Sang Un Park, So Young Choi
Background/Objectives: The integration of generative artificial intelligence (AI) into healthcare has expanded the competencies required of clinical nurses. However, existing nursing informatics education programs do not adequately prepare nurses to use generative AI effectively and ethically in clinical practice. This study aimed to develop and evaluate a metaverse-based generative AI nursing informatics competency education program for clinical nurses. Methods: A randomized controlled pretest-posttest design was employed. Forty-eight clinical nurses were randomly assigned to an intervention group (n = 24) or a control group (n = 24), and 46 participants completed the study. The six-week education program was developed using the Analysis, Design, Development, Implementation, and Evaluation (ADDIE) instructional design model and Bandura's self-efficacy theory. It was delivered through a metaverse platform using a flipped learning approach. Outcomes were measured at baseline, immediately after the intervention, and four weeks after the intervention. Data were analyzed using repeated-measures analysis of variance (ANOVA). Results: Compared with the control group, the intervention group demonstrated a significantly greater improvement in nursing informatics competency, the pre-specified primary outcome (p < 0.01), sustained at the four-week follow-up. Greater improvements were also observed for the secondary outcomes-general self-efficacy, ethical awareness of AI use, and evidence-based practice (all p < 0.01)-though these findings should be interpreted as hypothesis-generating given the absence of multiplicity adjustment. Conclusions: The metaverse-based generative AI education program improved self-reported nursing informatics competency and other key competencies among clinical nurses. Trial Registration: Clinical Research Information Service (CRIS) KCT0011821 registered on 8 April 2026.