The interview process has been identified as one of the major barriers to employment of autistic individuals, which contributes to the staggering rate of under and unemployment of autistic adults. Decreasing stress during the interview has been shown to improve interview performance. However, in order to effectively provide insights on stress to both interviewees and interviewers, it is necessary to first effectively measure stress. This work explores physiological stress detection through wearable sensing as a means of obtaining quantitative stress measures from young autistic adults undergoing a virtual simulated interview using supervised machine learning techniques. Several supervised learning models were explored and it was found that Elastic Net Regression had the best accuracy with individual models with an accuracy of 84.8% while Support Vector Regression models evaluated with leave-one-out cross validation had a group accuracy of 75.4%. The predictions from the stress model were used with data visualization techniques in order to provide insights on the interview process from both a group and individual viewpoint, showing that stress trends can be found and evaluated using the stress model. This work also addresses a major gap in physiological stress detection literature by presenting a novel dataset of physiological data and ground truth labels for 15 autistic young adults undergoing a simulated interview.

Sleep is vital to many processes involved in the well-being and health of children; however, it is estimated that 80% of children with Rett syndrome suffer from sleep disorders. Caregiver reports and questionnaires, which are the current method of studying sleep, are prone to observer bias and missed information. Polysomnography is considered the gold standard for sleep analysis but is labor and cost-intensive and limits the frequency of data collection for sleep disorder studies. Wearable digital health technologies, such as actigraphy devices, have shown potential and feasibility as a method for sleep analysis in Rett syndrome, but have not been validated against polysomnography. Furthermore, the collected accelerometer data has limitations due to the rigidity, periodic limb movement, and involuntary muscle contractions prevalent in Rett syndrome. Heart rate and electrodermal activity, along with other physiological signals, have been linked to sleep stages and can be utilized with machine learning to provide better resistance to noise and false positives than actigraphy. This research aims to address the gap in Rett syndrome sleep analysis by comparing the performance of a machine learning model utilizing both accelerometer data and physiological data features to the gold-standard polysomnography for sleep analysis in Rett syndrome. Our analytical validation pilot study ([ ] = 7) found that using physiological and accelerometer features, our machine learning models can differentiate between awake, non-rapid eye movement sleep, and rapid eye movement sleep in Rett syndrome children with an accuracy of 85.1% when using an individual model. Additionally, this work demonstrates that it is feasible to use digital health technologies in Rett syndrome, even at a young age, without data loss or interference from repetitive movements that are characteristic of Rett syndrome.

Computer-based job interview training, including virtual reality (VR) simulations, have gained popularity in recent years to support and aid autistic individuals, who face significant challenges and barriers in finding and maintaining employment. Although popular, these training systems often fail to resemble the complexity and dynamism of the employment interview, as the dialogue management for the virtual conversation agent either relies on choosing from a menu of prespecified answers, or dialogue processing is based on keyword extraction from the transcribed speech of the interviewee, which depends on the interview script. We address this limitation through automated dialogue act classification via transfer learning. This allows for recognizing intent from user speech, independent of the domain of the interview. We also redress the lack of training data for a domain general job interview dialogue act classifier by providing an original dataset with responses to interview questions within a virtual job interview platform from 22 autistic participants. Participants’ responses to a customized interview script were transcribed to text and annotated according to a custom 13-class dialogue act scheme. The best classifier was a fine-tuned bidirectional encoder representations from transformers (BERT) model, with an f1-score of 87%.

Background: Apathy is common among older adults residing in long-term care (LTC) and impairs quality of life for both older adults and care providers. Few pharmacological remedies exist, and nonpharmacologic approaches that engage those with apathy require extensive personnel time. Thus, technological approaches have been encouraged, including virtual reality (VR) and socially assistive robots (SAR). Despite a growing interest in their use, input from older adults and staff is often absent in their design. Involving older adults in the development of interactive health technologies is necessary to enhance the functionality, usability, and likelihood of promoting the intended health outcomes. Objective: We aimed to design and evaluate SAR and nonimmersive VR (SAR-VR) activities for pairs of older adults that would encourage human-to-human interaction, an essential activity to mitigate apathy. Methods: We implemented a multistep, user-centered design. A humanoid and dog SAR were used in combination with nonimmersive VR activities for pairs of older adults. An interdisciplinary team of engineers, nurses, and physicians collaborated with older adults and staff to create 4 activity prototypes, 3 with the humanoid robot and 1 with the dog robot. A total of 14 older adults at 2 sites participated in the design and evaluation of the different components of the system throughout all stages. Site 1 participants were instrumental in the development, and Site 2 participants validated the prototype activities. Data were collected at each session via observations, interviews, and a 6-item questionnaire that rated their degree of comfort and confidence in (1) using the wands, (2) interacting with the robot, and (3) interacting with the nonimmersive VR environment using a 5-point Likert response. Additionally, 5 staff from Site 2 were recruited to evaluate the ease of setting up and running the system at 2 different sessions. After each session, the system setup and interface were refined based on their feedback. Results: A total of 4 of 6 older adults (mean age 85, SD 9.3 years; 2 male) at Site 1 completed field testing development, and 8 residents (mean age 80, SD 4.7 years; 2 male) at Site 2 completed field testing validation. Participant comfort and confidence increased significantly over successive iterations of the system across most categories (Site 1: Wilcoxon signed rank test P=.03; Site 2: Wilcoxon signed rank test P<.001). Additionally, 5 LTC staff members successfully set up the system with minimal cueing from the researchers, demonstrating the usability of the system for caregivers. Iterative design changes incorporated hardware, software, and activity domains. Conclusions: These initial results demonstrate that LTC older adults and staff are capable and critical to the development and implementation of SAR-VR activities. Future studies are needed to evaluate the feasibility of implementation and effectiveness in reducing apathy. Trial Registration: ClinicalTrials.gov NCT05178992; https://clinicaltrials.gov/study/NCT05178992