NSF Award
2418602
One of the best ways to help students learn is to have them experience realistic simulations of the situations they will confront in practice. Simulation learning is particularly important in medical settings where students can practice skills without risking patient safety. However, one of the consistent challenges in simulation learning is to ensure that students can effectively review and learn from experiences that may be overwhelming in the moment. In this project, a multidisciplinary research team will implement technologies that record rich, detailed information about the events that occur during nursing simulations. This information will be used to support reflection-based learning by allowing students and instructors to review and elaborate upon key events during simulations. Developing artificial intelligence (AI)-assisted reflection tools will also make strides toward increasing the availability and reach of complex simulation training.<br/><br/>In this project, the research team will develop procedures and technologies that support simulation training in the domain of nursing. The approach combines recent visual cognition research on event understanding (e.g., integrating action identification and goal recognition with basic attentional and memory processes), learning sciences research on self-regulation, and technical developments in the processing of multi-modal learning data. The team will use a multimodal data analysis pipeline to collect and integrate learning analytics (including eye gaze, video, movement data, and computer action logs) to develop AI-based learning supports that can help assess the quality of learning actions and reflections and guide students to effective reflection. These goals will be embodied in a novel system for reflection on mixed-reality simulation learning. The initial version of the system will use a multimodal data pipeline and an AI engine to support two learning modules. The Debrief module will help students and instructors mark key events and focus on discussing them in a debriefing session immediately after they have participated in a learning activity. The Reflect module will engage students to comprehensively review simulations some days after they occur by segmenting their experience into discrete events and identifying the specific actions and goals associated with the events. These segmentations will be based on video and gaze replays that will allow students to observe what they attended to during their simulations. Each module will use a data dashboard to foster student and instructor reflection in support of self-regulation. The team will develop and conduct initial effectiveness studies of the system in in supporting conceptual understanding, metacognitive judgement accuracy, and subsequent simulation performance.<br/><br/>This project is funded by the Research on Innovative Technologies for Enhanced Learning (RITEL) program that supports early-stage exploratory research in emerging technologies for teaching and learning.<br/><br/>This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
