Clinical CompetenceNCT07896525
Generative AI Simulated Patients Versus Expert Demonstration Videos for Psychiatric Interview Training in Occupational Therapy Students
A study testing Generative AI simulated patient and Expert demonstration video in people with Clinical Competence and Communication Skills, run by Chang Gung Memorial Hospital at 1 site in Taiwan.
Trial summary
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: 1. Read more about this study
- Who is it for?
- Ages 18 years and olderHealthy volunteers can take part
- Conditions the study is for
- Clinical Competence, Communication Skills, Self Efficacy
- What is being tested?
- Generative AI simulated patient and Expert demonstration video
- Type of treatment
- Lifestyle or therapy programme
- Could I receive a placebo?
- No, everyone receives an active treatment
- How many people
- 53 participants
- Where
- 1 siteTaiwan
- Study dates
- 17 Sep 2025to 10 Dec 2025
- Phase
- Interventional
- Are there results?
- None posted in the registry
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages 18 years and older
- All sexes
- Healthy volunteers accepted
- Adult, Older adult
Who may be able to join
- Third-year undergraduate students in the Department of Occupational Therapy, Chang Gung University, enrolled in the required course "Vocational Rehabilitation and Work Capacity Evaluation Practicum" in the 2025 fall semester
- Provided written informed consent for the use of course data in research
Who cannot join
- Declined consent for research use of their data (these students still participated in all course activities as usual)
Trial locations and contacts
1 site in 1 country.
About this study
Official title: A Randomized Two-Period, Two-Sequence Crossover Trial Comparing Generative AI Simulated Patients and Expert Demonstration Videos for Teaching Psychiatric Work-History Interviewing to Occupational Therapy Students
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:
- Which teaching method leads to better interview performance in an objective structured clinical examination (OSCE) with a standardized patient?
- How do the two methods affect students' interview self-efficacy?
- How do students evaluate the two methods, and which learning sequence do they prefer?
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.
Read the detailed description
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.
- Conditions
- Clinical Competence, Communication Skills, Self Efficacy
- Being tested
- Generative AI simulated patient, Expert demonstration video
- Keywords
- generative artificial intelligence, virtual simulated patient, OSCE, occupational therapy education, psychiatric interview, crossover
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
Generative AI simulated patientBehavioural
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.
Expert demonstration videoBehavioural
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.
| Study group | Role | What they receive |
|---|---|---|
| Sequence 1: AI simulated patient, then expert video | Experimental | 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. Receives: Behavioral: Generative AI simulated patient; Behavioral: Expert demonstration video |
| Sequence 2: expert video, then AI simulated patient | Experimental | 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. Receives: Behavioral: Generative AI simulated patient; Behavioral: Expert demonstration video |
What is being measured
The primary outcome is the main question the study is designed to answer.
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.
Measured: Immediately after the Period 1 teaching session (same day, course Week 6), before crossover
Secondary outcomes (2)
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.
Measured: 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.
Measured: After students had experienced both methods (Week 7)
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted27 Oct 2026
- Study start17 Sep 2025
- Primary completion8 Oct 2025
- Study completion10 Dec 2025
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Other trials for Clinical CompetenceStudies of the same condition, open and under way.
- More trials run by Chang Gung Memorial HospitalThe sponsor's other registered studies.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Interventional
- Phase
- Phase N/A
- Primary purpose
- Other
- Allocation
- Randomised
- Intervention model
- Crossover
- Model description
- Two-period, two-sequence crossover. Sequence 1: AI simulated patient (Week 6) then expert demonstration video (Week 7). Sequence 2: expert demonstration video (Week 6) then AI simulated patient (Week 7). The primary outcome (OSCE) was assessed at the end of Period 1, before crossover.
- Masking
- Single blind
- Who is masked
- Outcomes assessor
- Enrolment
- 53 participants (actual)
Sponsor and investigators
- Lead sponsor
- Chang Gung Memorial Hospital
- Sponsor type
- University, hospital or other
- Collaborators
- Chang Gung University, Ministry of Education, Taiwan
- Responsible party
- Principal investigator, Poyu Chen, Chang Gung University
- Investigators
- Poyu Chen, PhD, Principal investigator, Chang Gung University
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07896525
- Sponsor's protocol ID
- 202501080B0A3
- Other IDs
- PSK1143035
- Status last verified
- Oct 2026
- First submitted
- 21 Oct 2026
- Last updated
- 2 Nov 2026
- Results posted
- No
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- 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.
