scholarly journals Identifying Challenging Behavior Profiles and Exploring their Impact on Treatment Efficacy in Autism Spectrum Disorder using Unsupervised Machine Learning (Preprint)

2021 ◽  
Author(s):  
Julie Gardner-Hoag ◽  
Marlena Novack ◽  
Chelsea Parlett-Pelleriti ◽  
Elizabeth Stevens ◽  
Dennis Dixon ◽  
...  
Keyword(s):  
Machine Learning ◽  
Autism Spectrum Disorder ◽  
Treatment Response ◽  
Challenging Behavior ◽  
Challenging Behaviors ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Unsupervised Machine Learning ◽  
Skill Mastery ◽  
The Impact

BACKGROUND Challenging behaviors are prevalent among individuals with autism spectrum disorder (ASD); however, research exploring the impact of challenging behaviors on treatment response is lacking. OBJECTIVE The purpose of the current study was to identify subtypes of ASD based on engagement in different challenging behaviors and evaluate differences in treatment response between subgroups. METHODS Retrospective data on challenging behaviors and treatment progress for 854 children with ASD were analyzed. First, participants were clustered based on eight observed challenging behaviors using k-means. Next, a multiple linear regression analysis was performed to find significant interactions between skill mastery and treatment hours, cluster assignment, and gender. RESULTS Seven diverse clusters were identified, which demonstrated a single dominant challenging behavior. For some clusters, significant differences in treatment response were found. Specifically, a cluster characterized by stereotypy was found to have significantly higher levels of skill mastery than clusters characterized by self-injurious behavior and aggression. CONCLUSIONS These findings have implications on the treatment of individuals with ASD. First, self-injurious behavior and aggression were prevalent among participants with the poorest treatment response, thus interventions targeting these challenging behaviors may be worth prioritizing. Furthermore, the use of unsupervised machine learning models to identify subtypes of ASD shows promise.

scholarly journals Identification and analysis of behavioral phenotypes in autism spectrum disorder via unsupervised machine learning

2019 ◽  
Vol 129 ◽  
pp. 29-36 ◽  
Author(s):  
Elizabeth Stevens ◽  
Dennis R. Dixon ◽  
Marlena N. Novack ◽  
Doreen Granpeesheh ◽  
Tristram Smith ◽  
...  
Keyword(s):  
Machine Learning ◽  
Autism Spectrum Disorder ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Unsupervised Machine Learning ◽  
Behavioral Phenotypes

Technology-Aided Interventions to Reduce Challenging Behaviors for Individuals With Autism Spectrum Disorder

2022 ◽  
pp. 108-125
Author(s):  
Maria Zygopoulou
Keyword(s):  
Autism Spectrum Disorder ◽  
Social Relations ◽  
Challenging Behavior ◽  
Negative Impact ◽  
Challenging Behaviors ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Functional Communication ◽  
Self Monitoring

Individuals with autism spectrum disorder (ASD) display a variety of challenging behaviors, such as tantrums, aggression, stereotypy, and disruption. Challenging behaviors can have a serious negative impact on the development of social relations, in the learning process, and education. To this aim, there is a need for appropriate interventions in order to improve the quality of life of individuals with ASD. This chapter aims to provide data with regard to different types of interventions and technological tools used for the reduction of challenging behaviors of students with ASD. Functional communication training with the use of speech-generating devices, video self-modeling, self-monitoring with the use of technological devices, and social stories presented in electronic form reflect types of interventions used for challenging behavior reduction. Research data indicate that technology-aided interventions are generally effective in reducing challenging behaviors of students with ASD.

Managing Challenging Behavior in Adolescents with Autism Spectrum Disorder

2017 ◽  
pp. 242-272
Author(s):  
Maya Matheis ◽  
Jasper A. Estabillo ◽  
Johnny L. Matson
Keyword(s):  
Autism Spectrum Disorder ◽  
Challenging Behavior ◽  
Behavioral Treatment ◽  
Behavioral Assessment ◽  
Challenging Behaviors ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Behavior Interventions ◽  
Treatment Methods ◽  
Assessment And Treatment

The term “challenging behavior” describes a wide range of behaviors that may be harmful to an individual and that pose significant risks related to health, emotional distress, or exclusion from community settings. Challenging behaviors occur at high rates among individuals with autism spectrum disorder (ASD). Some forms of challenging behavior include: aggression, self-injurious behavior (SIB), stereotypical behavior, pica, and vomiting/rumination. Functional behavioral assessment (FBA) is the process of gathering and interpreting data related to the underlying function of a behavior. Interventions that target the function of a behavior are more effective and efficient. Behavioral treatment methods for challenging behavior are based on operant principles of reinforcement and punishment. Several common treatment methods are described. Suggestions for the assessment and treatment of challenging behaviors are outlined.

