An interventional study of Generative AI simulated patient and Expert demonstration video in Clinical Competence, Communication Skills and Self Efficacy, sponsored by Chang Gung Memorial Hospital. Completed at 1 site in Taiwan. Open to participants aged 18 Years and older, including healthy volunteers. Per ClinicalTrials.gov, last updated 2026-11-02.
Sponsored by Chang Gung Memorial Hospital · Not applicable, Interventional, and Other
The goal of this study is to compare two methods for teaching psychiatric work-history interviewing to third-year occupational therapy students: practice with a generative AI simulated patient and an expert demonstration video. The main questions it aims to answer are:
Students enrolled in a required vocational rehabilitation course were randomly assigned to one of two sequences. In the first teaching week, one sequence practiced interviewing a GPT-4o-based simulated patient (a 35-year-old person with schizophrenia), and the other watched and discussed an expert demonstration interview of the same case. Both groups completed a 9-minute standardized-patient OSCE on the same day. In the following week, the two sequences crossed over to the other method. Interview self-efficacy was measured before teaching, after the first method, and after the second method.
Design: Randomized two-period, two-sequence crossover trial embedded in the required course "Vocational Rehabilitation and Work Capacity Evaluation Practicum" (Department of Occupational Therapy, Chang Gung University). Only the teaching method in two course weeks (Week 6 and Week 7) differed between groups; all other course content and schedule were identical.
Interventions: The two methods used the same case script and were matched for teaching time. (1) Generative AI simulated patient: students conducted one-on-one, repeatable practice interviews with a GPT-4o-based simulated patient portraying a 35-year-old person with schizophrenia; brief automated feedback was provided after the conversation. (2) Expert demonstration video: a clinical expert recorded a demonstration interview of the same case, which students watched followed by instructor-led discussion.
Sequence 1: AI simulated patient in Week 6, expert video in Week 7. Sequence 2: expert video in Week 6, AI simulated patient in Week 7.
Primary outcome: OSCE interview performance immediately after the first-period teaching session (Week 6), before crossover. The OSCE used a standardized patient, a 9-minute interview followed by a written case summary, and a 15-item rubric (4-point scale; domains: establishing a therapeutic relationship, gathering a complete work history, discussing work expectations; total score 60). Examiners were blinded to students' teaching group.
Secondary outcomes: a 10-item interview self-efficacy questionnaire (5-point scale) administered at T1 (before teaching), T2 (after the first method, before crossover) and T3 (after the second method); an anonymous questionnaire comparing the two methods and asking preferred learning sequence, administered after students had experienced both methods; and an end-of-course reflection questionnaire in which students retrospectively rated their confidence at different course stages.
Students could not be blinded to the teaching method. Consent for use of course data in research was obtained separately and did not affect course grades.
719 studies on the registry are indexed under Communication; 159 are open to participants now.
This study's enrollment of 53 is below the median of 144 across 571 interventional studies indexed under Communication.
Browse Communication studies →Chang Gung Memorial Hospital is the lead sponsor of 1,096 studies on the registry; 239 are open to participants now.
Counted across the registry records on this site, refreshed daily.
Go through the criteria one by one — yes, no or not sure — and take the list to your doctor or the study team. Kept in this browser only.
Exclusion Criteria:
* Declined consent for research use of their data (these students still participated in all course activities as usual)
Underlined terms in the criteria open these too. Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.
Before you join, the study team explains what taking part involves — its purpose, what happens, the risks and possible benefits — and answers your questions, so you can decide freely. Consent is usually recorded on a form (the informed consent form, ICF) signed by you or, where the law allows, by someone legally authorised to decide for you.
You can keep asking questions during the study, you are told of new information that matters, and you can choose to leave at any time.
Informed consent
Before you join, the study team explains what taking part involves — its purpose, what happens, the risks and possible benefits — and answers your questions, so you can decide freely. Consent is usually recorded on a form (the informed consent form, ICF) signed by you or, where the law allows, by someone legally authorised to decide for you.
You can keep asking questions during the study, you are told of new information that matters, and you can choose to leave at any time.
Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.
