Clinical Reasoning in Nursing EducationMAGICSNCT07872735
MAGICS - Multi-Agent Generative AI in Clinical Simulation for Clinical Deterioration Training
A study testing Generative AI-integrated Blended Simulation and High Fidelity Simulation in people with Clinical Reasoning in Nursing Education and Virtual Simulation, run by National University of Singapore.
Trial summary
This study compares the effectiveness of a Generative AI-integrated blended simulation programme and high-fidelity simulation alone on nursing students' clinical reasoning and learning experience during deterioration training Read more about this study
- Who is it for?
- Ages 18 to 55 yearsHealthy volunteers can take part
- Conditions the study is for
- Clinical Reasoning in Nursing Education, Virtual Simulation, Artificial Intelligence in Education
- What is being tested?
- Generative AI-integrated Blended Simulation and High Fidelity Simulation
- Could I receive a placebo?
- No, everyone receives an active treatment
- How many people
- 200 participants
- Where
- No sites listed yet
- Study dates
- 12 Oct 2026to 22 Nov 2026
- Phase
- Interventional
- Are there results?
- Not yet: the study is under way
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 to 55 years
- All sexes
- Healthy volunteers accepted
- Adult
Who may be able to join
- 18 to 55 years of age
- Third-year undergraduate nursing student at the Alice Lee Centre for Nursing Studies
- Have access to a computer and internet connection required for the virtual reality simulation program (Intervention arm)
Who cannot join
- Do not agree to be voice and/or video-recorded as part of the research activities
Trial locations and contacts
No sites are listed yet. Contact the study team or a site near you to ask about taking part.
About this study
Official title: MAGICS - Multi-Agent Generative AI in Clinical Simulation for Clinical Deterioration Training: A Cluster Randomized Controlled Trial
This study compares the effectiveness of a Generative AI-integrated blended simulation programme and high-fidelity simulation alone on nursing students' clinical reasoning and learning experience during deterioration training
- Conditions
- Clinical Reasoning in Nursing Education, Virtual Simulation, Artificial Intelligence in Education, Deterioration, Clinical, Simulation Training
- Being tested
- Generative AI-integrated Blended Simulation, High Fidelity Simulation
- Keywords
- Clinical Reasoning, Simulation Training, Artificial Intelligence, Large Language Models, Virtual Reality
- Medical subject headings
- Clinical Deterioration
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
Generative AI-integrated Blended SimulationOther
Generative AI-integrated Blended Simulation consists of a multi-agent, generative AI-integrated virtual simulation and in-person high fidelity simulation
High Fidelity SimulationOther
In-person high fidelity simulation, usual curriculum.
| Study group | Role | What they receive |
|---|---|---|
| Intervention Arm | Experimental | Participants will undergo a 4-hour blended simulation programme. In the first two hours, they will attempt two screen-based virtual reality simulation scenarios involving a patient deteriorating due to chest infection and sepsis. Participants will need to perform patient assessment and management on a virtual patient (Non-GenAI). Three GenAI agents will facilitate continuous learning support (GenAI teaching assistant), interprofessional communication training (GenAI doctor) and automated debriefing (GenAI nurse facilitator). In the next two hours, participants will undergo two team-based, high fidelity simulation on chest infection and sepsis. Receives: Other: Generative AI-integrated Blended Simulation |
| Control Arm | Active comparator | Participants will undergo a 4-hour in-person high fidelity simulation programme (usual curriculum). In the first two hours, a human nursing tutor will guide the participants through two high fidelity simulation scenarios involving a patient deteriorating due to chest infection and sepsis. Participants will need to perform patient assessment and management on a high fidelity mannekin. The human nursing tutor will provide continuous learning support, roleplay as a doctor to facilitate interprofessional communication training and conduct debriefing. In the next two hours, participants will undergo two team-based, high fidelity simulation on chest infection and sepsis. Receives: Other: High Fidelity Simulation |
What is being measured
The primary outcome is the main question the study is designed to answer.
Clinical Reasoning Competencies through a 15-minute video and audio-recorded simulation-based assessment within 2 weeks post-intervention.
Assessors used the validated Clinical Reasoning Evaluation Simulation Tool to measure nurses' clinical reasoning competencies during a simulated clinical deterioration scenario. Total score ranges from 11 (minimum) to 60 (maximum), with higher scores representing higher clinical reasoning competencies.
Measured: Within 2 weeks of postintervention
Change from Baseline in Sepsis Knowledge on the 25-item Sepsis Knowledge Quiz as compared with immediately after interventions.
The 25-item Sepsis Knowledge Quiz was developed and content validated by two advanced practice nurse, and two nursing academics. Total score ranges from 0 (minimum) to 25 (maximum), with higher scores representing higher application-based knowledge towards sepsis management and care.
