The Dawn of AI in Medical Education
In this webinar, we will be discussing the use of large language models (LLMs) to automate medical student OSCE note grading.
Learning Objectives
- Describe the time and cost implications of traditional OSCE note grading and how LLMs can streamline the process.
- Compare the grading accuracy of an LLM-based system with traditional human grading methods by analyzing performance data from real-world OSCE note evaluations.
- Outline the key components of an LLM-powered OSCE grading pipeline, including student note input, rubric integration, and automated scoring output, and discuss potential limitations and areas for improvement.
- Identify opportunities to integrate LLMs into their own educational and clinical workflows by examining the OSCE grading project as a model for innovation in emergency medicine education.
Moderators/Panelists