Pushing the boundaries of generative AI: multiple-choice question generation and assessment performance within medical education

View Full Paper

Ask AI

Bookmark

Share

Key Points

This research aims to assess the effectiveness of generative AI models, Gemini and Copilot, in generating assessment questions for medical education.
Generated 335 MCQs from two virtual patient cases using standardized prompts.
Evaluated the generated MCQs based on alignment with performance criteria and educational standards.
Used expert assessments to determine the quality of the MCQs and the tools' performance.
Analyzed performance using reliability and agreement statistics.
Gemini's MCQs showed superior consistency with expert consensus in Miller classifications.
Copilot's MCQs excelled in Bloom's alignment with expert judgments.
Both AI tools aligned well with learning objectives and key identifications.
Experts found MCQs easier than AI assessments suggested, revealing discrepancies in perceived difficulty.

We only have this paper's title and publication details.

Evaluates how generative AI tools perform in creating MCQs for medical education, indicating strengths and weaknesses.

No takes yet. Share an insight, caveat, or question.

Özdemir et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

Share