Comparing AI Role-Play and Peer Role-Play for Informed Consent Training in Endoscopy: A Randomized Control Trial

NCT07069504 | Recruiting

• 1 other identifier: GAS-25-013
• Study Type: interventional
• Target: 40
• Locations: 1 country
• Sites: 1

Brief Summary

The goal of this randomized controlled trial is to find out whether AI-based role play is effective in teaching healthcare trainees how to obtain informed consent from patients for endoscopic procedures. The main question is:

• How does generative AI-based role play compare to traditional peer role play in training healthcare trainees to deliver informed consent for endoscopic procedures? Researchers will compare AI-based role play with peer role play to see which method is more effective for teaching this skill. What participants will do:
• Attend a lecture on how to obtain informed consent.
• Take part in simulation-based training using either peer role play or AI-based role play.
• Participate in a simulated clinical encounter to assess their ability to obtain informed consent.

Conditions

Informed Consent Process

Keywords

artificial intelligence; virtual patient; simulation-based training; simulation training; education; informed consent; role play

Outcome Measures

Primary Outcomes (2)

• Informed consent checklist

  20-item checklist outlining 19 key steps of the informed consent process, rated on a 3-point scale (yes (2), partial (2), no (0)) and a 10-point global rating scale. The maximum total possible score is 28 on the checklist and 10 on the global rating scale (38 overall), with higher scores representing better performance. Trainee performance during the SP post-test, conducted immediately after training (Day 1), will be evaluated using this scale.

  Day 1 (immediately post-training)

• Communication Skills

  Communication Skills Global Rating Form published by Hodges B, McIlroy JH. Analytic global OSCE ratings are sensitive to level of training. Med Educ 2003; 37: 1012-6. The scale rates overall communication, empathy, coherence, verbal and non-verbal communcation on a 1-5 point scale. The maximum score is 25, with higher scores representing better performance. Trainee performance during the SP post-test, conducted immediately after training (Day 1), will be evaluated using this scale.

  Day 1 (immediately post-training)

Secondary Outcomes (1)

• Self-efficacy

  Baseline and Day 1

Other Outcomes (2)

• Perceptions of the AI platform (AI role play group only)

  Day 1

• AI System Usability (AI role play group only)

  Day 1

Study Arms (2)

AI Role Play

EXPERIMENTAL

Participants will interact with a generative AI-driven patient simulation designed to mimic a realistic consent discussion for an endoscopic procedure. The AI will respond dynamically to trainee input, prompting key elements of the consent process. After each case, the generative AI platform will provide the trainee with individualized feedback. Training will last 30 minutes. The same patient cases will be used in both groups.

Other: AI-based role play

Peer Role Play

ACTIVE COMPARATOR

Participants will be paired with another trainee (i.e., peer) in this group to conduct role play exercises, alternating between the roles of physician and patient, using standardized prompts and guidelines. After each case, the trainee portraying the patient will be asked to provide feedback to the individual portraying the participant. Training will last 30 minutes. The same patient cases will be used in both groups.

Other: Peer role play

Interventions

AI-based role play OTHER

Participants will role play informed consent scenarios with a generative AI-driven patient simulation designed to mimic a realistic consent discussion for an endoscopic procedure.

AI Role Play

Peer role play OTHER

Participants will role play informed consent discussions with a peer (i.e., another participant randomized to this group)

Peer Role Play

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• \) physician trainee enrolled at the University of Toronto.

You may not qualify if:

• \) have previously obtained informed consent for an endoscopic procedure 25 or more times in either real clinical or simulated settings.

Sponsors & Collaborators

• The Hospital for Sick Children: lead
• University of Toronto: collaborator
• Scarborough General Hospital: collaborator

Study Sites (1)

Scarborough Health Network, University of Toronto

Toronto, Ontario, M5G 0A4, Canada

RECRUITING

Related Publications (1)

• Hodges B, McIlroy JH. Analytic global OSCE ratings are sensitive to level of training. Med Educ. 2003 Nov;37(11):1012-6. doi: 10.1046/j.1365-2923.2003.01674.x.

  PMID: 14629415 BACKGROUND

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: SINGLE
• Who Masked: OUTCOMES ASSESSOR
• Purpose: OTHER
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Clinician Scientist

Study Record Dates

• First Submitted: June 30, 2025
• First Posted: July 16, 2025
• Study Start: July 2, 2025
• Primary Completion: September 1, 2025
• Study Completion (Estimated): December 31, 2026
• Last Updated: July 16, 2025

Record last verified: 2025-07

Locations

CA (1)