Ignite Creation Date:
2026-03-26 @ 3:14 PM
Ignite Modification Date:
2026-03-30 @ 8:49 PM
Study NCT ID:
NCT07390461
Status:
NOT_YET_RECRUITING
Last Update Posted:
2026-02-05
First Post:
2026-01-28
Is NOT Gene Therapy:
True
Has Adverse Events:
False
Brief Title:
Effectiveness of Artificial Intelligence Integrated Mixed Reality-based High-Alert Medications Management Simulation Program
Sponsor:
Organization:
Raw JSON
{'hasResults': False, 'derivedSection': {'miscInfoModule': {'versionHolder': '2026-03-25'}}, 'protocolSection': {'designModule': {'phases': ['NA'], 'studyType': 'INTERVENTIONAL', 'designInfo': {'allocation': 'RANDOMIZED', 'maskingInfo': {'masking': 'TRIPLE', 'whoMasked': ['PARTICIPANT', 'INVESTIGATOR', 'OUTCOMES_ASSESSOR']}, 'primaryPurpose': 'HEALTH_SERVICES_RESEARCH', 'interventionModel': 'PARALLEL'}, 'enrollmentInfo': {'type': 'ESTIMATED', 'count': 60}}, 'statusModule': {'overallStatus': 'NOT_YET_RECRUITING', 'startDateStruct': {'date': '2026-03-04', 'type': 'ESTIMATED'}, 'expandedAccessInfo': {'hasExpandedAccess': False}, 'statusVerifiedDate': '2026-01', 'completionDateStruct': {'date': '2026-03-06', 'type': 'ESTIMATED'}, 'lastUpdateSubmitDate': '2026-01-28', 'studyFirstSubmitDate': '2026-01-28', 'studyFirstSubmitQcDate': '2026-01-28', 'lastUpdatePostDateStruct': {'date': '2026-02-05', 'type': 'ACTUAL'}, 'studyFirstPostDateStruct': {'date': '2026-02-05', 'type': 'ACTUAL'}, 'primaryCompletionDateStruct': {'date': '2026-03-04', 'type': 'ESTIMATED'}}, 'outcomesModule': {'primaryOutcomes': [{'measure': 'High-Alert Medication clinical performance', 'timeFrame': 'Baseline, immediately post-intervention', 'description': 'The high-alert medication clinical performance competency assessment will utilize a questionnaire developed by our research team. The tool consists of 23 questions, of which 4 will vary depending on the simulation progress, resulting in a final assessment measuring 19 questions. Each item will be graded by the instructor on a scale of 0 for failure or incorrect execution, 1 for insufficient or inadequate execution, and 2 for accurate execution. The developed items will undergo a validity assessment by six experts before being revised and supplemented for use. Higher scores indicate greater clinical performance in high-alert medication.'}], 'secondaryOutcomes': [{'measure': 'Global Interpersonal Communication Competence', 'timeFrame': 'Baseline, immediately post-intervention', 'description': "communication competence will be measured using the Global Interpersonal Communication Competence (GICC) scale developed by Heo Kyung-ho (2003), which was modified and supplemented by Lee Hyun-sook and Kim Jong-gyeong (2010). It consists of 15 items, each rated on a 5-point Likert scale ranging from 1 (not at all) to 5 (very much), with higher scores indicating greater communication competence. In the study by Lee Hyun-sook and Kim Jong-gyeong (2010), the Cronbach's ⍺ was .83."}, {'measure': 'Clinical Reasoning Competency', 'timeFrame': 'Baseline, immediately post-intervention', 'description': "Clinical reasoning competency will be measured using the Clinical Reasoning Competency Scale (CRCS) developed by Bae et al. (2023). It consists of 22 items, each rated on a 5-point Likert scale ranging from 1 (not at all) to 5 (very much). A higher score indicates greater clinical reasoning competency. In the study by Bae et al. (2023), Cronbach's ⍺ was .92."}, {'measure': 'Medication Safety Competence', 'timeFrame': 'Baseline, immediately post-intervention', 'description': 'Medication safety competency will be measured using the Medication Safety Competence Scale (MSCS) developed by Park and Seomun (2021). It consists of 36 items and six subscales (patient-centered medication management, problem situation improvement, managing influencing factors, managing crisis situations, interdisciplinary collaboration, and responsibility as a nursing professional). Each item is rated on a 5-point Likert scale (1 = "not at all" to 5 = "very much"), with a total score of 36 to a maximum of 180. A higher total score indicates a higher level of medication safety competency. The reliability of the MSCS was Cronbach\'s α = .96.'