Twelve tips to leverage AI for efficient and effective medical question generation: A guide for educators using Chat...

Area of Science:

• Medical Education
• Artificial Intelligence

Background:

• Medical education requires high-quality assessment questions, a process that is time-consuming and expertise-dependent.
• Large language models (LLMs) offer a potential innovative solution for generating these questions.

Purpose of the Study:

• To explore the utility of ChatGPT in generating diverse, high-quality medical assessment questions, specifically multiple-choice questions (MCQs).
• To enhance educator productivity and facilitate self-directed student learning through AI-assisted question generation.

Main Methods:

• Utilized 12 strategies to guide ChatGPT in generating assessment questions.
• Ensured alignment with Bloom's taxonomy and core knowledge domains.
• Promoted best practices in assessment design.

Main Results:

• Demonstrated ChatGPT's capability to generate assessment questions aligned with educational objectives.
• Showcased the potential for AI to augment, not replace, human expertise in medical assessment.

Conclusions:

• LLM tools like ChatGPT can assist in creating high-standard medical assessment questions.
• Subject matter experts remain crucial for ensuring the ultimate quality and accuracy of AI-generated content in medical education.