Related Experiment Video
Updated: Jun 30, 2026

Project-Based Learning Guidelines for Health Sciences Students: An Analysis with Data Mining and Qualitative Techniques
Published on: December 9, 2022
LLM-Generated multiple choice practice quizzes for preclinical medical students.
Troy Camarata1, Lise McCoy2, Robert L Rosenberg3
1Baptist University College of Osteopathic Medicine, Memphis, Tennessee, United States.
Artificial intelligence can create medical exam questions, but expert review is crucial. Large language models show promise for generating practice quizzes when supervised by subject matter experts.
Area of Science:
- Medical Education
- Artificial Intelligence in Education
Background:
- Multiple choice questions (MCQs) are essential for medical education assessment.
- Automated MCQ generation can reduce faculty workload and expand student practice resources.
Purpose of the Study:
- To assess the feasibility of using ChatGPT for generating USMLE/COMLEX-USA-style medical practice questions.
- To evaluate the quality and accuracy of AI-generated medical assessment items.
Main Methods:
- Second-year medical students used ChatGPT-generated renal physiology quizzes.
- Independent experts evaluated question quality against NBME/NBOME guidelines.
Main Results:
- 49% of AI-generated questions had writing flaws; 22% had factual/conceptual errors.
- 91% of questions were deemed suitable as a revision starting point.
Conclusions:
- Large language models (LLMs) are feasible for generating medical education practice questions.
- Expert supervision and training in item writing are essential for effective LLM use in medical assessment.
More Related Videos
Related Concept Videos
Surveys
Methods of Documentation II: POMR
Methods of Documentation III: PIE
Systematic Error: Methodological and Sampling Errors
Sampling errors originate from improper sampling methods or the wrong sample population. These errors can be minimized by refining the sampling strategy. Defective instruments or faulty calibrations are the sources of instrumental...
Preclinical Development: Overview
Self-Report Tests of Personality

