AI vs Human Exam Assessment and Development (AHEAD Trial)
NCT07481162 · Status: COMPLETED · Phase: NA · Type: INTERVENTIONAL · Enrollment: 258
Last updated 2026-03-18
Summary
The Artificial Intelligence (AI) vs Human Exam Assessment and Development (AHEAD) Trial is a participant-blinded randomized controlled trial conducted among first-year medical students at the University of British Columbia. The study evaluates whether multiple-choice examination questions generated using large language models (LLMs) perform comparably to traditionally human-written questions in medical education.
Participants were randomized to complete one of two versions of a formative mock final examination consisting of 112 case-based single-best-answer multiple-choice questions (MCQs) aligned with the same course learning objectives. One exam version contained AI-generated questions produced using a structured LLM workflow with independent AI verification, while the other contained questions authored by senior medical students using conventional methods.
The study evaluates exam feasibility, psychometric reliability, validity, student acceptability, and educational impact. Outcomes include exam performance, item discrimination indices, distractor efficiency, student perceptions of exam quality and difficulty, and changes in perceived preparedness for the upcoming summative examination.
Conditions
- Medical Education Assessment
Interventions
- OTHER
-
AI-generated MCQ examination
A formative mock examination composed of 112 case-based multiple-choice questions generated using large language models aligned with course learning objectives.
- OTHER
-
Human-generated MCQ examination
A formative mock examination composed of 112 case-based multiple-choice questions written by senior medical students using conventional item-writing methods aligned with the same course learning objectives.
Sponsors & Collaborators
-
University of British Columbia
lead OTHER
Principal Investigators
-
Anita Palepu, MD, MPH, FRCPC · University of British Columbia
Study Design
- Allocation
- RANDOMIZED
- Purpose
- OTHER
- Masking
- SINGLE
- Model
- PARALLEL
Eligibility
- Min Age
- 18 Years
- Sex
- ALL
- Healthy Volunteers
- Yes
Timeline & Regulatory
- Start
- 2024-12-08
- Primary Completion
- 2024-12-09
- Completion
- 2024-12-09
Countries
- Canada
Study Locations
More Related Trials
-
Evaluation of AI-Generated Clinical Advice by Physicians
NCT06980467 ·Status: NOT_YET_RECRUITING ·Phase: NA
-
Randomised Controlled Trial of Artificial Intelligence-assisted Health Education
NCT07305337 ·Status: RECRUITING ·Phase: NA
-
AI-generated Feedback in Social Robotic Virtual Patients
NCT07277829 ·Status: COMPLETED ·Phase: NA
-
An AI Educational Agent for Medical Machine Learning Courses
NCT07449182 ·Status: RECRUITING ·Phase: NA
-
Mitigating Automation Bias in Physician-LLM Diagnostic Reasoning Using Behavioral Nudges
NCT07328815 ·Status: RECRUITING ·Phase: NA
-
AI to Create Accessible & Reliable Patient Education Materials
NCT06997107 ·Status: ACTIVE_NOT_RECRUITING ·Phase: NA
-
Simulated Patient and AI-based Roleplay for History-taking
NCT06766383 ·Status: COMPLETED ·Phase: NA
-
Comparing Artificial Intelligence and Physicians: A Vignette-Based Study in Pediatric Clinical Decision-Making
NCT07179861 ·Status: COMPLETED
-
LLM-Assisted vs Manual Writing for Clinical Documentation: Effects on Time and Quality
NCT07187050 ·Status: COMPLETED ·Phase: NA
-
Learning Diagnostic Reasoning Through AI
NCT06754826 ·Status: COMPLETED ·Phase: NA
-
Multimodal Radiology Report to Improve Patient-centered Radiology
NCT07159438 ·Status: NOT_YET_RECRUITING ·Phase: NA
-
Multi-Disciplinary Treatment on the Anthropomorphism of Large Language Models
NCT06627985 ·Status: NOT_YET_RECRUITING
-
Artificial Intelligence Powered Mental Health Support Tool For Physicians In Training
NCT07087119 ·Status: NOT_YET_RECRUITING ·Phase: NA
-
Evaluating AI-Generated Plain Language Summaries on Patient Comprehension of Ophthalmology Notes Among English-Speaking Patients
NCT06859216 ·Status: RECRUITING ·Phase: NA
-
The Impact of Large Language Models on Diagnostic Reasoning Among LLM-Trained Medical Doctors
NCT06774612 ·Status: COMPLETED ·Phase: NA
-
Project 3 Example: Human-AI Collaboration Tester (HAICT) Exp. 7
NCT05272189 ·Status: COMPLETED ·Phase: NA
-
Artificial Intelligence Versus Human-controlled Doctor in Virtual Reality Simulation for Sepsis Team Training
NCT05953441 ·Status: COMPLETED ·Phase: NA
-
The Diagnostic and Triage Capacity of Laypeople-large Language Model Collaboration in China
NCT07250516 ·Status: COMPLETED ·Phase: NA
-
Physician Response Evaluation With Contextual Insights vs. Standard Engines - Artificial Intelligence RAG vs LLM Clinical Decision Support
NCT07037940 ·Status: COMPLETED ·Phase: NA
-
Impact of GPT Use on Essay Writing Performance and Cognitive Abilities
NCT06511102 ·Status: COMPLETED ·Phase: NA
-
Study on the Medical Education Capability of the EyeTeacher Artificial Intelligence Platform
NCT06759012 ·Status: NOT_YET_RECRUITING ·Phase: NA
-
Automation Bias in Physician-LLM Diagnostic Reasoning
NCT06963957 ·Status: COMPLETED ·Phase: NA
-
Improving the Accuracy of Artificial Intelligence Triage in Primary Care
NCT07237919 ·Status: RECRUITING ·Phase: NA
-
Large Language Models to Aid Gynecological Oncology Treatment
NCT06865534 ·Status: RECRUITING ·Phase: NA
-
Attitudes and Perceptions of Corresponding Authors From Top International Medical Journals Regarding the Use of Artificial Intelligence in the Scientific Process
NCT07326501 ·Status: ENROLLING_BY_INVITATION