No abstract

Objective Monitoring technology may assist in managing self-injurious behavior (SIB), a pervasive concern in autism spectrum disorder (ASD). Affiliated stakeholder perspectives should be considered to design effective and accepted SIB monitoring methods. We examined caregiver experiences to generate design guidance for SIB monitoring technology. Materials and Methods Twenty-three educators and 16 parents of individuals with ASD and SIB completed interviews or focus groups to discuss needs related to monitoring SIB and associated technology use. Results Qualitative content analysis of participant responses revealed 7 main themes associated with SIB and technology: triggers, emotional responses, SIB characteristics, management approaches, caregiver impact, child/student impact, and sensory/technology preferences. Discussion The derived themes indicated areas of emphasis for design at the intersection of monitoring and SIB. Systems design at this intersection should consider the range of manifestations of and management approaches for SIB. It should also attend to interactions among children with SIB, their caregivers, and the technology. Design should prioritize the transferability of physical technology and behavioral data as well as the safety, durability, and sensory implications of technology. Conclusions The collected stakeholder perspectives provide preliminary groundwork for an SIB monitoring system responsive to needs as articulated by caregivers. Technology design based on this groundwork should follow an iterative process that meaningfully engages caregivers and individuals with SIB in naturalistic settings.

As the informatics community grows in its ability to address health disparities, there is an opportunity to expand our impact by focusing on the disability community as a health disparity population. Although informaticians have primarily catered design efforts to one disability at a time, digital health technologies can be enhanced by approaching disability from a more holistic framework, simultaneously accounting for multiple forms of disability and the ways disability intersects with other forms of identity. The urgency of moving toward this more holistic approach is grounded in ethical, legal, and design-related rationales. Shaped by our research and advocacy with the disability community, we offer a set of guidelines for effective engagement. We argue that such engagement is critical to creating digital health technologies which more fully meet the needs of all disabled individuals.

Self-injurious behavior (SIB) is among the most dangerous concerns in autism spectrum disorder (ASD), often requiring detailed and tedious management methods. Sensor-based behavioral monitoring could address the limitations of these methods, though the complex problem of classifying variable behavior should be addressed first. We aimed to address this need by developing a group-level model accounting for individual variability and potential nonlinear trends in SIB, as a secondary analysis of existing data. Ten participants with ASD and SIB engaged in free play while wearing accelerometers. Movement data were collected from > 200 episodes and 18 different types of SIB. Frequency domain and linear movement variability measures of acceleration signals were extracted to capture differences in behaviors, and metrics of nonlinear movement variability were used to quantify the complexity of SIB. The multi-level logistic regression model, comprising of 12 principal components, explained > 65% of the variance, and classified SIB with > 75% accuracy. Our findings imply that frequency-domain and movement variability metrics can effectively predict SIB. Our modeling approach yielded superior accuracy than commonly used classifiers (~ 75 vs. ~ 64% accuracy) and had superior performance compared to prior reports (~ 75 vs. ~ 69% accuracy) This work provides an approach to generating an accurate and interpretable group-level model for SIB identification, and further supports the feasibility of developing a real-time SIB monitoring system.

Self-injurious behavior (SIB), such as head banging or self-hitting, is considered one of the most dangerous characteristics of autism spectrum disorder (ASD) (Mahatmya, Zobel, & Valdovinos, 2008). Clinicians traditionally rely on structured observation, which can be time-consuming and invasive. Recent technological developments in motion tracking may decrease these burdens. For example, accelerometers in smart watches can gather movement information, which could be automatically classified to detect and predict events associated with SIB using machine learning algorithms. While such systems have clear potential to objectively, accurately, and efficiently monitor and predict SIB, this potential will not be fully realized unless devices are adopted and integrated into clinics and homes. The lack of user input when designing home-based technological interventions for ASD likely contributes to the fact that technology has been rarely, if at all, implemented. In ongoing work, we included stakeholders before design is complete, and embraced a user-centered perspective by evaluating user needs and translating them into system requirements (Karsh, Weinger, Abbott, & Wears, 2010). To this end, we evaluated stakeholder perspectives regarding monitoring technology for SIB in children with ASD. Sixteen parents (age 31-62, M = 45.1 ± 8.1 years) with children (age 6-26, M = 14.1 ± 6.7 years) with ASD and SIB were engaged in individual or group interviews to assess needs and challenges associated with SIB. Interviews with broad and open-ended questions were conducted to allow for response variability that may decrease in larger groups. Questions spanned several aspects of SIB and its management, as well as current and projected technology use. Parents discussed perceived benefits and challenges of different technologies, such as smart watches and video cameras, as related to tracking movement associated with SIB. Data from the first six interviews influenced a second version of interview questions to reflect participant responses. Qualitative content analysis was used to organize the responses into seven main themes surrounding experiences of SIB and technology: (1) triggers, (2) emotional responses, (3) SIB characteristics, (4) management strategies, (5) caregiver impact, (6) child impact, and (7) preferred sensory stimuli (Graneheim & Lundman, 2004). Data were cross-coded with two underlying themes of (8) uncertainty and (9) state of experience. Critical to preserving the original interview content, categories and themes were derived directly from the data rather than from predetermined topics (Hsieh & Shannon, 2005). The derived themes were related to the needs and challenges of SIB, and they were then interpreted to determine design considerations for monitoring methods. Parents described changes in SIB, and they often associated these changes with either child-specific variables (e.g., maturity, medical concerns) or environment-specific variables (e.g., time, new triggers). The variety of triggers and behaviors and the high likelihood of these parameters changing require adaptive monitoring technology capable of learning new behavioral patterns. Tracking systems should be customizable to accommodate the strong presence of variability (Cabibihan, Javed, Aldosari, Frazier, & Elbashir, 2017) and to support patient and contextual variability, which is an opportunity for human factors research through the patient work lens (Valdez, Holden, Novak, & Veinot, 2014). Participants also expressed a shared deficit in resources, referring to both a lack of available technology and information. Monitoring system design should therefore employ affordable, accessible technology while empowering caregivers to access interpretable data. Whether devices are embedded in the environment or attached to a child, parents prefer mitigating required input because of their already high levels of stress, discussed within the caregiver impact theme. Parents mentioned that their typical schedules afforded limited time for data collection, which indicates the designed system should require a limited number of quick interactions. Automated and manual options (Valdez et al., 2014) may address both the need to reduce workload, a factor affecting patient work (Holden, Valdez, Schubert, Thompson, & Hundt, 2017), and the need to increase control when monitoring SIB. The findings from this study and the resulting design implications provide a foundation for future technology development. It is expected that early-stage user involvement will encourage acceptance of this monitoring technology (Panchanathan & McDaniel, 2015; Veryzer & Borja de Mozota, 2005). Users will continue to participate throughout the design process. Careful consideration of the user may lead to accepted and adopted health technology with both efficiency and accuracy in detecting SIB. Results from this study highlight the importance of parent consideration in the health technology space for children with disabilities, particularly when parents participate in management methods. Further, this research contributes to an underexplored domain of qualitative human factors applied to disability and design. Future work could employ human factors approaches, such as contextual inquiries (Marcu et al., 2013) reflecting the patient work framework, to evaluate child and parent needs within the home setting. This research was supported by a National Science Foundation Graduate Research Fellowship (to the first author) and a 4-VA Collaborative Research Grant (to RSV). However, neither agency had any involvement in data analysis or interpretation.