}]}, 'oversightModule': {'oversightHasDmc': False, 'isFdaRegulatedDrug': False, 'isFdaRegulatedDevice': False}, 'conditionsModule': {'keywords': ['High-alert medications', 'nurse', 'mixed reality', 'artificial intelligence', 'medication safety'], 'conditions': ['Healhty']}, 'referencesModule': {'references': [{'type': 'RESULT', 'citation': "Bae, J., Lee, J., Choi, M., Jang, Y., Park, C. G., & Lee, Y. J. (2023). Development of the clinical reasoning competency scale for nurses. BMC nursing, 22(1), 138. Elendu, C., Amaechi, D. C., Okatta, A. U., Amaechi, E. C., Elendu, T. C., Ezeh, C. P., & Elendu, I. D. (2024). The impact of simulation-based training in medical education: A review. Medicine, 103(27), e38813. Fernández-Alcántara, M., Escribano, S., Juliá-Sanchis, R., Castillo-López, A., Pérez-Manzano, A., Macur, M., Kalender-Smajlović, S., García-Sanjuán, S., & Cabañero-Martínez, M. J. (2025). Virtual Simulation Tools for Communication Skills Training in Health Care Professionals: Literature Review. JMIR Medical Education, 11(1), e63082. Frost, J., Delaney, L., & Fitzgerald, R. (2020). Exploring the application of mixed reality in nurse education. BMJ Simulation & Technology Enhanced Learning, 6(4), 214. Fu, Y., Hu, Y., & Sundstedt, V. (2022). A systematic literature review of virtual, augmented, and mixed reality game applications in healthcare. ACM Transactions on Computing for Healthcare (HEALTH), 3(2), 1-27. Gaffney, T. A., Hatcher, B. J., & Milligan, R. (2016). Nurses' role in medical error recovery: an integrative review. Journal of clinical nursing, 25(7-8), 906-917. Han, Y., Chen, J., Xu, Y., Huang, P., & Hou, L. (2024). Nurse-led medication management as a critical component of transitional care for preventing drug-related problems. Aging Clinical and Experimental Research, 36(1), 151. Hodkinson, A., Tyler, N., Ashcroft, D. M., Keers, R. N., Khan, K., Phipps, D., Abuzour, A., Bower, P., Avery, A., & Campbell, S. (2020). Preventable medication harm across health care settings: a systematic review and meta-analysis. BMC medicine, 18(1), 313. Jeon, H. G., & Jeong, H. W. (2025). Effectiveness of a Mixed Reality Simulation Program for Dyspnoea Care on New Nurses' Clinical Competency: A Mixed-Methods Study. Nurse Education in Practice, 104397. Mardani, A., Griffiths, P., & Vaismoradi, M. (202"}]}, 'descriptionModule': {'briefSummary': "The goal of this clinical trial is to learn if a Artificial Intelligence integrated Mixed Reality-based High-Alert Medications Management Simulation Program (AIMR-HAM) helps hospital nurses manage high-alert medicines (HAMs) more safely. MR mixes real and virtual elements to let nurses practice in realistic scenarios.\n\nThe main questions are:\n\nDoes the AIMR-HAM improve nurses' medication safety skills? Does the AIMR-HAM lower medication errors and improve clinical performance?\n\nResearchers will compare two groups to answer these questions:\n\nIntervention group: AIMR-HAM Control group: standard education only\n\nWho can take part:\n\nNurses who work at large hospitals and have 1 to 6 years of clinical experience.\n\nAbout 60 nurses will join the study.\n\nWhat participants will do:\n\nAttend the assigned training (AIMR-HAM or standard education only). Complete short tests and surveys before and after training to measure skills, communication, and clinical reasoning.