Designing Autism Spectrum Disorder Interventions for Community Implementation

2020 ◽  
pp. 407-421
Author(s):  
Robin L. Gabriels ◽  
Julia Barnes
Keyword(s):  
Mental Health ◽  
Autism Spectrum Disorder ◽  
Implementation Science ◽  
Child Outcomes ◽  
Challenging Behaviors ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Evidence Based ◽  
Children With Asd ◽  
The Impact

There are well-documented gaps between evidence-based interventions (EBIs) developed and tested in controlled research settings and those delivered in routine, community-based care. The field of implementation science has developed in response to identified gaps to study methods to promote the uptake and sustainment of EBIs in community care. Community mental health (MH) services play an important role in caring for individuals with autism spectrum disorder (ASD) across the lifespan who have co-occurring psychiatric conditions. This chapter summarizes over a decade of community-engaged research aimed to (a) characterize MH services for children with ASD, including the training needs of therapists and clinical needs of children with ASD receiving care; (b) develop the AIM HI (An Individualized Mental Health Intervention for ASD) intervention, a package of well-established, evidence-based behavioral strategies designed to reduce challenging behaviors in children served in MH service settings; (c) test the impact of training therapists to deliver AIM HI on child outcomes; (d) identify potential influences on implementation; and (e) test the impact of different implementation strategies to enhance therapist delivery of AIM HI. The chapter includes directions for future research including applying the AIM HI development model to older individuals with ASD and other community service systems and integrating implementation science approaches earlier in the pipeline of research-to-practice translation.

Pharmacogenomic Studies in Intellectual Disabilities and Autism Spectrum Disorder: A Systematic Review: Études Pharmacogénomiques en Déficiences Intellectuelles et Trouble du Spectre de L’autisme: Une Revue Systématique

2020 ◽  
pp. 070674372097195
Author(s):  
Kazunari Yoshida ◽  
Emiko Koyama ◽  
Clement C. Zai ◽  
Joseph H. Beitchman ◽  
James L. Kennedy ◽  
...  
Keyword(s):  
Systematic Review ◽  
Autism Spectrum Disorder ◽  
Adverse Effects ◽  
Candidate Gene ◽  
Treatment Outcomes ◽  
Treatment Response ◽  
Age Groups ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
The Impact

Background: Individuals with intellectual disability (ID) and autism spectrum disorder (ASD) often receive psychotropic medications such as antipsychotics and antidepressants to treat aberrant behaviors and mood symptoms, frequently resulting in polypharmacy and drug-related adverse effects. Pharmacogenomic (PGx) studies with ASD and/or ID (ASD/ID) have been scarce despite the promise of optimizing treatment outcomes. We reviewed the literature on PGx studies with antipsychotics and antidepressants (e.g., treatment response and adverse effects) in ASD/ID. Methods: We performed a systematic review using MEDLINE, Embase, and PsycINFO, including peer-reviewed original articles in English referring to PGx in the treatment of ASD/ID in any age groups (e.g., treatment response and adverse effects). Results: A total of 28 PGx studies using mostly candidate gene approaches were identified across age groups. Notably, only 3 studies included adults with ASD/ID while the other 25 studies focused specifically on children/adolescents with ASD/ID. Twelve studies primarily investigated treatment response, of which 5 and 6 studies included patients treated with antipsychotics and antidepressants, respectively. Most interesting results for response were reported for 2 sets of candidate gene studies, namely: (1) The DRD3 Ser9Gly (rs6280) polymorphism was examined in patients treated with risperidone in 3 studies, 2 of which reported an association with risperidone treatment response and (2) the SLC6A4 5-HTTLPR polymorphism and treatment response to antidepressants which was investigated in 4 studies, 3 of which reported significant associations. In regard to side effects, 9 of 15 studies focused on hyperprolactinemia in patients treated with risperidone. Among them, 7 and 5 studies examined the impact of CYP2D6 and DRD2 Taq1A polymorphisms, respectively, yielding mostly negative study findings. Conclusions: There is limited data available on PGx in individuals with ASD/ID and in particular in adults. Given the potential for PGx testing in improving treatment outcomes, additional PGx studies for psychotropic treatment in ASD/ID across age groups are warranted.

scholarly journals Supporting autism spectrum disorder screening and intervention with machine learning and wearables: a systematic literature review

2021 ◽  
Author(s):  
Rita Francese ◽  
Xiaomin Yang
Keyword(s):  
Machine Learning ◽  
Autism Spectrum Disorder ◽  
Challenging Behaviors ◽  
Research Work ◽  
Economic Loss ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Machine Learning Techniques ◽  
Learning Approaches ◽  
Noninvasive Sensors

AbstractThe number of autism spectrum disorder individuals is dramatically increasing. For them, it is difficult to get an early diagnosis or to intervene for preventing challenging behaviors, which may be the cause of social isolation and economic loss for all their family. This SLR aims at understanding and summarizing the current research work on this topic and analyze the limitations and open challenges to address future work. We consider papers published between 2015 and the beginning of 2021. The initial selection included about 2140 papers. 11 of them respected our selection criteria. The papers have been analyzed by mainly considering: (1) the kind of action taken on the autistic individual, (2) the considered wearables, (3) the machine learning approaches, and (4) the evaluation strategies. Results revealed that the topic is very relevant, but there are many limitations in the considered studies, such as reduced number of participants, absence of datasets and experimentation in real contexts, need for considering privacy issues, and the adoption of appropriate validation approaches. The issues highlighted in this analysis may be useful for improving machine learning techniques and highlighting areas of interest in which experimenting with the use of different noninvasive sensors.

Sign in / Sign up

Export Citation Format

Share Document