scholarly journals The Contribution of Machine Learning and Eye-Tracking Technology in Autism Spectrum Disorder Research: A Systematic Review

Electronics ◽  
2021 ◽  
Vol 10 (23) ◽  
pp. 2982
Author(s):  
Konstantinos-Filippos Kollias ◽  
Christine K. Syriopoulou-Delli ◽  
Panagiotis Sarigiannidis ◽  
George F. Fragulis
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Autism Spectrum Disorder ◽  
Eye Tracking ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Assessment Tools ◽  
Future Research ◽  
Promising Tool ◽  
Tracking Technology

Early and objective autism spectrum disorder (ASD) assessment, as well as early intervention are particularly important and may have long term benefits in the lives of ASD people. ASD assessment relies on subjective rather on objective criteria, whereas advances in research point to up-to-date procedures for early ASD assessment comprising eye-tracking technology, machine learning, as well as other assessment tools. This systematic review, the first to our knowledge of its kind, provides a comprehensive discussion of 30 studies irrespective of the stimuli/tasks and dataset used, the algorithms applied, the eye-tracking tools utilised and their goals. Evidence indicates that the combination of machine learning and eye-tracking technology could be considered a promising tool in autism research regarding early and objective diagnosis. Limitations and suggestions for future research are also presented.

Diagnostic test accuracy for use of machine learning in diagnosis of autism spectrum disorder: A Systematic Review and Meta-Analysis (Preprint)

2019 ◽  
Author(s):  
Sun Jae Moon ◽  
Jin Seub Hwang ◽  
Rajesh Kana ◽  
John Torous ◽  
Jung Won Kim
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Autism Spectrum Disorder ◽  
Meta Analysis ◽  
Learning Algorithms ◽  
Structural Mri ◽  
Autism Spectrum ◽  
Machine Learning Algorithms ◽  
Spectrum Disorder ◽  
Test Accuracy

BACKGROUND Over the recent years, machine learning algorithms have been more widely and increasingly applied in biomedical fields. In particular, its application has been drawing more attention in the field of psychiatry, for instance, as diagnostic tests/tools for autism spectrum disorder. However, given its complexity and potential clinical implications, there is ongoing need for further research on its accuracy. OBJECTIVE The current study aims to summarize the evidence for the accuracy of use of machine learning algorithms in diagnosing autism spectrum disorder (ASD) through systematic review and meta-analysis. METHODS MEDLINE, Embase, CINAHL Complete (with OpenDissertations), PsyINFO and IEEE Xplore Digital Library databases were searched on November 28th, 2018. Studies, which used a machine learning algorithm partially or fully in classifying ASD from controls and provided accuracy measures, were included in our analysis. Bivariate random effects model was applied to the pooled data in meta-analysis. Subgroup analysis was used to investigate and resolve the source of heterogeneity between studies. True-positive, false-positive, false negative and true-negative values from individual studies were used to calculate the pooled sensitivity and specificity values, draw SROC curves, and obtain area under the curve (AUC) and partial AUC. RESULTS A total of 43 studies were included for the final analysis, of which meta-analysis was performed on 40 studies (53 samples with 12,128 participants). A structural MRI subgroup meta-analysis (12 samples with 1,776 participants) showed the sensitivity at 0.83 (95% CI-0.76 to 0.89), specificity at 0.84 (95% CI -0.74 to 0.91), and AUC/pAUC at 0.90/0.83. An fMRI/deep neural network (DNN) subgroup meta-analysis (five samples with 1,345 participants) showed the sensitivity at 0.69 (95% CI- 0.62 to 0.75), the specificity at 0.66 (95% CI -0.61 to 0.70), and AUC/pAUC at 0.71/0.67. CONCLUSIONS Machine learning algorithms that used structural MRI features in diagnosis of ASD were shown to have accuracy that is similar to currently used diagnostic tools.

