Behavioral Monitoring to Identify Self-Injurious Behavior among Children with Autism Spectrum Disorder
| dc.contributor.author | Garside, Kristine Dianne Cantin | en |
| dc.contributor.committeechair | Nussbaum, Maury A. | en |
| dc.contributor.committeemember | Srinivasan, Divya | en |
| dc.contributor.committeemember | Kong, Zhenyu | en |
| dc.contributor.committeemember | White, Susan Williams | en |
| dc.contributor.committeemember | Kim, Sun Wook | en |
| dc.contributor.department | Industrial and Systems Engineering | en |
| dc.date.accessioned | 2019-03-26T08:00:22Z | en |
| dc.date.available | 2019-03-26T08:00:22Z | en |
| dc.date.issued | 2019-03-25 | en |
| dc.description.abstract | Self-injurious behavior (SIB) is one of the most dangerous behavioral responses among individuals with autism spectrum disorder (ASD), often leading to injury and hospitalization. There is an ongoing need to measure the triggers of SIB to inform management and prevention. These triggers are determined traditionally through clinical observations of the child with SIB, often involving a functional assessment (FA), which is methodologically documenting responses to stimuli (e.g., environmental or social) and recording episodes of SIB. While FA has been a "gold standard" for many years, it is costly, tedious, and often artificial (e.g., in controlled environments). If performed in a naturalistic environment, such as the school or home, caregivers are responsible for tracking behaviors. FA in naturalistic environments relies on caregiver and patient compliance, such as responding to prompts or recalling past events. Recent technological developments paired with classification methods may help decrease the required tracking efforts and support management plans. However, the needs of caregivers and individuals with ASD and SIB should be considered before integrating technology into daily routines, particularly to encourage technology acceptance and adoption. To address this, the perspectives of SIB management and technology were first collected to support future technology design considerations (Chapter 2). Accelerometers were then selected as a specific technology, based on caregiver preferences and reported preferences of individuals with ASD, and were used to collect movement data for classification (Chapter 3). Machine learning algorithms with featureless data were explored, resulting in individual-level models that demonstrated high accuracy (up to 99%) in detecting and classifying SIB. Group-level classifiers could provide more generalizable models for efficient SIB monitoring, though the highly variable nature of both ASD and SIB can preclude accurate detection. A multi-level regression model (MLR) was implemented to consider such individual variability (Chapter 4). Both linear and nonlinear measures of motor variability were assessed as potential predictors in the model. Diverse classification methods were used (as in Chapter 3), and MLR outperformed other group level classifiers (accuracy ~75%). Findings from this research provide groundwork for a future smart SIB monitoring system. There are clear implications for such monitoring methods in prevention and treatment, though additional research is required to expand the developed models. Such models can contribute to the goal of alerting caregivers and children before SIB occurs, and teaching children to perform another behavior when alerted. | en |
| dc.description.abstractgeneral | Autism spectrum disorder (ASD) is a prevalent developmental disorder that adversely affects communication, social skills, and behavioral responses. Roughly half of individuals diagnosed with ASD show self-injurious behavior (SIB), including self-hitting or head banging), which can lead to injury and hospitalization. Clinicians or trained caregivers traditionally observe and record events before/after SIB to determine possible causes (“triggers”) of this behavior. Clinicians can then develop management plans to redirect, replace, or extinguish SIB at the first sign of a known trigger. Tracking SIB in this way, though, requires substantial experience, time, and effort from caregivers. Observations may suffer from subjectivity and inconsistency if tracked across caregivers, or may not generalize to different contexts if SIB is only tracked in the home or school. Recent technological innovations, though, could objectively and continuously monitor SIB to address the described limitations of traditional tracking methods. Yet, “smart” SIB tracking will not be adopted into management plans unless first accepted by potential users. Before a monitoring system is developed, caregiver needs related to SIB, management, and technology should be evaluated. Thus, as an initial step towards developing an accepted SIB monitoring system, caregiver perspectives of SIB management and technology were collected here to support future technology design considerations (Chapter 2). Sensors capable of collecting the acceleration of movement (accelerometers) were then selected as a specific technology, based on the reported preferences of caregivers and individuals with ASD, and were used to capture SIB movements from individuals with ASD (Chapter 3). These movements were automatically classified as “SIB” or “non-SIB” events using machine learning algorithms. When separately applying these methods to each individual, up to 99% accuracy in detecting and classifying SIB was achieved. Classifiers that predict SIB for diverse individuals could provide more generalizable and efficient methods for SIB monitoring. ASD and SIB presentations, however, range across individuals, which impose challenges for SIB detection. A multi-level regression model (MLR) was implemented to consider individual differences, such as those that may occur from diagnosis or behavior (Chapter 4). Model inputs included measures capturing changes of movement over time, and these were found to enhance SIB identification. Diverse classification models were also developed (as in Chapter 3), though MLR outperformed these (yielding accuracy of ~75%). Findings from this research provide groundwork for a smart SIB monitoring system. There are clear implications for monitoring methods in prevention, though additional research is required to expand the developed models. Such models can contribute to the goal of alerting caregivers and children before SIB occurs, and teaching children to perform another behavior when alerted. | en |
| dc.description.degree | Doctor of Philosophy | en |
| dc.format.medium | ETD | en |
| dc.identifier.other | vt_gsexam:19073 | en |
| dc.identifier.uri | http://hdl.handle.net/10919/88533 | en |
| dc.publisher | Virginia Tech | en |
| dc.rights | In Copyright | en |
| dc.rights.uri | http://rightsstatements.org/vocab/InC/1.0/ | en |
| dc.subject | autism spectrum disorder | en |
| dc.subject | self-injurious behavior | en |
| dc.subject | accelerometers | en |
| dc.subject | classification | en |
| dc.subject | Machine learning | en |
| dc.title | Behavioral Monitoring to Identify Self-Injurious Behavior among Children with Autism Spectrum Disorder | en |
| dc.type | Dissertation | en |
| thesis.degree.discipline | Industrial and Systems Engineering | en |
| thesis.degree.grantor | Virginia Polytechnic Institute and State University | en |
| thesis.degree.level | doctoral | en |
| thesis.degree.name | Doctor of Philosophy | en |
Files
Original bundle
1 - 1 of 1