Effects of generative artificial intelligence (GenAI) patient simulation on perceived clinical competency among global nursing undergraduates: a cross-over randomised controlled trial

Abstract

Background: This study compared scenario-based generative artificial intelligence (GenAI) patient simulation with immersive 360° virtual reality (VR) simulation in terms of perceived clinical competence, cultural awareness, AI readiness, and simulation effectiveness among nursing students. Methods: This cross-over randomised controlled study design was conducted from June 2024 to August 2024. Forty-four undergraduate nursing students from years 1–3 were randomised to receive either GenAI patient simulation (Group B) or 360° VR simulation (Group A) with a one-week washout period. Five self-reported questionnaires were used to measure clinical competency: the Clinical Competence Questionnaire (CCQ), Cultural Awareness Scale (CAS), Medical Artificial Intelligence Readiness Scale for Medical Students (MAIRS-MS), Simulation Effectiveness Tool – Modified Questionnaire (SET-M), and a demographic questionnaire. Results: Both interventions significantly improved clinical competence, cultural awareness, and AI readiness. When administered first, GenAI patient simulation demonstrated greater initial effects on clinical competence and AI readiness compared to the 360° VR simulation, though both groups achieved similar improvements by study completion. At T1, Group B (receiving GenAI) demonstrated significantly larger improvements in CCQ total score [47.68 (95% CI: 36.68, 58.68), p < 0.001] compared to Group A (receiving 360° VR) [24.95 (95% CI: 13.96, 35.95), p < 0.001], with significant between-group difference [16.59 (95% CI: 2.77, 30.41), p = 0.020]. At T2 (post-crossover), both groups maintained significant improvements. For MAIRS-MS (measured at baseline and following each group’s GenAI exposure), Group B showed improvement from baseline to T1 [30.18 (95% CI: 23.35, 37.01), p < 0.001] while Group A showed improvement from baseline to T2 [16.64 (95% CI: 9.80, 23.47), p < 0.001], with significant between-group difference [12.09 (95% CI: 4.43, 19.75), p = 0.003]. Both groups experienced changes in CAS scores, though between-group differences were not statistically significant. For SET-M, most participants (75%) felt debriefing contributed to their learning, and 68.2% reported increased confidence in nursing assessment skills. Conclusions: The findings provide preliminary evidence of its effectiveness in enhancing perceived clinical outcomes among nursing students. Both 360° VR simulation and GenAI patient simulation may serve as effective teaching tools; however, GenAI patient simulation appeared to demonstrate a greater initial effect on clinical competence and AI readiness, although both interventions proved effective across all measured domains. Clinical trial registration/number: Not applicable.