Unsupervised Machine Learning for Identifying Challenging Behavior Profiles to Explore Cluster-Based Treatment Efficacy in Children With Autism Spectrum Disorder: Retrospective Data Analysis Study
BackgroundChallenging behaviors are prevalent among individuals with autism spectrum disorder; however, research exploring the impact of challenging behaviors on treatment response is lacking. ObjectiveThe purpose of this study was to identify types of autism spectrum disorder based on e...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2021-06-01
|
| Series: | JMIR Medical Informatics |
| Online Access: | https://medinform.jmir.org/2021/6/e27793 |
| _version_ | 1818906010137395200 |
|---|---|
| author | Gardner-Hoag, Julie Novack, Marlena Parlett-Pelleriti, Chelsea Stevens, Elizabeth Dixon, Dennis Linstead, Erik |
| author_facet | Gardner-Hoag, Julie Novack, Marlena Parlett-Pelleriti, Chelsea Stevens, Elizabeth Dixon, Dennis Linstead, Erik |
| author_sort | Gardner-Hoag, Julie |
| collection | DOAJ |
| description | BackgroundChallenging behaviors are prevalent among individuals with autism spectrum disorder; however, research exploring the impact of challenging behaviors on treatment response is lacking.
ObjectiveThe purpose of this study was to identify types of autism spectrum disorder based on engagement in different challenging behaviors and evaluate differences in treatment response between groups.
MethodsRetrospective data on challenging behaviors and treatment progress for 854 children with autism spectrum disorder were analyzed. Participants were clustered based on 8 observed challenging behaviors using k means, and multiple linear regression was performed to test interactions between skill mastery and treatment hours, cluster assignment, and gender.
ResultsSeven 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 low levels of stereotypy was found to have significantly higher levels of skill mastery than clusters characterized by self-injurious behavior and aggression (P<.003).
ConclusionsThese findings have implications on the treatment of individuals with autism spectrum disorder. Self-injurious behavior and aggression were prevalent among participants with the worst treatment response, thus interventions targeting these challenging behaviors may be worth prioritizing. Furthermore, the use of unsupervised machine learning models to identify types of autism spectrum disorder shows promise. |
| first_indexed | 2024-12-19T21:32:25Z |
| format | Article |
| id | doaj.art-8ee70a0bbf0844ff9bb7d51d00d0bbe3 |
| institution | Directory Open Access Journal |
| issn | 2291-9694 |
| language | English |
| last_indexed | 2024-12-19T21:32:25Z |
| publishDate | 2021-06-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | JMIR Medical Informatics |
| spelling | doaj.art-8ee70a0bbf0844ff9bb7d51d00d0bbe32022-12-21T20:04:53ZengJMIR PublicationsJMIR Medical Informatics2291-96942021-06-0196e2779310.2196/27793Unsupervised Machine Learning for Identifying Challenging Behavior Profiles to Explore Cluster-Based Treatment Efficacy in Children With Autism Spectrum Disorder: Retrospective Data Analysis StudyGardner-Hoag, JulieNovack, MarlenaParlett-Pelleriti, ChelseaStevens, ElizabethDixon, DennisLinstead, ErikBackgroundChallenging behaviors are prevalent among individuals with autism spectrum disorder; however, research exploring the impact of challenging behaviors on treatment response is lacking. ObjectiveThe purpose of this study was to identify types of autism spectrum disorder based on engagement in different challenging behaviors and evaluate differences in treatment response between groups. MethodsRetrospective data on challenging behaviors and treatment progress for 854 children with autism spectrum disorder were analyzed. Participants were clustered based on 8 observed challenging behaviors using k means, and multiple linear regression was performed to test interactions between skill mastery and treatment hours, cluster assignment, and gender. ResultsSeven 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 low levels of stereotypy was found to have significantly higher levels of skill mastery than clusters characterized by self-injurious behavior and aggression (P<.003). ConclusionsThese findings have implications on the treatment of individuals with autism spectrum disorder. Self-injurious behavior and aggression were prevalent among participants with the worst treatment response, thus interventions targeting these challenging behaviors may be worth prioritizing. Furthermore, the use of unsupervised machine learning models to identify types of autism spectrum disorder shows promise.https://medinform.jmir.org/2021/6/e27793 |
| spellingShingle | Gardner-Hoag, Julie Novack, Marlena Parlett-Pelleriti, Chelsea Stevens, Elizabeth Dixon, Dennis Linstead, Erik Unsupervised Machine Learning for Identifying Challenging Behavior Profiles to Explore Cluster-Based Treatment Efficacy in Children With Autism Spectrum Disorder: Retrospective Data Analysis Study JMIR Medical Informatics |
| title | Unsupervised Machine Learning for Identifying Challenging Behavior Profiles to Explore Cluster-Based Treatment Efficacy in Children With Autism Spectrum Disorder: Retrospective Data Analysis Study |
| title_full | Unsupervised Machine Learning for Identifying Challenging Behavior Profiles to Explore Cluster-Based Treatment Efficacy in Children With Autism Spectrum Disorder: Retrospective Data Analysis Study |
| title_fullStr | Unsupervised Machine Learning for Identifying Challenging Behavior Profiles to Explore Cluster-Based Treatment Efficacy in Children With Autism Spectrum Disorder: Retrospective Data Analysis Study |
| title_full_unstemmed | Unsupervised Machine Learning for Identifying Challenging Behavior Profiles to Explore Cluster-Based Treatment Efficacy in Children With Autism Spectrum Disorder: Retrospective Data Analysis Study |
| title_short | Unsupervised Machine Learning for Identifying Challenging Behavior Profiles to Explore Cluster-Based Treatment Efficacy in Children With Autism Spectrum Disorder: Retrospective Data Analysis Study |
| title_sort | unsupervised machine learning for identifying challenging behavior profiles to explore cluster based treatment efficacy in children with autism spectrum disorder retrospective data analysis study |
| url | https://medinform.jmir.org/2021/6/e27793 |
| work_keys_str_mv | AT gardnerhoagjulie unsupervisedmachinelearningforidentifyingchallengingbehaviorprofilestoexploreclusterbasedtreatmentefficacyinchildrenwithautismspectrumdisorderretrospectivedataanalysisstudy AT novackmarlena unsupervisedmachinelearningforidentifyingchallengingbehaviorprofilestoexploreclusterbasedtreatmentefficacyinchildrenwithautismspectrumdisorderretrospectivedataanalysisstudy AT parlettpelleritichelsea unsupervisedmachinelearningforidentifyingchallengingbehaviorprofilestoexploreclusterbasedtreatmentefficacyinchildrenwithautismspectrumdisorderretrospectivedataanalysisstudy AT stevenselizabeth unsupervisedmachinelearningforidentifyingchallengingbehaviorprofilestoexploreclusterbasedtreatmentefficacyinchildrenwithautismspectrumdisorderretrospectivedataanalysisstudy AT dixondennis unsupervisedmachinelearningforidentifyingchallengingbehaviorprofilestoexploreclusterbasedtreatmentefficacyinchildrenwithautismspectrumdisorderretrospectivedataanalysisstudy AT linsteaderik unsupervisedmachinelearningforidentifyingchallengingbehaviorprofilestoexploreclusterbasedtreatmentefficacyinchildrenwithautismspectrumdisorderretrospectivedataanalysisstudy |