A Systematic Review of Effects of Social Stories Interventions for Individuals With Autism Spectrum Disorder

2015 ◽  
Vol 33 (1) ◽  
pp. 25-34 ◽  
Author(s):  
Cathy H. Qi ◽  
Erin E. Barton ◽  
Margo Collier ◽  
Yi-Ling Lin ◽  
Charisse Montoya
Keyword(s):  
Systematic Review ◽  
Autism Spectrum Disorder ◽  
Visual Analysis ◽  
Causal Relation ◽  
Single Case ◽  
Social Stories ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Future Research ◽  
Design Standards

The purpose of this systematic review was to synthesize 22 single-case research design (SCRD) studies on social stories intervention for individuals with autism spectrum disorder (ASD). We used the What Works Clearinghouse (WWC) SCRD standards to analyze study rigor and evidence of a causal relation. We calculated four nonoverlap indices to evaluate intervention, maintenance, and generalization effects. Results suggested that all studies met the WWC design standards with or without reservations. Seven studies (32%) provided strong or moderate evidence of a causal relation. Nonoverlap indices calculations indicated social stories intervention was effective. Using the WWC 5-3-20 guidelines to determine evidence of social stories, social stories intervention would not be considered an evidence-based practice (EBP) for individuals with ASD based on visual analysis, but would be deemed an EBP based on nonoverlap indices. It is worth noting that WWC used visual analysis, not nonoveralap indices, to determine whether an intervention meets the 5-3-20 replication rule. Findings of the systematic review showed there were discrepancies. Implications for future research and practice are discussed.

A Systematic Review of Law Enforcement Training Related to Autism Spectrum Disorder

2020 ◽  
Vol 35 (4) ◽  
pp. 221-233 ◽  
Author(s):  
Kirsten S. Railey ◽  
Abigail M. A. Love ◽  
Jonathan M. Campbell
Keyword(s):  
Systematic Review ◽  
Autism Spectrum Disorder ◽  
Law Enforcement ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Future Research ◽  
Law Enforcement Training ◽  
Training Format ◽  
Effectiveness Of Training ◽  
Meta Analyses

Although research confirms the effectiveness of training to improve law enforcement officers’ (LEOs) awareness and knowledge of people with intellectual disability and learning disabilities, review of the efficacy of autism-specific law enforcement training is needed. To provide up-to-date information regarding training for LEOs related to autism spectrum disorder (ASD), a systematic review of the literature was conducted. Adhering to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses for Protocols (PRISMA), we conducted a search of 13 professional databases and 28 journals using search terms related to both ASD and law enforcement training. From 606 articles identified during the initial search, only two articles met inclusion criteria, which suggests that limited research exists that explores ASD and law enforcement training. Included studies were summarized in terms of participants as well as training format, content, and outcomes. Limitations of the current literature, directions for future research, and current implications for practice are discussed.

Schizophrenia and Other Psychotic Disorders in Autism Spectrum Disorder

2020 ◽  
pp. 51-72
Author(s):  
Katherine Gotham ◽  
Florencia Pezzimenti ◽  
Mareike Eydt-Beebe ◽  
Gloria T. Han ◽  
Catherine G. Herrington
Keyword(s):  
Autism Spectrum Disorder ◽  
Best Practice ◽  
Psychotic Disorders ◽  
Historical Context ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Assessment Tools ◽  
Psychotic Symptoms ◽  
Future Research ◽  
Schizophrenia Spectrum Disorders

There is substantial data pointing to evidence of heightened rates of psychotic experiences and schizophrenia spectrum disorders in individuals with autism spectrum disorder (ASD). Given overlapping genetics and neurobiology between the two disorders, the prevalence of this comorbidity is not surprising. And yet, psychosis in ASD has received relatively little attention in either the scientific or the clinical literatures. Following an introduction to the shared historical context of schizophrenia and ASD, this chapter reviews the diagnostic criteria for psychosis and the assessment tools available for evaluating symptoms. Difficulties in differentiating true psychotic symptoms from several hallmark ASD features, as well as in diagnosing psychosis in minimally verbal individuals with ASD, are highlighted, and recommendations for making this diagnostic distinction are offered. With regard to treatment, there is a striking absence of literature addressing how to treat psychosis when it presents in individuals with ASD. This chapter highlights best practice treatments for childhood-onset and adult schizophrenia and related disorders and discusses how these treatments might apply or need adaptation when treating an individual with ASD. Finally, this chapter offers recommendations for future research regarding the nature, prevalence, developmental course, assessment, and most effective treatments for schizophrenia and other psychotic disorders when they present in individuals with ASD.

