Related Experiment Video
Updated: May 14, 2026

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
Published on: September 20, 2018
Large language models for generating medical examinations: systematic review.
Yaara Artsi1, Vera Sorin2,3,4, Eli Konen2,3
1Azrieli Faculty of Medicine, Bar-Ilan University, Ha'Hadas St. 1, Rishon Le Zion, Zefat, 7550598, Israel. yaara.artsi77@gmail.com.
Large language models (LLMs) show potential for generating medical multiple-choice questions (MCQs). However, current AI-generated MCQs require significant revision for exam validity, suggesting LLMs are best used as supplementary tools.
Area of Science:
- Medical Education Technology
- Artificial Intelligence in Healthcare
- Assessment and Evaluation
Background:
- Medical educators face challenges in creating high-quality multiple-choice questions (MCQs) for exams.
- This systematic review examines the utility of large language models (LLMs) in generating medical MCQs.
Conclusions:
- LLMs show promise for assisting in the creation of medical MCQs.
- Current LLM-generated MCQs necessitate careful review and modification for exam suitability.
- Further research is required to establish conclusive evidence; LLMs are currently best viewed as supplementary tools.
Related Concept Videos
Detection of Gross Error: The Q Test
Higher Mental Functions of the Brain: Language
Language formation and comprehension take place in the dominant hemisphere. The dominant hemisphere is responsible for understanding the meaning of spoken, written, or sign language, as well as the ability to communicate. For most people, the left hemisphere is the dominant one. The right hemisphere, then, gives tone and emotional context to the...
Components of Language
Introduction to Language of Pathophysiology l
Introduction to Language of Pathophysiology ll