\n\nReport any medication errors that occur during the study. Why this matters: The study will show whether AIMR-HAM training can improve how nurses handle HAMs and make patient care safer.", 'detailedDescription': "This trial evaluates whether a Artificial Intelligence integrated Mixed Reality-based High-Alert Medications Management Simulation Program (AIMR-HAM) improves high-alert medications (HAMs) management skills, clinical performance (simulation-based observed assessments), communication, and medication error rates among hospital nurses with 1-6 years of clinical experience. The trial aims to assess the effectiveness of AIMR-HAM in enhancing practical competency and patient safety in real-world clinical practice.\n\nStudy design and randomization The study is a single-center, parallel-group, randomized controlled trial with approximately 60 participating nurses. Participants are randomly assigned 1:1 to the intervention or control group using a computer-generated randomization schedule (e.g., block randomization). Randomization is performed by an independent data manager to maintain allocation concealment. Outcome assessors are blinded to group assignment (assessor-blinded).\n\nIntervention - AIMR-HAM (intervention group)\n\nOverview: The intervention combines MR headset-based, scenario-driven hands-on practice.\n\nKey components:\n\n1. Orientation\n2. Pre-briefing\n3. AIMR simulation\n4. Debriefing\n\nTechnical note: The MR setup integrates virtual elements with the physical environment to deliver visual and auditory cues; device make/model and software version can be specified in the protocol field.\n\nControl group: The control group receives the hospital's standard medication management education (lectures, case discussions, and workshops). The schedule and total contact time are matched to the intervention group to control for time and attention.\n\nParticipant procedures and timeline The study flow is: screening → written informed consent → baseline (pre-intervention) assessment → randomization → assigned training (MR + standard education or standard education only) → immediate post-training assessment → follow-up assessment (for example, 1 month post-training) → study completion. At each assessment point, participants complete the same set of evaluations to allow comparison over time.\n\nData collection methods\n\n: Clinical performance and skills are measured using standardized performance checklists and observer rating scales during simulated assessments. Trained evaluators, blinded to allocation, conduct these assessments.\n\nSelf-report instruments (confidence, communication, cognitive workload) are collected via electronic or paper questionnaires and entered into the study database.\n\nMedication error data are collected from the hospital incident reporting system and participant self-reports during the study period; duplicate reports are reconciled through data review and classification.\n\nThe MR system automatically records participant interaction logs (timestamps, actions, decision points) which can be used as supplementary analytic data.\n\nAnalysis overview\n\nPrimary analyses follow the intention-to-treat principle. Continuous outcomes (e.g., competency scores) are compared using t-tests or linear regression; repeated measures are analyzed with mixed-effects models to account for within-participant correlations.\n\nBinary outcomes (e.g., presence of medication error) are analyzed using logistic regression or risk estimates.\n\nPre-specified covariates (for example, baseline scores or clinical unit) are included in adjusted analyses as needed. Sensitivity analyses address missing data (e.g., multiple imputation) and protocol deviations.\n\nSafety and ethics The study has received institutional review board (IRB) approval. All participants provide written informed consent before enrollment. Any discomfort related to MR use (such as dizziness or nausea) is monitored and managed per protocol; serious adverse events are reported to the IRB and hospital oversight bodies promptly. Personal data are de-identified or encrypted and stored with restricted access.