Title : From burden to breakthrough: Generative AI–enhanced simulation for interprofessional nursing education
Abstract:
Background: Interprofessional education (IPE) is essential for preparing nurses to deliver safe, coordinated, team-based care, but many programs lack the time, personnel, and resources to build and implement high-fidelity simulation at scale. Generative artificial intelligence (AI) offers a novel solution by rapidly producing realistic, customizable electronic health records (EHRs) and patient narratives that can be reused, adapted, and expanded with minimal additional workload for faculty.
Purpose: This project compared simulation efficacy, faculty time involvement, and student satisfaction with traditional format using faculty-created scenarios and medical records with ones generated using AI.
Methods: Faculty used generative AI to create dynamic EHRs, orders, and patient biographies for a series of orthopedic and complex medical–surgical cases, then embedded these into a standardized patient–based IPE simulation that positioned senior nursing students as primary nurses and standardized patients, and occupational therapy students as therapists and observers. AI-generated charts were iteratively refined to incorporate lines, drains, isolation precautions, functional limitations, and evolving clinical data, allowing the same core framework to support multiple case variants and levels of difficulty. Competency development was evaluated using pre/post interprofessional teamwork measures and observation of chart navigation, data synthesis, and documentation behaviors. This was compared to previous iterations that utilized paper charts, rudimentary google sheet EHRs, and faculty-created material for patients’ medical records using the same pre/post measures.
Results: AI-enabled content creation reduced scenario and chart-development time from days to hours per case, allowing faculty to increase the number and complexity of simulations without adding staff or sacrificing fidelity. The expanded scenario set supported more nuanced assessment of interprofessional communication, role negotiation, shared care planning with students demonstrating increased competency and self-rated confidence across all domains. Additionally, it enabled faculty to introduce layers of complexity and assess student competency in delegation and documentation.
Conclusions: Integrating generative AI into the interprofessional simulation dramatically reduced faculty preparation time, supported rapid scaling and diversification of scenarios, and enabled richer assessment of interprofessional and documentation competencies for nursing and occupational therapy students. Generative AI functioned as a force multiplier for nursing education, transforming a labor-intensive IPE simulation into a scalable, adaptable learning ecosystem that simultaneously enriched realism and broadened competency evaluation. This approach illustrates how thoughtfully governed AI tools can help schools of nursing expand high-impact simulation experiences while protecting faculty bandwidth and aligning with contemporary competency frameworks.
