1

Stroke 2025Augmented reality enables visualization of and interaction with both physical and virtual environments. Holograms can allow 3‐dimensional image transmission to distant sites, allowing patients to interact with providers as if in the same space. Our prior publication resulted in high satisfaction/immersion for patients interacting with Holo‐Stroke providers. Our aim here was to determine if providers assessing computed tomographic angiographies (CTAs) for large vessel occlusion would result in reliability and satisfaction.

CHI 2025 Emergency Remote Teaching (ERT) during COVID-19 offered a unique chance to study online higher education at scale, beyond traditional lab settings. Through a review of 22 empirical studies, we analyzed how online classrooms addressed different types of interaction. Our findings highlight the need for future research that centers Learner-Content interaction as a way to balance flexibility with structure—especially as ERT may continue to shape education going forward.

CHI 2025 Trust in autonomous vehicles varies widely among individuals, and this study uses machine learning to identify the key factors influencing young adults’ trust. Surveying over 1,400 participants, the analysis reveals that perceptions of AV risks and benefits, usability attitudes, institutional trust, prior experience, and mental models are the strongest predictors of trust—while psychosocial traits and driving styles play a lesser role. These findings underscore the need to account for individual differences when designing trustworthy AV systems.

CHI 2025 Interdisciplinary engagement across disciplines is often hindered by stylistic and conceptual differences. Drawing on Large Language Models (LLMs), this work explores how metaphor-based support can improve accessibility and engagement. A survey of early-career HCI researchers found that metaphors increased interest in STS texts, particularly for those with limited prior exposure. We propose a dialogic model of metaphor exchange to support shared understanding and critical reflection across disciplines.

CHI 2025 Explanation errors from autonomous vehicles undermine user comfort, trust, and satisfaction—particularly in unfamiliar or non-routine driving contexts. Through a driving simulator study, the work shows that even subtle inaccuracies in how AVs communicate can erode user confidence, emphasizing the need for clear, context-aware explanations to foster reliable human-machine interaction.

AMIA 2024Using ASR and NLP, we developed a pipeline to analyze social signals in audio recordings of 782 primary care visits, achieving 90.1% accuracy and fairness across patient groups. The analysis revealed significant disparities in provider behaviors, with more patient-centered communication observed toward white patients, highlighting the potential of automated tools to uncover biases and promote equitable healthcare.

DIS 2024Cross‑device contouring lets oncologists use mobile touchscreens to cut planning time while preserving accuracy.

CHI 2024 Analyzing patient-provider communication through social signals like dominance, interactivity, engagement, and warmth can help improve care by identifying opportunities for better interactions. We introduce a machine-learning pipeline embedded in ConverSense, a web application that visualizes communication patterns across visits. A user study with clinicians and patients highlights its potential to provide actionable, context-specific feedback for enhancing communication quality and patient outcomes.

CHI 2024 Implicit bias among healthcare providers can negatively impact care quality and patient outcomes, necessitating tools to identify and address these biases. Through design sessions with 24 primary care providers, we found they prefer feedback with transparent metrics, trends across visits, and actionable tips presented in a dashboard. These insights can guide the development of interactive systems to support equitable healthcare, especially for marginalized communities.

CHI 2024Through interviews, workshops, and a global survey, this study uncovered gaps between how contouring is taught and what residents need to learn effectively. While faculty often focus on efficiency, residents seek timely, varied, and cognitively rich feedback. Key challenges include limited support for sharing reasoning and balancing clinical with teaching responsibilities. Sociotechnical solutions are proposed to bridge these gaps, such as using senior learners for peer teaching and capturing cognitive insights through in-situ video feedback.