\n\nQuality assurance and reliability measures\n\nInstructors and evaluators receive standardized training to ensure consistent delivery of the intervention and scoring of outcomes.\n\nRandomization, data entry, and data handling follow standard operating procedures. Data undergo regular monitoring and periodic quality checks; independent data quality audits may be performed if indicated.\n\nConclusion and potential impact This trial will determine whether AIMR-HAM leads to measurable improvements in nurses' medication management competency and reduces medication errors compared with standard education. Findings may inform hospital education practices and support wider adoption of AIMR-HAM for clinical skill training."}, 'eligibilityModule': {'sex': 'ALL', 'stdAges': ['CHILD', 'ADULT', 'OLDER_ADULT'], 'healthyVolunteers': True, 'eligibilityCriteria': 'Inclusion Criteria:\n\n* Nurses with at least one to six years of clinical experience.\n\n * Those who understand the purpose and procedures of this study and have given written consent to participate.\n\n * Those who have no physical or cognitive limitations in using mixed reality devices.\n\n ④ Those who are able to communicate in Korean and understand and respond to questions.\n\nExclusion Criteria:\n\n* Those who do not wish to participate in the study. ② Those who have participated in education related to high-alert medications within the past six months.\n\n * Those who are unable or have difficulty participating in the mixed reality education program due to visual, hearing, or neurological impairments, or adverse effects such as dizziness or motion sickness.\n\n * Those who voluntarily withdraw from the study midway through.'}, 'identificationModule': {'nctId': 'NCT07390461', 'acronym': 'AIMR-HAM', 'briefTitle': 'Effectiveness of Artificial Intelligence Integrated Mixed Reality-based High-Alert Medications Management Simulation Program', 'organization': {'class': 'OTHER', 'fullName': 'Chonnam National University Hospital'}, 'officialTitle': 'Effectiveness of Artificial Intelligence Integrated Mixed Reality-based High-Alert Medications Management Simulation Program', 'orgStudyIdInfo': {'id': 'CNUH-2025-435'}, 'secondaryIdInfos': [{'id': 'RS-2024-00345750', 'type': 'OTHER_GRANT', 'domain': 'The National Research Foundation of Korea'}]}, 'armsInterventionsModule': {'armGroups': [{'type': 'EXPERIMENTAL', 'label': 'Arm 1', 'description': 'Participants receive a Artificial Intelligence integrated Mixed Reality-based High-Alert Medications Management Simulation Program', 'interventionNames': ['Other: Artificial Intelligence integrated Mixed Reality-based Simulation Program']}, {'type': 'ACTIVE_COMPARATOR', 'label': 'Arm 2', 'description': "Participants receive the hospital's standard medication-management education", 'interventionNames': ['Other: Standard medication-management education']}], 'interventions': [{'name': 'Artificial Intelligence integrated Mixed Reality-based Simulation Program', 'type': 'OTHER', 'description': 'Participants in the intervention arm receive Artificial Intelligence integrated Mixed Reality-based High-Alert Medications Management Simulation Program', 'armGroupLabels': ['Arm 1']}, {'name': 'Standard medication-management education', 'type': 'OTHER', 'description': "Participants receive the hospital's standard medication-management education (didactic lectures, case discussions, and workshops)", 'armGroupLabels': ['Arm 2']}]}, 'contactsLocationsModule': {'centralContacts': [{'name': 'Hwigon Jeon, Ph.D. student', 'role': 'CONTACT', 'email': 'tjdans779@gmail.com', 'phone': '+82-10-5121-0700'}]}, 'ipdSharingStatementModule': {'ipdSharing': 'UNDECIDED'}, 'sponsorCollaboratorsModule': {'leadSponsor': {'name': 'Chonnam National University Hospital', 'class': 'OTHER'}, 'responsibleParty': {'type': 'PRINCIPAL_INVESTIGATOR', 'investigatorTitle': 'professor', 'investigatorFullName': 'Jinkyung Park', 'investigatorAffiliation': 'Chonnam National University Hospital'}}}}