AI role-play versus peer role-play to teach informed consent for endoscopy
COMPARING AI ROLE-PLAY AND PEER ROLE-PLAY FOR INFORMED CONSENT TRAINING IN ENDOSCOPY: A RANDOMIZED CONTROL TRIAL
This project tests whether AI-based virtual patient role-play or peer role-play better teaches University of Toronto physician trainees to obtain informed consent for endoscopic procedures.
Quick facts
| Phase | Not applicable |
|---|---|
| Study type | Interventional |
| Enrollment | 40 (estimated) |
| Ages | 18 Years and up |
| Sex | All |
| Sponsor | The Hospital for Sick Children Academic / other |
| Locations | 1 site (Toronto, Ontario) |
| Trial ID | NCT07069504 on ClinicalTrials.gov |
What this trial studies
Participants receive a lecture on obtaining informed consent then are randomized to practice with either an AI-driven virtual patient simulation or traditional peer role-play. After training, each trainee completes a standardized simulated clinical encounter that is scored for clarity, empathy, and completeness of the consent discussion. Outcomes include objective ratings of communication and informed consent performance plus trainee self-reported confidence. The single-center randomized design compares educational effectiveness and practical scalability of AI simulations versus peer-based practice.
Who should consider this trial
Good fit: Ideal participants are physician trainees enrolled at the University of Toronto who have performed fewer than 25 informed consent encounters for endoscopy.
Not a fit: Individuals who are not University of Toronto physician trainees or who already have extensive prior experience obtaining endoscopy consent (25 or more prior encounters) are unlikely to benefit from this training comparison.
Why it matters
Potential benefit: If successful, AI-based role-play could expand access to realistic, repeatable consent training and improve trainees' ability to explain risks, benefits, and alternatives for endoscopic procedures.
How similar studies have performed: Preliminary and pilot work suggests AI-driven virtual patients are perceived as realistic and educationally valuable, but direct randomized evidence comparing them to peer role-play is limited.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: 1\) physician trainee enrolled at the University of Toronto. Exclusion Criteria: 1\) have previously obtained informed consent for an endoscopic procedure 25 or more times in either real clinical or simulated settings.
Where this trial is running
Toronto, Ontario
- Scarborough Health Network, University of Toronto — Toronto, Ontario, Canada (Recruiting)
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.