Morality in autism spectrum disorder: A systematic review

2019 ◽  
Vol 32 (3) ◽  
pp. 1069-1085
Author(s):  
E. E. Dempsey ◽  
C. Moore ◽  
S. A. Johnson ◽  
S. H. Stewart ◽  
I. M. Smith
Keyword(s):  
Systematic Review ◽  
Decision Making ◽  
Autism Spectrum Disorder ◽  
Moral Development ◽  
Interpersonal Relationships ◽  
Critical Evaluation ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Future Research ◽  
Moral Decision Making

AbstractMoral reasoning and decision making help guide behavior and facilitate interpersonal relationships. Accounts of morality that position commonsense psychology as the foundation of moral development, (i.e., rationalist theories) have dominated research in morality in autism spectrum disorder (ASD). Given the well-documented differences in commonsense psychology among autistic individuals, researchers have investigated whether the development and execution of moral judgement and reasoning differs in this population compared with neurotypical individuals. In light of the diverse findings of investigations of moral development and reasoning in ASD, a summation and critical evaluation of the literature could help make sense of what is known about this important social-cognitive skill in ASD. To that end, we conducted a systematic review of the literature investigating moral decision making among autistic children and adults. Our search identified 29 studies. In this review, we synthesize the research in the area and provide suggestions for future research. Such research could include the application of an alternative theoretical framework to studying morality in autism spectrum disorder that does not assume a deficits-based perspective.

Measuring change in facial emotion recognition in individuals with autism spectrum disorder: A systematic review

Autism ◽  
2020 ◽  
Vol 24 (7) ◽  
pp. 1607-1628
Author(s):  
Andrea Trubanova Wieckowski ◽  
L Taylor Flynn ◽  
J Anthony Richey ◽  
Denis Gracanin ◽  
Susan W White
Keyword(s):  
Autism Spectrum Disorder ◽  
Emotion Recognition ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Assessment Tools ◽  
Facial Emotion Recognition ◽  
Facial Emotion ◽  
Future Research ◽  
Adults With Autism ◽  
Electronic Database Search

Children and adults with autism spectrum disorder are less accurate in facial emotion recognition, which is thought to contribute to impairment in social functioning. Although many interventions have been developed to improve facial emotion recognition, there is no consensus on how to best measure facial emotion recognition in people with autism spectrum disorder. This lack of agreement has led to wide variability in how facial emotion recognition is measured and, subsequently, inconsistent findings related to impact of intervention targeting facial emotion recognition impairment. The purpose of this review is to synthesize the extant research on measurement of facial emotion recognition in the context of treatment. We conducted an electronic database search to identify relevant, peer-reviewed articles published between January 1998 and November 2019 to identify studies evaluating change in facial emotion recognition in autism spectrum disorder. Sixty-five studies met inclusion criteria, utilizing a total of 36 different assessment measures for facial emotion recognition in individuals with autism spectrum disorder. Only six of the measures were used in multiple studies conducted by different investigative teams. The outcomes of the studies are reported and summarized with the goal of informing future research. Lay Abstract Children and adults with autism spectrum disorder show difficulty recognizing facial emotions in others, which makes social interaction challenging. While there are many treatments developed to improve facial emotion recognition, there is no agreement on the best way to measure such abilities in individuals with autism spectrum disorder. The purpose of this review is to examine studies that were published between January 1998 and November 2019 and have measured change in facial emotion recognition to evaluate the effectiveness of different treatments. Our search yielded 65 studies, and within these studies, 36 different measures were used to evaluate facial emotion recognition in individuals with autism spectrum disorder. Only six of these measures, however, were used in different studies and by different investigators. In this review, we summarize the different measures and outcomes of the studies, in order to identify promising assessment tools and inform future research.

Sign in / Sign up

Export Citation Format

Share Document