Study at a glance
From the registry record, last updated by the sponsor on 2 Nov 2026. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- A Randomized Two-Period, Two-Sequence Crossover Trial Comparing Generative AI Simulated Patients and Expert Demonstration Videos for Teaching Psychiatric Work-History Interviewing to Occupational Therapy Students
- ClinicalTrials.gov ID
- NCT07896525
- Acronym / sponsor ID
- 202501080B0A3
- Conditions
- Clinical Competence, Communication Skills, Self Efficacy
- Keywords
- generative artificial intelligence, virtual simulated patient, OSCE, occupational therapy education, psychiatric interview, crossover
- Study type
- Interventional
- Recruitment status
- Completed
- Enrolment
- 53 participants (actual)
- Lead sponsor
- Chang Gung Memorial HospitalUniversity, hospital or other
- Collaborators
- Chang Gung University, Ministry of Education, Taiwan
- Study start
- 17 Sep 2025 (actual)
- Primary completion
- 8 Oct 2025 (actual)
- Study completion
- 10 Dec 2025 (actual)
- First posted
- 27 Oct 2026 (actual)
- Results
- Not posted in the source record
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
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:
- Which teaching method leads to better interview performance in an objective structured clinical examination (OSCE) with a standardized patient?
- How do the two methods affect students' interview self-efficacy?
- How do students evaluate the two methods, and which learning sequence do they prefer?
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.
Detailed description
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.
Study design
- Primary purpose
- Other
- Allocation
- Randomised
- Intervention model
- Crossover
- Masking
- Single blind (outcomes assessor)
- Number of arms
- 2
- Model description
- Two-period, two-sequence crossover. Sequence 1: AI simulated patient (Week 6) then expert demonstration video (Week 7). Sequence 2: expert demonstration video (Week 6) then AI simulated patient (Week 7). The primary outcome (OSCE) was assessed at the end of Period 1, before crossover.
| Arm | Type | Receives |
|---|---|---|
| Sequence 1: AI simulated patient, then expert video | Experimental | Behavioral: Generative AI simulated patient, Behavioral: Expert demonstration videoPeriod 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. |
| Sequence 2: expert video, then AI simulated patient | Experimental | Behavioral: Generative AI simulated patient, Behavioral: Expert demonstration videoPeriod 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. |
Who may qualify
- Ages
- 18 years and older
- Sex
- All
- Healthy volunteers
- Accepted
- Age groups
- Adult, Older adult
Key inclusion criteria (2 listed)
- Third-year undergraduate students in the Department of Occupational Therapy, Chang Gung University, enrolled in the required course "Vocational Rehabilitation and Work Capacity Evaluation Practicum" in the 2025 fall semester
- Provided written informed consent for the use of course data in research
Key exclusion criteria (1 listed)
- Declined consent for research use of their data (these students still participated in all course activities as usual)
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Interventions
| Intervention | Type | Arms |
|---|---|---|
| Generative AI simulated patientOne-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. | Behavioural | Sequence 1: AI simulated patient, then expert video, Sequence 2: expert video, then AI simulated patient |
| Expert demonstration videoA 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. | Behavioural | Sequence 1: AI simulated patient, then expert video, Sequence 2: expert video, then AI simulated patient |
Primary outcome
OSCE interview performance score
Time frame: Immediately after the Period 1 teaching session (same day, course Week 6), before crossover
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.
2 secondary outcomes
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
Time frame: After students had experienced both methods (Week 7)
Results and safety
The study is completed, but results are not available in the source record. That does not mean the treatment did or did not work.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 2 Nov 2026.
- Individual participant dataSharing planned: 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.
Related trials for Clinical Competence
Active, not recruiting
Enhancing Male Nursing Students' Competence in Maternity Care: A Quasi-Experimental Study in Egypt
Maternity Nursing, Obstetric Nursing
Not yet recruiting
The Effectiveness of Situation Awareness Approach on Nursing Competencies in Obstetric Practicum: A Multimodal Teaching
Non-disease Research. Enhancing Nursing Students' Obstetric Situation Awareness and Clinical Decision-making Through Multimodal Teaching, Clinical Competence
Not yet recruiting
Remote Guidance for eFAST Training Using a Head-Mounted Device
Clinical Competence, Ultrasonography
Not yet recruiting
The Effect of Scenario-Based Simulation Training for Nutritional Counseling During Pregnancy on Nursing Students' Anxiety Levels, Self-Efficacy Perceptions, and Clinical Skill Performance
Student Nursing, Simulation Training
Not yet recruiting
VR Simulation-Based Implanted Port Catheter Training in Nursing Students
Nursing Education, Clinical Competence
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part. This study is not recruiting at the moment.
Poyu Chen, PhD principal investigator
Chang Gung University
1 site in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
A study testing Generative AI simulated patient and Expert demonstration video in people with Clinical Competence and Communication Skills, run by Chang Gung Memorial Hospital at 1 site in Taiwan.
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
The sponsor lists 2 inclusion and 1 exclusion criteria. Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: finished, as of the sponsor's last update on 2 Nov 2026. Status can change between updates, so confirm with the study contact before making plans.
Where is the study taking place?
The record lists 1 site in Taiwan. Whether a site is taking part right now should be confirmed with that site. See every site.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
The study is completed, but results are not available in the source record. That does not mean the treatment did or did not work.
How can a doctor refer a patient or contact the research team?
The record lists no contact. The official record names the sponsor, who can be asked directly. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
OSCE interview performance score (time frame: Immediately after the Period 1 teaching session (same day, course Week 6), before crossover). It is what the study was designed to measure, not a finding.
Where can I read the original study information?
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 2 Nov 2026.