Artificial intelligence (AI) is rapidly advancing the way medical education approaches both simulation and assessment. In simulation, generative AI enables the creation of dynamic, branching scenarios that closely mirror clinical complexity, streamlining case design while maintaining fidelity to competency frameworks. Large language models also serve as adaptive “virtual patients,” providing safe, scalable opportunities for learners to practice interviews, decision-making, and communication with immediate, automated feedback. In evaluation and assessment, AI is being applied to analyze learner performance across written work, OSCEs, and simulated encounters—offering rubric-aligned scoring, narrative feedback, and predictive analytics that approach the reliability of expert raters. Together, these innovations promise not only more efficient training but also more consistent and personalized evaluation, while raising important considerations around validation, fairness, and ethical use. This session will highlight current applications and emerging opportunities for AI in both simulation and learner assessment within medical education.
Learning objectives:
- By the end of this session, participants will be able to describe at least two applications of AI in enhancing simulation design and learner assessment in medical education.
- By the conclusion of the lecture, participants will be able to identify at least one practical strategy for integrating AI into simulation or evaluation workflows that reduces faculty time or improves assessment reliability compared with baseline methods.
