RESUMO
Early detection and intervention for relapse is important in the treatment of schizophrenia spectrum disorders. Researchers have developed AI models to predict relapse from patient-contributed data like social media. However, these models face challenges, including misalignment with practice and ethical issues related to transparency, accountability, and potential harm. Furthermore, how patients who have recovered from schizophrenia view these AI models has been underexplored. To address this gap, we first conducted semi-structured interviews with 28 patients and reflexive thematic analysis, which revealed a disconnect between AI predictions and patient experience, and the importance of the social aspect of relapse detection. In response, we developed a prototype that used patients' Facebook data to predict relapse. Feedback from seven patients highlighted the potential for AI to foster collaboration between patients and their support systems, and to encourage self-reflection. Our work provides insights into human-AI interaction and suggests ways to empower people with schizophrenia.
RESUMO
BACKGROUND: Individuals with autism often experience heightened anxiety in workplace environments because of challenges in communication and sensory overload. As these experiences can result in negative self-image, promoting their self-efficacy in the workplace is crucial. Virtual reality (VR) systems have emerged as promising tools for enhancing the self-efficacy of individuals with autism in navigating social scenarios, aiding in the identification of anxiety-inducing situations, and preparing for real-world interactions. However, there is limited research exploring the potential of VR to enhance self-efficacy by facilitating an understanding of emotional and physiological states during social skills practice. OBJECTIVE: This study aims to develop and evaluate a VR system that enabled users to experience simulated work-related social scenarios and reflect on their behavioral and physiological data through data visualizations. We intended to investigate how these data, combined with the simulations, can support individuals with autism in building their self-efficacy in social skills. METHODS: We developed WorkplaceVR, a comprehensive VR system designed for engagement in simulated work-related social scenarios, supplemented with data-driven reflections of users' behavioral and physiological responses. A within-subject deployment study was subsequently conducted with 14 young adults with autism to examine WorkplaceVR's feasibility. A mixed methods approach was used, compassing pre- and postsystem use assessments of participants' self-efficacy perceptions. RESULTS: The study results revealed WorkplaceVR's effectiveness in enhancing social skills and self-efficacy among individuals with autism. First, participants exhibited a statistically significant increase in perceived self-efficacy following their engagement with the VR system (P=.02). Second, thematic analysis of the interview data confirmed that the VR system and reflections on the data fostered increased self-awareness among participants about social situations that trigger their anxiety, as well as the behaviors they exhibit during anxious moments. This increased self-awareness prompted the participants to recollect their related experiences in the real world and articulate anxiety management strategies. Furthermore, the insights uncovered motivated participants to engage in self-advocacy, as they wanted to share the insights with others. CONCLUSIONS: This study highlights the potential of VR simulations enriched with physiological and behavioral sensing as a valuable tool for augmenting self-efficacy in workplace social interactions for individuals with autism. Data reflection facilitated by physiological sensors helped participants with autism become more self-aware of their emotions and behaviors, advocate for their characteristics, and develop positive self-beliefs.
