Test ◽  
And Behavior

Autism spectrum disorder (ASD) is a challenging developmental condition that involves restricted and/or repetitive behaviors and persistent challenges in social interaction and speech and nonverbal communication. There is not a standard medical test used to diagnose ASD; therefore, diagnosis is made by looking at the child's developmental history and behavior. In recent years, due to the increase in diagnosed cases of ASD, researchers proposed software-based tools to aid in and expedite the diagnosis. Considering the fact that most of these tools rely on the use of classifiers, in study, random forest, decision tree, k-nearest neighbors, and zero rule algorithms are used as classifiers, and their performances are compared using well-known performance metrics. As proven in the study, random forest algorithm can provide higher accuracy than the others in the classification of ASD and can be integrated into a computer- or humanoid-robot-based system for automated prescreening and diagnosis of ASD in preschool children groups.

Differential Diagnosis of Autism Spectrum Disorder Versus Language Disorder in Children Ages 2 to 5 Years: Contributions of Parent-Reported Development and Behavior

2019 ◽  
Vol 58 (11-12) ◽  
pp. 1232-1238
Author(s):  
Annette E. Richard ◽  
Elise K. Hodges ◽  
Martha D. Carlson
Keyword(s):  
Autism Spectrum Disorder ◽  
Differential Diagnosis ◽  
Language Disorder ◽  
Social Withdrawal ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Developmental Problems ◽  
Self Help ◽  
Children With Asd ◽  
And Behavior

Early diagnosis of autism spectrum disorder (ASD) has focused on differentiating children with ASD from neurotypical children. However, many children presenting with concern for ASD are ultimately diagnosed with language disorder (LD). This study aimed to identify differences in parent-rated development and behavior among children ages 2 to 5 years presenting with concern for ASD who were diagnosed with either ASD or LD. Children with ASD were rated as more socially withdrawn and more delayed in social development and self-help skills than those with LD. Parent-rated developmental delays were positively correlated with scores on an autism screening measure and with social withdrawal and pervasive developmental problems among children with ASD. Among those with LD, parent-rated social and self-help development were positively correlated with social withdrawal and attention problems. Thus, parent ratings of social withdrawal and development of social and self-help skills may facilitate differential diagnosis of ASD and LD in children ages 2 to 5 years.

scholarly journals No Differences in Emotion Recognition Strategies in Children with Autism Spectrum Disorder: Evidence from Hybrid Faces

2014 ◽  
Vol 2014 ◽  
pp. 1-8 ◽  
Author(s):  
Kris Evers ◽  
Inneke Kerkhof ◽  
Jean Steyaert ◽  
Ilse Noens ◽  
Johan Wagemans
Keyword(s):  
Autism Spectrum Disorder ◽  
Emotion Recognition ◽  
Facial Expressions ◽  
Research Area ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Correct Identification ◽  
Face Region ◽  
Processing Strategies ◽  
Neutral Expression

Emotion recognition problems are frequently reported in individuals with an autism spectrum disorder (ASD). However, this research area is characterized by inconsistent findings, with atypical emotion processing strategies possibly contributing to existing contradictions. In addition, an attenuated saliency of the eyes region is often demonstrated in ASD during face identity processing. We wanted to compare reliance on mouth versus eyes information in children with and without ASD, using hybrid facial expressions. A group of six-to-eight-year-old boys with ASD and an age- and intelligence-matched typically developing (TD) group without intellectual disability performed an emotion labelling task with hybrid facial expressions. Five static expressions were used: one neutral expression and four emotional expressions, namely, anger, fear, happiness, and sadness. Hybrid faces were created, consisting of an emotional face half (upper or lower face region) with the other face half showing a neutral expression. Results showed no emotion recognition problem in ASD. Moreover, we provided evidence for the existence of top- and bottom-emotions in children: correct identification of expressions mainly depends on information in the eyes (so-called top-emotions: happiness) or in the mouth region (so-called bottom-emotions: sadness, anger, and fear). No stronger reliance on mouth information was found in children with ASD.

scholarly journals Autistic Spectrum Disorder in the Context of Pandemic by Covid-19: Caring for Children and Caregivers

2021 ◽  
Author(s):  
José Vilelas
Keyword(s):  
Autism Spectrum Disorder ◽  
Neurodevelopmental Disorders ◽  
Scientific Evidence ◽  
Children With Autism ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Special Importance ◽  
Negative Behaviors ◽  
The Family ◽  
And Behavior

