Use of AI (GPT-4)-generated multiple-choice questions for the examination of surgical subspecialty residents
Bibliographic record
Abstract
INTRODUCTION: Multiple-choice questions (MCQs) are essential in medical education and widely used by licensing bodies. They are traditionally created with intensive human effort to ensure validity. Recent advances in artificial intelligence (AI), particularly large language models (LLMs), offer the potential to streamline this process. This study aimed to develop and test a GPT-4 model with customized instructions for generating MCQs to assess urology residents. METHODS: A GPT-4 model was embedded using guidelines from medical licensing bodies and reference materials specific to urology. This model was tasked with generating MCQs designed to mimic the format and content of the 2023 urology examination outlined by the Royal College of Physicians and Surgeons of Canada (RCPSC). Following generation, a selection of MCQs underwent expert review for validity and suitability. RESULTS: From an initial set of 123 generated MCQs, 60 were chosen for inclusion in an exam administered to 15 urology residents at the University of Toronto. The exam results demonstrated a general increasing performance with level of training cohorts, suggesting the MCQs' ability to effectively discriminate knowledge levels among residents. The majority (33/60) of the questions had discriminatory value that appeared acceptable (discriminatory index 0.2-0.4) or excellent (discriminatory index >0.4). CONCLUSIONS: This study highlights AI-driven models like GPT-4 as efficient tools to aid with MCQ generation in medical education assessments. By automating MCQ creation while maintaining quality standards, AI can expedite processes. Future research should focus on refining AI applications in education to optimize assessments and enhance medical training and certification outcomes.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.022 | 0.107 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.009 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".