Forecasting High-Risk Behavioral and Medical Events in Children with Autism through Analysis of Digital Behavioral Records.

Individuals with Autism Spectrum Disorder may display interfering behaviors that limit their inclusion in educational and community settings, negatively impacting their quality of life. These behaviors may also signal potential medical conditions or indicate upcoming high-risk behaviors. This study explores behavior patterns that precede high-risk, challenging behaviors or seizures the following day. We analyzed an existing dataset of behavior and seizure data from 331 children with profound ASD over nine years. We developed a deep learning-based algorithm designed to predict the likelihood of aggression, elopement, and self-injurious behavior (SIB) as three high-risk behavioral events, as well as seizure episodes as a high-risk medical event occurring the next day. The proposed model attained accuracies of 78.4%, 80.68%, 85.43%, and 69.95% for predicting the next-day occurrence of aggression, SIB, elopement, and seizure episodes, respectively. The results were proven significant for more than 95% of the population for all high-risk event predictions using permutation-based statistical tests. Our findings emphasize the potential of leveraging historical behavior data for the early detection of high-risk behavioral and medical events, paving the way for behavioral interventions and improved support in both social and educational environments.

Off-body Sleep Analysis for Predicting Adverse Behavior in Individuals with Autism Spectrum Disorder.

Poor sleep quality in Autism Spectrum Disorder (ASD) individuals is linked to severe daytime behaviors. This study explores the relationship between a prior night's sleep structure and its predictive power for next-day behavior in ASD individuals. The motion was extracted using a low-cost near-infrared camera in a privacy-preserving way. Over two years, we recorded overnight data from 14 individuals, spanning over 2,000 nights, and tracked challenging daytime behaviors, including aggression, self-injury, and disruption. We developed an ensemble machine learning algorithm to predict next-day behavior in the morning and the afternoon. Our findings indicate that sleep quality is a more reliable predictor of morning behavior than afternoon behavior the next day. The proposed model attained an accuracy of 74% and a F1 score of 0.74 in target-sensitive tasks and 67% accuracy and 0.69 F1 score in target-insensitive tasks. For 7 of the 14, better-than-chance balanced accuracy was obtained (p-value<0.05), with 3 showing significant trends (p-value<0.1). These results suggest off-body, privacy-preserving sleep monitoring as a viable method for predicting next-day adverse behavior in ASD individuals, with the potential for behavioral intervention and enhanced care in social and learning settings.

Associated Factors of Self-injury Among Adolescents with Autism Spectrum Disorder in a Community and Residential Treatment Setting.

Self-injurious behavior (SIB) occurs in up to 50% of individuals with autism. As one of the most serious conditions in individuals with developmental disabilities, SIB affects the individual and his or her family in multiple contexts. A systematic analysis of factors most commonly associated with SIB could inform the development of individualized intervention strategies. The current study examined factors related to SIB in an analysis of client records of 145 children with autism in a comprehensive care center. Predictor variables included age, gender, the Adaptive Behavior Composite, sensory processing, aggression, stereotypies, irritability, adaptive skills, and medical conditions. Age, irritability, and the Adaptive Behavior Composite were found to significantly predict SIB.

Examining the Association Between Electrodermal Activity and Problem Behavior in Severe Autism Spectrum Disorder: A Feasibility Study.

Background: Many individuals with autism spectrum disorder (ASD) engage in problem behavior, presenting significant challenges for those providing care and services for this population. Psychophysiological measures of arousal, such as electrodermal activity (EDA), may provide an early indication of subsequent problem behavior. However, variability in EDA patterns associated with behaviors may limit this predictive ability. Methods: EDA data was sampled from eight individuals with severe ASD in a naturalistic setting, while participating in educational programming in a school setting at a residential facility for severely affected individuals with developmental disabilities, to examine variability in EDA patterns. Results: An anticipatory rise in EDA only occurred 60% of the time prior to the problem behavior. Additionally, EDA after a problem behavior returned to median baseline levels only 45% of the time. Conclusions: Heterogeneity of EDA responses in those with the most severe forms of ASD will be an important consideration in future studies utilizing psychophysiological tools such as EDA to anticipate problem behavior, including the need for monitoring of return to baseline after problem behaviors. Incorporation of this consideration may lead to greater reliability of these approaches to help anticipate and manage problem behaviors.

Increasing independence in autism spectrum disorders: a review of three focused interventions.

The features of autism that inhibit the independent demonstration of skills, as well as three effective interventions for increasing independence, are explored in this review article. Independent performance may prove difficult for individuals with autism spectrum disorders (ASD) due to the core deficits of the disability, as well as executive function deficits that impact initiation and generalization. These difficulties, coupled with intervention strategies that encourage over-reliance on adult support, contribute to poor long term outcomes for adults with ASD in employment, housing, and relationship development. Self-monitoring, video modeling, and individual work systems each emphasize a shift in stimulus control from continuous adult management to an alternative stimulus and have proven successful in addressing executive function deficits and increasing independence.

Social interaction and repetitive motor behaviors.

Students with autism have difficulty initiating social interactions and may exhibit repetitive motor behavior (e.g., body rocking, hand flapping). Increasing social interaction by teaching new skills may lead to reductions in problem behavior, such as motor stereotypies. Additionally, self-monitoring strategies can increase the maintenance of skills. A multiple baseline design was used to examine whether multi-component social skills intervention (including peer training, social initiation instruction, and self-monitoring) led to a decrease in repetitive motor behavior. Social initiations for all participants increased when taught to initiate, and social interactions continued when self-monitoring was introduced. Additionally, participants' repetitive motor behavior was reduced. Changes in social behavior and in repetitive motor behavior maintained more than one month after the intervention ended.