FindTrial
Sign In

AI Versus Human-Generated Multiple-Choice Questions for Medical Education: A Cohort Study in a High-Stakes Examination

Assessing the Non-Inferiority of AI-Generated Multiple-Choice Questions in Medical Education: A Comparative Study of ChatGPT-4 and Human-Authored Items

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2400093883
Enrollment
Unknown
Registered
2024-12-13
Start date
2024-08-20
Completion date
Unknown
Last updated
2024-12-16

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Medical Education

Interventions

AI MCQ:None
Human MCQ:None

Sponsors

The Chinese University of Hong Kong
Lead Sponsor

Eligibility

Sex/Gender
All
Age
20 Years to 34 Years

Inclusion criteria

Inclusion criteria: All Emergency Medical doctors who applied for the Primary Examination on Emergency Medicine (PEEM, organised by HK College of Emergency Medicine) examination.

Exclusion criteria

Exclusion criteria: 1. Incomplete Participation 2. Trainees who withdraw consent

Design outcomes

Primary

MeasureTime frame
MCQ performance;—

Secondary

MeasureTime frame
MCQ production time;MCQ quality ;—

Countries

China

Contacts

Public ContactAlex KK Law

Accident and Emergency Medicine Academic Unit, The Chinese University of Hong Kong

alexlaw@cuhk.edu.hk+852 6301 6191

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Feb 4, 2026