In-the-Wild Affect Analysis of Children with ASD Using Heart Rate.

Recognizing the affective state of children with autism spectrum disorder (ASD) in real-world settings poses challenges due to the varying head poses, illumination levels, occlusion and a lack of datasets annotated with emotions in in-the-wild scenarios. Understanding the emotional state of children with ASD is crucial for providing personalized interventions and support. Existing methods often rely on controlled lab environments, limiting their applicability to real-world scenarios. Hence, a framework that enables the recognition of affective states in children with ASD in uncontrolled settings is needed. This paper presents a framework for recognizing the affective state of children with ASD in an in-the-wild setting using heart rate (HR) information. More specifically, an algorithm is developed that can classify a participant's emotion as positive, negative, or neutral by analyzing the heart rate signal acquired from a smartwatch. The heart rate data are obtained in real time using a smartwatch application while the child learns to code a robot and interacts with an avatar. The avatar assists the child in developing communication skills and programming the robot. In this paper, we also present a semi-automated annotation technique based on facial expression recognition for the heart rate data. The HR signal is analyzed to extract features that capture the emotional state of the child. Additionally, in this paper, the performance of a raw HR-signal-based emotion classification algorithm is compared with a classification approach based on features extracted from HR signals using discrete wavelet transform (DWT). The experimental results demonstrate that the proposed method achieves comparable performance to state-of-the-art HR-based emotion recognition techniques, despite being conducted in an uncontrolled setting rather than a controlled lab environment. The framework presented in this paper contributes to the real-world affect analysis of children with ASD using HR information. By enabling emotion recognition in uncontrolled settings, this approach has the potential to improve the monitoring and understanding of the emotional well-being of children with ASD in their daily lives.

Improving capacity to identify, assess, and manage adolescents engaging in non-suicidal self-injury using patient avatars.

PURPOSE: We developed and evaluated a training comprising a didactic and virtual practice session with human-guided patient avatars to increase pediatric residents' competence to identify and assess non-suicidal self-injury (NSSI) and suicide risk. METHODS: Thirty pediatric residents at three children's hospitals in Florida participated in the training and completed pre-, one-month post-, and three-months post-training surveys. One-way repeated measures ANOVA with post-hoc comparisons determined changes in confidence, comfort, behavioral intentions, attitudes, knowledge, and behavior over time. Qualitative responses provided feedback on the training, especially the novel practice session with adolescent patient avatars. RESULTS: Three-months post-training residents expressed significantly greater confidence in talking to adolescents who self-injure, applying the SOARS method to assess self-injury, and assessing functions/reasons for self-injury; reported feeling significantly more comfortable asking about self-injury, well-equipped to handle the emotional aspects of self-injury, and comfortable treating adolescents who self-injure; reported greater behavioral intentions to talk to adolescents about self-injury, assess an adolescent's stage of change for stopping self-injury, and provide brief interventions for adolescents who self-injure; and used SOARS to evaluate current NSSI with a greater proportion of adolescent patients. Qualitative feedback expressed positive perceptions, especially related to the virtual-reality role-play session. CONCLUSIONS: Incorporating an interactive, human-guided virtual experience using role-playing and feedback with patient avatars represents a viable option comparable to using typical standardized patients to expand the scalability of NSSI trainings for pediatric residents, especially when they occur virtually.

Mixed Reality for PTSD/TBI Assessment.

Mixed Reality (MR) refers to the blending of virtual content into the real world. Using MR, we create contextually meaningful scenarios in which users carry out tasks encountered in the presence of visual and aural distracters. Visual distracters can include subtle ones - people walking; and more abrupt ones - cartons falling. Aural distracters can include gentle ones - fans whirring; and more aggressive ones - automobiles backfiring. The intensity of these distracters can be dynamically controlled by a therapist or software that takes into account the patient's perceived level of stress. Intensity can also be controlled between experiences. For example, one may increase the stress level in a subsequent session, attempting to improve a person's tolerance. Assessment of progress includes psychophysical metrics (stress indicators) and the performance of tasks (accuracy and adherence to time constraints). By accurately capturing a patient's interaction with the environment in the context of simulation events, we can use MR as a tool for assessment and rehabilitation planning for individuals with stress-related injuries. This paper reports on the MR environment we have developed and its efficacy (realized and potential) for the assessment of post-traumatic stress disorder (PTSD) with or without traumatic brain injury (TBI).