Measured: Baseline and immediately after 4-hour research session
Secondary outcomes (3)
Change from Baseline in Attitudes towards Generative Artificial Intelligence Use for Simulation Learning on the 13-item Generative Artificial Intelligence Attitude Scale for Students as compared with immediately after interventions.
The Generative Artificial Intelligence Attitude Scale for Students is a validated and self-reported instrument using a 5-point Likert scale. It measures participants' acceptance towards the use of Gen artificial intelligence applications for simulation learning. Total score ranges from 13 (minimum) to 65 (maximum), with higher scores representing greater acceptance towards generative artificial intelligence use for simulation learning.
Measured: Baseline and immediately after 4-hour research session
Post-intervention Satisfaction with Simulation-based Learning on the 18-item Satisfaction with Simulation Experience Scale
The Satisfaction with Simulation Experience Scale is a validated and self-reported instrument using a 5-point Likert scale. It measures the participant's satisfaction with simulation-based learning program. Total score ranges from 18 (minimum) to 90 (maximum), with higher scores representing higher satisfaction towards the simulation-based learning.
Measured: Immediately after 4-hour research session
Post-intervention Blended Simulation Perceptions on the 9-item Perceptions of Blended Simulation Scale, for Intervention Arm only.
The Perceptions of Blended Simulation Scale is a validated and self-reported instrument using a 5-point Likert scale. It measures participants' experience with blended simulation interventions incorporating technology-enhanced and in-person, team-based components. Total score ranges from 9 (minimum) to 45 (maximum), with higher scores representing greater perceptions towards the use of blended simulation for learning.
Measured: Immediately after 4-hour research session
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted14 Oct 2026
- Study start12 Oct 2026 (estimated)
- Primary completion22 Nov 2026 (estimated)
- Study completion22 Nov 2026 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Other trials for Clinical Reasoning in Nursing EducationStudies of the same condition, open and under way.
- 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
- Parallel groups
- Masking
- Single blind
- Who is masked
- Outcomes assessor
- Enrolment
- 200 participants (estimated)
Sponsor and investigators
- Lead sponsor
- National University of Singapore
- Sponsor type
- University, hospital or other
- Responsible party
- Principal investigator, Nicholas Neo Wee Siong, National University of Singapore
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07872735
- Sponsor's protocol ID
- DERC-001910
- Other IDs
- ALCNS/2025/PTSG-202526-011
- Acronym
- MAGICS
- Status last verified
- Oct 2026
- First submitted
- 7 Oct 2026
- Last updated
- 21 Oct 2026
- Results posted
- No
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- No: The data sets collected or analyzed during the study are available from the corresponding author on reasonable request
Study at a glance
From the registry record, last updated by the sponsor on 21 Oct 2026. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- MAGICS - Multi-Agent Generative AI in Clinical Simulation for Clinical Deterioration Training: A Cluster Randomized Controlled Trial
- ClinicalTrials.gov ID
- NCT07872735
- Acronym / sponsor ID
- MAGICS / DERC-001910
- Conditions
- Clinical Reasoning in Nursing Education, Virtual Simulation, Artificial Intelligence in Education, Deterioration, Clinical, Simulation Training
- Keywords
- Clinical Reasoning, Simulation Training, Artificial Intelligence, Large Language Models, Virtual Reality
- Study type
- Interventional
- Recruitment status
- Not yet recruiting
- Enrolment
- 200 participants (estimated)
- Lead sponsor
- National University of SingaporeUniversity, hospital or other
- Study start
- 12 Oct 2026 (estimated)
- Primary completion
- 22 Nov 2026 (estimated)
- Study completion
- 22 Nov 2026 (estimated)
- First posted
- 14 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.
