IGE: Track 2: AI-Driven Virtual Teaching Assistant (ViTA) in Medical Biophysics Graduate Education

This National Science Foundation Innovations in Graduate Education (IGE) award to Clemson University will develop and evaluate an artificial intelligence (AI)-driven Virtual Teaching Assistant (ViTA) designed to support interdisciplinary graduate education in medical biophysics. Graduate students in this field face unique challenges due to the complexity of integrating concepts from physics, biology, chemistry, and engineering. These challenges are compounded by the lack of structured human teaching assistant support in many advanced courses. ViTA is an innovative solution that uses expert-validated generative AI to deliver personalized, context aware academic support within existing graduate curricula. By offering real-time feedback and interactive engagement, ViTA aims to improve learning outcomes, support a wide variety of student populations and contribute to institutional efforts to improve scalable graduate education. ViTA integrates fine-tuned generative AI models with retrieval-augmented generation pipelines to provide expert-validated, domain-specific feedback embedded directly into a learning management system. The project will use a mixed-methods research design to evaluate ViTA’s impact across cognitive, behavioral, and affective learning domains. Assessment strategies include validated pre/post tests, surveys of self-efficacy and cognitive load, reflective journals, and AI interaction analytics. Control and experimental cohorts will be drawn from students at the same academic level, including those taking medical biophysics courses as electives. Findings from this project will generate new knowledge on AI-supported interdisciplinary education, inform ethical pedagogical use of AI in graduate instruction, and provide a scalable framework that can be adapted across STEM disciplines. All tools, datasets, and protocols will be openly shared through public repositories and institutional partners to maximize replicability and long-term impact. 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.