Developing high-quality problem-based learning (PBL) cases remains a significant challenge in medical education. It is resource-intensive and competes with faculty responsibilities in teaching, clinical care, research, and administration. As a result, many institutions struggle to generate sufficient cases to sustain active learning. The emergence of artificial intelligence (AI) and large language models (LLMs) offers a potential solution. We introduced the PBL Case Builder, a customised ChatGPT application designed to guide educators through structured case creation. The builder enforces four input parameters: target audience, curriculum context, core topic, and desired complexity, before generating content, ensuring contextualisation, and pedagogical alignment. Cases are produced in a consistent format, including progressive triggers, mapped learning objectives, and tutor prompts, which educators can then refine. This shifts their role from author to reviewer, reducing workload while enhancing efficiency and consistency. This innovative solution demonstrates that AI-assisted case building can streamline development, promote adaptability, and improve transparency in pedagogical design. Future work should evaluate the educational impact of AI-generated versus human-generated (traditional) cases, explore student and faculty perceptions, and create peer-reviewed repositories to scale this innovation globally.
Abouzeid et al. (Fri,) studied this question.