This study compares the effectiveness of a Generative AI-integrated blended simulation programme and high-fidelity simulation alone on nursing students' clinical reasoning and learning experience during deterioration training
Study design
- Primary purpose
- Other
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Masking
- Single blind (outcomes assessor)
- Number of arms
- 2
| Arm | Type | Receives |
|---|---|---|
| Intervention Arm | Experimental | Other: Generative AI-integrated Blended SimulationParticipants will undergo a 4-hour blended simulation programme. In the first two hours, they will attempt two screen-based virtual reality simulation scenarios involving a patient deteriorating due to chest infection and sepsis. Participants will need to perform patient assessment and management on a virtual patient (Non-GenAI). Three GenAI agents will facilitate continuous learning support (GenAI teaching assistant), interprofessional communication training (GenAI doctor) and automated debriefing (GenAI nurse facilitator). In the next two hours, participants will undergo two team-based, high fidelity simulation on chest infection and sepsis. |
| Control Arm | Active comparator | Other: High Fidelity SimulationParticipants will undergo a 4-hour in-person high fidelity simulation programme (usual curriculum). In the first two hours, a human nursing tutor will guide the participants through two high fidelity simulation scenarios involving a patient deteriorating due to chest infection and sepsis. Participants will need to perform patient assessment and management on a high fidelity mannekin. The human nursing tutor will provide continuous learning support, roleplay as a doctor to facilitate interprofessional communication training and conduct debriefing. In the next two hours, participants will undergo two team-based, high fidelity simulation on chest infection and sepsis. |
Who may qualify
- Ages
- 18 to 55 years
- Sex
- All
- Healthy volunteers
- Accepted
- Age groups
- Adult
Key inclusion criteria (3 listed)
- 18 to 55 years of age
- Third-year undergraduate nursing student at the Alice Lee Centre for Nursing Studies
- Have access to a computer and internet connection required for the virtual reality simulation program (Intervention arm)
Key exclusion criteria (1 listed)
- Do not agree to be voice and/or video-recorded as part of the research activities
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-integrated Blended SimulationGenerative AI-integrated Blended Simulation consists of a multi-agent, generative AI-integrated virtual simulation and in-person high fidelity simulation | Other | Intervention Arm |
| High Fidelity SimulationIn-person high fidelity simulation, usual curriculum. | Other | Control Arm |
Primary outcome
Clinical Reasoning Competencies through a 15-minute video and audio-recorded simulation-based assessment within 2 weeks post-intervention.
Time frame: Within 2 weeks of postintervention
Assessors used the validated Clinical Reasoning Evaluation Simulation Tool to measure nurses' clinical reasoning competencies during a simulated clinical deterioration scenario. Total score ranges from 11 (minimum) to 60 (maximum), with higher scores representing higher clinical reasoning competencies.
Change from Baseline in Sepsis Knowledge on the 25-item Sepsis Knowledge Quiz as compared with immediately after interventions.
Time frame: Baseline and immediately after 4-hour research session
The 25-item Sepsis Knowledge Quiz was developed and content validated by two advanced practice nurse, and two nursing academics. Total score ranges from 0 (minimum) to 25 (maximum), with higher scores representing higher application-based knowledge towards sepsis management and care.
3 secondary outcomes
Change from Baseline in Attitudes towards Generative Artificial Intelligence Use for Simulation Learning on the 13-item Generative Artificial Intelligence Attitude Scale for Students as compared with immediately after interventions.
Time frame: Baseline and immediately after 4-hour research session
Post-intervention Satisfaction with Simulation-based Learning on the 18-item Satisfaction with Simulation Experience Scale
Time frame: Immediately after 4-hour research session
Post-intervention Blended Simulation Perceptions on the 9-item Perceptions of Blended Simulation Scale, for Intervention Arm only.
Time frame: Immediately after 4-hour research session
Results and safety
This study is still under way. Results are not available in the source record yet.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 21 Oct 2026.
- Individual participant dataSharing planned: No. The data sets collected or analyzed during the study are available from the corresponding author on reasonable request
Related trials for Clinical Reasoning in Nursing Education
Not yet recruiting
Effectiveness of Serious Games on Nursing Students' Clinical Reasoning
Clinical Reasoning
Not yet recruiting
Comparative Case Learning in Undergraduate Nursing Students
Clinical Reasoning in Nursing Education
Not yet recruiting
THE EFFECT OF DIGITAL STORYTELLING ON NURSING STUDENTS' NURSING PROCESS EDUCATION
Education, Nursing, Students, Nursing
Not yet recruiting
The Effect of Artificial Intelligence-Supported Intramuscular and Subcutaneous Injection Training on Nursing Students
AI Chatbot, Nursing Education
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.
Questions about this trial
What is this clinical trial studying?
A study testing Generative AI-integrated Blended Simulation and High Fidelity Simulation in people with Clinical Reasoning in Nursing Education and Virtual Simulation, run by National University of Singapore.
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 3 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: opening soon, as of the sponsor's last update on 21 Oct 2026. Status can change between updates, so confirm with the study contact before making plans.
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?
This study is still under way. Results are not available in the source record yet.
How can a doctor refer a patient or contact the research team?
Contact Nicholas Wee Siong Neo, MSc (+6565167451, e1513523@u.nus.edu), or a site near the patient. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Clinical Reasoning Competencies through a 15-minute video and audio-recorded simulation-based assessment within 2 weeks post-intervention. (time frame: Within 2 weeks of postintervention). The study lists 2 primary outcomes in all. 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 21 Oct 2026.