An interventional study of Generative AI and Gamified Simulation-Based Train-the-Trainer BLS Programme and Conventional Instructor-Led Simulation-Based BLS Training in Cardiac Arrest and Cardiopulmonary Resuscitation, sponsored by Eastern International University. Not yet recruiting at 2 sites in 2 countries. Open to participants aged 20 Years and older, including healthy volunteers. Per ClinicalTrials.gov, last updated 2026-10-27.
Sponsored by Eastern International University · Not applicable, Interventional, and Other
The goal of this randomized controlled trial is to learn whether adding generative artificial intelligence (AI) feedback, gamified practice and a structured Train-the-Trainer component to a one-day simulation-based Basic Life Support (BLS) course improves BLS competence among high school teachers and school health staff in Ho Chi Minh City, Vietnam.
The main questions it aims to answer are:
Researchers will compare the Generative AI and gamified Train-the-Trainer programme (Group 1) with a conventional instructor-led simulation-based BLS course of the same length and the same 90 minutes of hands-on manikin practice (Group 2).
Participants will:
Design: individually randomized, school-size-stratified, parallel-group randomized controlled trial with 1:1 allocation and three measurement points: baseline (T1, before randomization), immediately after the training day (T2) and three-month follow-up (T3, 12 +/- 2 weeks).
Setting and sample: eight public high schools in Ho Chi Minh City, Vietnam, are selected by stratified simple random sampling (two small, two medium and four large schools). All eligible full-time personnel (physical education teachers, teachers of other subjects and school health staff) are invited; seven participants are enrolled per school (n = 56; 28 per group). Sample size was calculated with G*Power 3.1.9.4 (repeated-measures ANOVA, within-between interaction; f = 0.25, alpha = .05, power = .95, 2 groups, 3 measurements, correlation .50), giving 44, inflated to 56 for 20% anticipated attrition.
Randomization and concealment: after T1, participants are randomized individually 1:1 within school-size stratum using a computer-generated sequence with permuted blocks of variable size (2, 4, 6), prepared by an independent statistician and concealed in sequentially numbered, opaque, sealed envelopes.
Blinding: participants and trainers cannot be blinded. Outcome assessors for the BLS Performance Checklist (scored live) and the BLS Teaching Skills Assessment (rated from video) are blinded to allocation, and the data analyst remains blinded to group labels until the primary analyses are complete.
Interventions: both groups receive a one-day programme (08:00-16:00) in six matched stages at the simulation facility of the School of Health Sciences, Eastern International University, delivered by instructors of equivalent qualification and covering the same five clinical modules (recognition of cardiac arrest, activation of emergency response/115 call, high-quality CPR, ventilation, AED use). Both groups receive exactly 90 minutes of hands-on manikin practice with real-time device feedback. Group 1 additionally receives AI-assisted narrative feedback on compression technique (OpenAI GPT-4o-mini via an institutional API; no personal identifiers are transmitted), gamified practice stations and a structured Train-the-Trainer micro-teaching component with structured peer and facilitator feedback. Group 2 receives conventional instructor-led practice and basic teaching exposure. Group 2 participants are offered the full Group 1 programme free of charge after T3.
Instruments: Tool 1 BLS Performance Checklist (15 items, 0-15) on the WorldPoint CPR Taylor manikin; Tool 2 BLS Questionnaire (demographics; 15-item knowledge test; 10-item attitudes scale; 10-item self-efficacy scale); Tool 3 BLS Teaching Skills Assessment (10 items, 0-20). Content validity is assessed by five experts (I-CVI/S-CVI); reliability is assessed with Cronbach's alpha and intraclass correlation coefficients.
Pilot: before the main trial, a separate pilot study with 20-30 eligible school personnel at one public high school outside the sampling frame (October 2026) evaluates feasibility and the psychometric properties of the instruments; pilot participants are not enrolled in this trial and pilot data are never pooled with trial data.
Ethics: approved by the Burapha University Institutional Review Board, Thailand (Panel 3, full board review), certificate no. IRB3-136/2569, protocol code G-HS077/2569, approved 30 September 2026. Approval from the Ethics Committee of Eastern International University, Vietnam, is obtained before any recruitment or data collection. Recruitment is led by investigators of the Faculty of Nursing, Burapha University, Thailand; data collection takes place in Ho Chi Minh City, Vietnam.
926 studies on the registry are indexed under Heart Arrest; 226 are open to participants now.
This study's planned enrollment of 56 is below the median of 100 across 518 interventional studies indexed under Heart Arrest.
Browse Heart Arrest studies →This is the only study on the registry with Eastern International University as lead sponsor.
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:
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.
Participants attend a one-day (08:00-16:00) simulation-based BLS programme at Eastern International University covering recognition of cardiac arrest, activation of the emergency response system (115), high-quality CPR, ventilation and AED use. Of the 90 minutes of hands-on practice, 45 minutes are on the WorldPoint CPR Taylor manikin with real-time feedback and 45 minutes on an instrumented manikin with generative-AI narrative feedback (GPT-4o-mini) and gamified challenge stations. The day includes AI-supported pre-learning, AI-assisted goal setting, video- and AI-assisted debriefing, structured Train-the-Trainer micro-teaching with facilitator and peer feedback, and an AI-assisted individual practice summary.
