{
  "id": 9842,
  "url": "https://doi.org/10.1186/s12909-025-06796-6",
  "title": "AI versus human-generated multiple-choice questions for medical education: a cohort study in a high-stakes examination",
  "summary": "BACKGROUND: The creation of high-quality multiple-choice questions (MCQs) is essential for medical education assessments but is resource-intensive and time-consuming when done by human experts. Large language models (LLMs) like ChatGPT-4o offer a promising alternative, but their efficacy remains unclear, particularly in high-stakes exams. OBJECTIVE: This study aimed to evaluate the quality and psychometric properties of ChatGPT-4o-generated MCQs compared to human-created MCQs in a high-stakes me",
  "authors": "Alex Kwok-Keung Law, Jerome Lok Tsun So, Chun Tat Lui, Yu Fai Choi, Koon Ho Cheung, Kevin Kei Ching Hung",
  "category": "research",
  "topics": "healthcare,children-education",
  "orgs": "openai",
  "regions": null,
  "published_at": "2025-02-08T00:00:00.000Z",
  "fetched_at": "2026-07-14T16:34:00.826Z",
  "source_slug": "openalex",
  "source_name": "OpenAlex",
  "source_homepage": "https://openalex.org",
  "ethics_ai_record_url": "https://ethics.ai/record/9842",
  "original_url": "https://doi.org/10.1186/s12909-025-06796-6",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}