The COVID-19 pandemic has brought important challenges to society and families, with repercussions on child behavior and development with special importance for children with neurodevelopmental disorders that affect and impair the child’s functionality: Autism spectrum disorder. Thus, we set as objective to Identify and analyze the scientific evidence of interventions performed on children with Autism Spectrum Disorder in the context of a Covid-19 pandemic. A search was conducted in the MEDLINE, PubMed, CINHAL databases and gray literature. Children with Autism Spectrum Disorders (EAP) may become more anxious, agitated and unregulated with the change in routines to which they are subjected in this phase of the Covid 19 pandemic. Autism disorders affect communication, social interaction and behavior, usually with a tendency to be repetitive and routine, but in a scenario of pandemic and social isolation, anxiety and agitation may be more pronounced and, in more severe cases, there may be less capacity to function. It is important that the family of the child with ASD propose cooperative activities or resources that they have at home and that can be adapted. The insertion of some tasks contributes to the establishment of the ability to play independently. In it, the child gets involved independently. And so it prevents negative behaviors from occurring due to leisure and the need for attention, also favoring concentration.

scholarly journals Technology-Assisted Intervention for Children with Autism Spectrum Disorder using Augmented Reality

2020 ◽  
Vol 8 (5) ◽  
pp. 2156-2162
Keyword(s):  
Autism Spectrum Disorder ◽  
Augmented Reality ◽  
Social Communication ◽  
Children With Autism ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Children With Asd ◽  
The Social ◽  
Behavior Skills ◽  
And Behavior

Technology-assisted intervention has potentials in improving the social, communication and behavior impairments in of children with autism spectrum disorder (ASD). Augmented reality (AR) offers multitude of possibilities and opportunities for the intervention of children with ASD. Therefore, this study identifies 13 researches from 2012 to 2018 that documented the efficacy of augmented reality applications in supporting the intervention of children with ASD. This study reviews the applications of augmented reality that nhanced the intervention for children with autism in (i) social skills, (ii) communication skills, and (iii) behavior skills. The conclusion reports the significant roles of augmented reality as technology-assisted intervention for children with ASD.

scholarly journals Caregiver Daily Reporting of Symptoms in Autism Spectrum Disorder: Observational Study Using Web and Mobile Apps (Preprint)

2018 ◽  
Author(s):  
Abigail Bangerter ◽  
Nikolay V. Manyakov ◽  
David Lewin ◽  
Matthew Boice ◽  
Andrew Skalkin ◽  
...  
Keyword(s):  
Clinical Trial ◽  
Autism Spectrum Disorder ◽  
Observational Study ◽  
Mobile Apps ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Web Based ◽  
Paper And Pencil ◽  
And Behavior ◽  
Retrospective Reporting

BACKGROUND Currently, no medications are approved to treat core symptoms of autism spectrum disorder (ASD). One barrier to ASD medication development is the lack of validated outcome measures able to detect symptom change. Current ASD interventions are often evaluated using retrospective caregiver reports that describe general clinical presentation but often require recall of specific behaviors weeks after they occur, potentially reducing accuracy of the ratings. My JAKE, a mobile and Web-based mobile health (mHealth) app that is part of the Janssen Autism Knowledge Engine—a dynamically updated clinical research system—was designed to help caregivers of individuals with ASD to continuously log symptoms, record treatments, and track progress, to mitigate difficulties associated with retrospective reporting. OBJECTIVE My JAKE was deployed in an exploratory, noninterventional clinical trial to evaluate its utility and acceptability to monitor clinical outcomes in ASD. Hypotheses regarding relationships among daily tracking of symptoms, behavior, and retrospective caregiver reports were tested. METHODS Caregivers of individuals with ASD aged 6 years to adults (N=144) used the My JAKE app to make daily reports on their child’s sleep quality, affect, and other self-selected specific behaviors across the 8- to 10-week observational study. The results were compared with commonly used paper-and-pencil scales acquired over a concurrent period at regular 4-week intervals. RESULTS Caregiver reporting of behaviors in real time was successfully captured by My JAKE. On average, caregivers made reports 2-3 days per week across the study period. Caregivers were positive about their use of the system, with over 50% indicating that they would like to use My JAKE to track behavior outside of a clinical trial. More positive average daily reporting of overall type of day was correlated with 4 weekly reports of lower caregiver burden made at 4-week intervals (r=–0.27, P=.006, n=88) and with ASD symptoms (r=–0.42, P<.001, n=112). CONCLUSIONS My JAKE reporting aligned with retrospective Web-based or paper-and-pencil scales. Use of mHealth apps, such as My JAKE, has the potential to increase the validity and accuracy of caregiver-reported outcomes and could be a useful way of identifying early changes in response to intervention. Such systems may also assist caregivers in tracking symptoms and behavior outside of a clinical trial, help with personalized goal setting, and monitoring of progress, which could collectively improve understanding of and quality of life for individuals with ASD and their families. CLINICALTRIAL ClinicalTrials.gov NCT02668991; https://clinicaltrials.gov/ct2/show/NCT02668991 

Sign in / Sign up

Export Citation Format

Share Document