Period 1 (Week 6): practice with the generative AI simulated patient, followed by the OSCE on the same day. Period 2 (Week 7): crossover to the expert demonstration video.
Behavioral: Generative AI simulated patient · Behavioral: Expert demonstration video
Period 1 (Week 6): expert demonstration video with instructor-led discussion, followed by the OSCE on the same day. Period 2 (Week 7): crossover to practice with the generative AI simulated patient.
Behavioral: Generative AI simulated patient · Behavioral: Expert demonstration video
One-on-one, repeatable practice interviews with a GPT-4o-based simulated patient portraying a 35-year-old person with schizophrenia, using the same case script as the expert video and matched for teaching time. Brief automated feedback was provided after the conversation.
A clinical expert's recorded demonstration interview of the same schizophrenia case, viewed by students and followed by instructor-led discussion; matched to the AI simulated patient session for teaching time and case content.
OSCE interview performance score
Psychiatric work-history interview performance with a standardized patient, rated by examiners blinded to the teaching group using a 15-item rubric on a 4-point scale (1 = needs improvement to 4 = excellent) across three domains: establishing a therapeutic relationship, gathering a complete work history, and discussing work expectations. Total score range 15-60; higher scores indicate better performance.
Time frame: Immediately after the Period 1 teaching session (same day, course Week 6), before crossover
Interview self-efficacy
Psychiatric Interview Self-Efficacy Questionnaire (study-specific, 10 items), assessing confidence in conducting psychiatric work-history interviews, rated on a 5-point scale. Total score range 10 to 50; higher scores indicate greater interview self-efficacy.
Time frame: T1: before teaching (Week 5); T2: after Period 1, before crossover (Week 6); T3: after Period 2 (Week 7)
Student evaluation of the two teaching methods and preferred learning sequence
Teaching Method Evaluation Questionnaire (study-specific, anonymous), administered after students had experienced both teaching methods. Eight parallel statements on the learning experience (e.g., clarity of instruction, a safe environment in which to make mistakes, usefulness of feedback) were rated separately for each teaching method on a 5-point Likert scale (1 = strongly disagree to 5 = strongly agree). Total score range 8 to 40 for each method; higher scores indicate a more favorable evaluation. Four forced-choice items comparing the two methods and asking the preferred learning sequence are reported descriptively as the number of students choosing each option.
Time frame: After students had experienced both methods (Week 7)
End-of-course retrospective reflection on interview confidence
End-of-Course Retrospective Confidence Reflection Questionnaire (study-specific, exploratory), administered as an end-of-course reflection activity. Students retrospectively rated their psychiatric interview confidence at seven course stages (from before any practice, through each teaching method, to before and after their first real-client interview and the end of the course) on a visual analogue-type numeric rating scale from 1 (lowest confidence) to 10 (highest confidence). Score range 1 to 10 at each stage; higher scores indicate greater confidence. Items on the learning resource recalled during real-client interviews and the preferred learning sequence are reported descriptively as the number of students choosing each option.
Time frame: End of course (approximately 10 weeks after the teaching sessions)
Plan to share: No — Individual participant data will not be publicly shared because participants did not consent to data sharing beyond the research team, as approved by the Institutional Review Board of Chang Gung Medical Foundation. De-identified data may be made available from the principal investigator upon reasonable request and with IRB approval.
No publications or documents are linked to this record.
Ran from Sep 2025 to primary completion in Oct 2025, 0 months.
Of 390 non-industry interventional studies with no phase under Communication, half reached primary completion within 18 months of starting (the median), counting those still running; a quarter within 6 and three quarters within 36. This study's 0 months is below that.
Counting every sponsor, half of 394 studies reached it within 18 months; a quarter within 6 and three quarters within 36.
How these figures are worked out, and which studies are left out of them.
From the registry record's own update history. This site started tracking changes on Sep 25, 2026; for anything earlier, see the record history on ClinicalTrials.gov ↗
This study is completed, as verified in Oct 2026. You cannot join it, but the record below documents what was studied.
Get an email when the registry record changes — status, dates, results — or when someone posts here.
Sign in to followQuestions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.
Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.
Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.
Chang Gung Memorial Hospital →