Search for: All records

This study introduces AutoCLC, an AI-powered system designed to assess and provide feedback on closed-loop communication (CLC) in professional learning environments. CLC, where a sender’s Call-Out statement is acknowledged by the receiver’s Check-Back statement, is a critical safety protocol in high-reliability domains, including emergency medicine resuscitation teams. Existing methods for evaluating CLC lack quantifiable metrics and depend heavily on human observation. AutoCLC addresses these limitations by leveraging natural language processing and large language models to analyze audio recordings from Advanced Cardiovascular Life Support (ACLS) simulation training. The system identifies CLC instances, measures their frequency and rate per minute, and categorizes communications as effective, incomplete, or missed. Technical evaluations demonstrate AutoCLC achieves 78.9% precision for identifying Call-Outs and 74.3% for Check-Backs, with a performance gap of only 5% compared to human annotations. A user study involving 11 cardiac arrest instructors across three training sites supported the need for automated CLC assessment. Instructors found AutoCLC reports valuable for quantifying CLC frequency and quality, as well as for providing actionable, example-based feedback. Participants rated AutoCLC highly, with a System Usability Scale score of 76.4%, reflecting above-average usability. This work represents a significant step toward developing scalable, data-driven feedback systems that enhance individual skills and team performance in high-reliability settings. 

Simulation-based learning has become a cornerstone of healthcare education, fostering essential skills like communication, teamwork or decision-making in safe, controlled environments. However, participants’ reflection on simulations often rely on subjective recollections, limiting their effectiveness in promoting learning. This symposium explores how multimodal analytics and AI can enhance simulation-based education by automating teamwork analysis data, providing structured feedback, and supporting reflective practices. The papers examine real-time analytics for closed-loop communication in cardiac arrest simulations, multimodal data use to refine feedback in ICU nursing simulations, generative AI-powered chatbots facilitating nursing students' interpretation of multimodal learning analytics dashboards, and culturally sensitive, AI-based scenarios for Breaking Bad News in an Indian context. Collectively, these contributions highlight the transformative potential of using data and AI-enhanced solutions, emphasizing personalization, cultural sensitivity, and human-centered design, and invite dialogue on the pedagogical, technological and ethical implications of introducing data-based practices and AI-based tools in medical education. 

Applying customized epidermal electronics closely onto the human skin offers the potential for biometric sensing and unique, always-available on-skin interactions. However, iterating designs of an on-skin interface from schematics to physical circuit wiring can be time-consuming, even with tiny modifications; it is also challenging to preserve skin wearability after repeated alteration. We present SkinLink, a reconfigurable on-skin fabrication approach that allows users to intuitively explore and experiment with the circuitry adjustment on the body. We demonstrate SkinLink with a customized on-skin prototyping toolkit comprising tiny distributed circuit modules and a variety of streamlined trace modules that adapt to diverse body surfaces. To evaluate SkinLink's performance, we conducted a 14-participant usability study to compare and contrast the workflows with a benchmark on-skin construction toolkit. Four case studies targeting a film makeup artist, two beauty makeup artists, and a wearable computing designer further demonstrate different application scenarios and usages. 

The emergence of on-skin interfaces has created an opportunity for seamless, always-available on-body interactions. However, developing a new fabrication process for on-skin interfaces can be time-consuming, challenging to incorporate new features, and not available for quick form-factor preview through prototyping. We introduce SkinKit, the first construction toolkit for on-skin interfaces, which enables fast, low-fidelity prototyping with a slim form factor directly applicable to the skin. SkinKit comprises modules consisting of skin-conformable base substrates and reusable Flexible Printed Circuits Board (FPCB) blocks. They are easy to attach and remove under tangible plug-and-play construction but still offer robust conductive connections in a slim form. Further, SkinKit aims to lower the barrier to entry in building on-skin interfaces without demanding technical expertise. It leverages a variety of preprogrammed modules connected in unique sequences to achieve various function customizations. We describe our iterative design and development process of SkinKit, comparing materials, connection mechanisms, and modules reflecting on its capability. We report results from single- and multi- session workshops with 34 maker participants spanning STEM and design backgrounds. Our findings reveal how diverse maker populations engage in on-skin interface design, what types of applications they choose to build, and what challenges they faced.