Behavioral: Generative AI and Gamified Simulation-Based Train-the-Trainer BLS Programme
Participants attend a one-day (08:00-16:00) simulation-based BLS programme at Eastern International University with the same timetable, the same five clinical modules and the same 90 minutes of hands-on practice, all on the WorldPoint CPR Taylor manikin with real-time device feedback, delivered by instructors of equivalent qualification. Content review uses printed materials, debriefing is an instructor-led group discussion without video or AI, and teaching exposure consists of observing an instructor demonstration and delivering a short demonstration without the Train-the-Trainer methodology. No generative AI or gamification is used. After the three-month follow-up, participants are offered the full Group 1 programme free of charge.
Behavioral: Conventional Instructor-Led Simulation-Based BLS Training
One-day simulation-based BLS course augmented with three elements: (1) generative-AI narrative feedback on compression technique, in which sensor metrics from an instrumented manikin are sent without personal identifiers to OpenAI GPT-4o-mini and returned as a short Vietnamese comment against AHA high-quality CPR targets, plus AI support for pre-learning, content questions, lesson planning and an individual practice summary; (2) a locally run gamified CPR module with timed skill-challenge stations, points, badges, adaptive difficulty and a team leaderboard; and (3) a structured Train-the-Trainer component with lesson planning, 5-minute micro-teaching and structured facilitator and peer feedback across five teaching domains.
One-day instructor-led simulation-based BLS course matched to the experimental programme stage for stage, covering the same five clinical modules with 90 minutes of hands-on practice on the WorldPoint CPR Taylor manikin with real-time device feedback. Content review uses printed materials, debriefing is an instructor-led group discussion, and teaching exposure is limited to observing and delivering a short demonstration. No generative AI, gamification or structured Train-the-Trainer methodology is used.
BLS Performance Score (BLS Performance Checklist)
BLS performance measured with the researcher-developed 15-item BLS Performance Checklist (Tool 1) based on the 2020 AHA Guidelines, covering recognition of cardiac arrest, activation of the emergency response system, high-quality CPR and AED use, in one standardized scenario on a WorldPoint CPR Taylor manikin with feedback monitor in Blind Mode. Each item is scored 0 or 1; total score 0-15, higher scores indicate better performance. Scored live by trained assessors blinded to group allocation.
Time frame: Baseline (T1, 3-7 days before training, before randomization), immediately after the training day (T2, same day), and 3 months after training (T3, 12 +/- 2 weeks)
BLS Knowledge Score
BLS Knowledge Questionnaire (Tool 2, Part 2): 15 multiple-choice items based on the 2020 AHA Guidelines. Total score 0-15; higher scores indicate better knowledge.
Time frame: Baseline (T1, 3-7 days before training, before randomization), immediately after the training day (T2, same day), and 3 months after training (T3, 12 +/- 2 weeks)
Attitudes Toward BLS Score
Attitudes toward BLS Scale (Tool 2, Part 3): 10 Likert-type items on a five-point response format. Total score 10-50; higher scores indicate more positive attitudes toward BLS.
Time frame: Baseline (T1, 3-7 days before training, before randomization), immediately after the training day (T2, same day), and 3 months after training (T3, 12 +/- 2 weeks)
Self-Efficacy in Performing BLS Score
Self-Efficacy in Performing BLS Scale (Tool 2, Part 4): 10 items on a five-point response format, aligned with Bandura's Social Learning Theory. Total score 10-50; higher scores indicate greater self-efficacy.
Time frame: Baseline (T1, 3-7 days before training, before randomization), immediately after the training day (T2, same day), and 3 months after training (T3, 12 +/- 2 weeks)
BLS Teaching Skills Score (BLS Teaching Skills Assessment)
BLS Teaching Skills Assessment (Tool 3): 10-item rubric across five domains (content accuracy, demonstration skills, facilitation skills, learner engagement, feedback skills), each item scored 0-2; total score 0-20, higher scores indicate better teaching skills. Rated from video of a 5-7 minute micro-teaching session by an assessor blinded to group allocation.
Time frame: Immediately after the training day (T2, same day) and 3 months after training (T3, 12 +/- 2 weeks)
Plan to share: No — Individual participant data will not be shared. Under the approved ethics protocol, identifiable data are accessible only to the principal investigator and the two thesis advisors, and all study records are destroyed one year after publication of the findings. Results will be reported only in aggregate.
No publications or documents are linked to this record.
Start is estimated for Nov 2026; primary completion for Apr 2027, 5 months later.
Of 204 non-industry interventional studies with no phase under Heart Arrest, half reached primary completion within 29 months of starting (the median), counting those still running; a quarter within 10 and three quarters within 47. This study's planned 5 months is below that.
Counting every sponsor, half of 218 studies reached it within 28 months; a quarter within 10 and three quarters within 47.
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 not yet recruiting, 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.