Despite the growing research on users’ perceptions of health AI, adolescents’ perspectives remain underexplored. This study explores adolescents’ perceived benefits and risks of health AI technologies in clinical and personal health settings. Employing Design Fiction, we conducted interviews with 16 adolescents (aged 13-17) using four fictional design scenarios that represent current and future health AI technologies as probes. Our findings revealed that with a positive yet cautious attitude, adolescents envision unique benefits and risks specific to their age group. While health AI technologies were seen as valuable learning resources, they also raised concerns about confidentiality with their parents. Additionally, we identified several factors, such as severity of health conditions and previous experience with AI, influencing their perceptions of trust and privacy in health AI. We explore how these insights can inform the future design of health AI technologies to support learning, engagement, and trust as adolescents navigate their healthcare journey.
Soundscapes are widely used for relaxation, but their potential for personalized, navigable experiences remains under-explored. To address this, we developed Sonora, an AI tool that enables real-time generation of synthetic, spatialized soundscapes, allowing users to navigate immersive auditory environments and customize soundscapes using voice commands. Sonora's architecture integrates audio diffusion models and LLMs within Unity. A between-subjects study with 32 participants investigated its effects on anxiety and user experience, compared to a control condition involving passive listening to a soundscape. Participants who interacted with Sonora reported higher entertainment than the control group. A positive correlation was found between state anxiety and user requests for Sonora, suggesting anxious users engaged more. Participants with moderate to high trait anxiety experienced significant reductions in state anxiety across both conditions, with no significant difference in cognitive load. Our findings highlight Sonora's potential to promote relaxation, emphasizing the value of personalized experiences for mental health.
Expressing stressful experiences in words is proven to improve mental and physical health, but individuals often disengage with writing interventions as they struggle to organize their thoughts and emotions. Reflective prompts have been used to provide direction, and large language models (LLMs) have demonstrated the potential to provide tailored guidance. However, current systems often limit users' flexibility to direct their reflections. We thus present ExploreSelf, an LLM-driven application designed to empower users to control their reflective journey, providing adaptive support through dynamically generated questions. Through an exploratory study with 19 participants, we examine how participants explore and reflect on personal challenges using ExploreSelf. Our findings demonstrate that participants valued the flexible navigation of adaptive guidance to control their reflective journey, leading to deeper engagement and insight. Building on our findings, we discuss the implications of designing LLM-driven tools that facilitate user-driven and effective reflection of personal challenges.
Advancements in artificial intelligence-powered search engines have enhanced the efficiency of online health information searches by generating direct answers to queries using top-ranked featured snippets (FS). However, such functionalities may contribute to health anxiety, particularly when the displayed results are distressing. This study investigated the effect of algorithmic transparency (AT) explanations (absence vs. presence) on mitigating FS-triggered health anxiety. The results of an online experiment (N = 206) yielded two key findings: First, participants exposed to AT explanations detailing the selection process of FS experienced reduced trust in the search engine and distressing results, which subsequently alleviated health anxiety. Second, the moderating effect of pre-existing cyberchondria on the relationship between AT explanations and trust was observed, but only within a limited threshold. Overall, the findings empirically validate AT explanations as an effective approach to mitigate FS-induced health anxiety. Theoretical and practical implications are discussed.
Parenting brings emotional and physical challenges, from balancing work, childcare, and finances to coping with exhaustion and limited personal time. Yet, one in three parents never seek support. AI systems potentially offer stigma-free, accessible, and affordable solutions. Yet, user adoption often fails due to issues with explainability and reliability. To see if these issues could be solved using a co-design approach, we developed and tested NurtureBot, a wellbeing support assistant for new parents. 32 parents co-designed the system through Asynchronous Remote Communities method, identifying the key challenge as achieving a "successful chat." As part of co-design, parents role-played as NurtureBot, rewriting its dialogues to improve user understanding, control, and outcomes. The refined prototype, featuring an Interaction Layer, was evaluated by by 32 initial and 46 new parents, showing improved user experience and usability, with final CUQ score of 91.3/100, demonstrating successful interaction patterns. Our process revealed useful interaction design lessons for effective AI parenting support.
Healthcare simulations help learners develop teamwork and clinical skills in a risk-free setting, promoting reflection on real-world practices through structured debriefs. However, despite video's potential, it is hard to use, leaving a gap in providing concise, data-driven summaries for supporting effective debriefing.
Addressing this, we present TeamVision, an AI-powered multimodal learning analytics (MMLA) system that captures voice presence, automated transcriptions, body rotation, and positioning data, offering educators a dashboard to guide debriefs immediately after simulations.
We conducted an in-the-wild study with 56 teams (221 students) and recorded debriefs led by six teachers using TeamVision. Follow-up interviews with 15 students and five teachers explored perceptions of its usefulness, accuracy, and trustworthiness. This paper examines: i) how TeamVision was used in debriefing, ii) what educators found valuable/challenging, and iii) perceptions of its effectiveness. Results suggest TeamVision enables flexible debriefing and highlights the challenges and implications of using AI-powered systems in healthcare simulation.