Student or educator? Sign up with your school email and get 6 months of Pro free.

The DOI matches its Crossref record; 39 of the 39 references it cites were found in a registry or an index; 7 of the 13 sources its claims cite were checked for support.

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

Open access

Published version of a preprint

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.

Overview

CoChat Summary

TL;DR

In a cross-over randomised controlled trial with 44 undergraduate nursing students from six countries, both generative AI (GenAI) patient simulation and 360° VR simulation improved perceived clinical competence, cultural awareness, and AI readiness. GenAI showed greater initial effects on clinical competence and AI readiness when delivered first, though both groups improved by study completion.

Key findings

  • Both interventions significantly improved perceived clinical competence. At T1, Group B (GenAI first) had a larger CCQ total-score improvement [47.68 (95% CI: 36.68, 58.68), p < 0.001] than Group A (360° VR first) [24.95 (95% CI: 13.96, 35.95), p < 0.001], with a significant between-group difference [16.59 (95% CI: 2.77, 30.41), p = 0.020]. By T2, both groups maintained improvements and the between-group difference was not significant [2.41 (95% CI: −11.41, 16.23), p = 0.727].
  • For AI readiness, Group B improved from baseline to T1 after GenAI exposure [30.18 (95% CI: 23.35, 37.01), p < 0.001], while Group A improved from baseline to T2 after its GenAI exposure [16.64 (95% CI: 9.80, 23.47), p < 0.001]; the between-group difference was significant [12.09 (95% CI: 4.43, 19.75), p = 0.003], favouring GenAI first. Significant between-group differences also appeared on MAIRS-MS Cognition and Ability subscales.
  • Cultural awareness improved in both groups. Group B showed significant CAS total-score gains at T1 [27.59 (95% CI: 9.54, 45.64), p = 0.003] and T2 [20.91 (95% CI: 2.86, 38.96), p = 0.024]; Group A showed significant improvement at T1 [18.27 (95% CI: 0.22, 36.32), p = 0.047] with marginal significance at T2. No significant between-group differences were detected for CAS total or subscales.
  • On SET-M, 75% (n = 33) strongly agreed debriefing contributed to learning, 68.2% (n = 30) strongly agreed they were more confident in nursing assessment skills, and 72.7% (n = 32) strongly agreed they were confident using evidence-based practice to provide nursing care.

Methods

  • Cross-over randomised controlled trial conducted June–August 2024 with 44 undergraduate nursing students in years 1–3 from Hong Kong, Taiwan, Thailand, Spain, South Korea, and Australia. Participants were randomised 1:1 to Group A (360° VR first, then GenAI) or Group B (GenAI first, then 360° VR), with a one-week washout. Both groups received an acute pneumonia case at T1 and an acute appendicitis case at T2, each involving a 60-minute simulation plus 60-minute structured 3D-model debriefing.
  • Measures included the Clinical Competence Questionnaire (CCQ), Cultural Awareness Scale (CAS), Medical Artificial Intelligence Readiness Scale for Medical Students (MAIRS-MS), Simulation Effectiveness Tool–Modified (SET-M), and a demographic questionnaire at baseline (T0), T1, and T2. MAIRS-MS was administered at baseline and after each group’s GenAI exposure; SET-M was measured at T1 only.
  • Analysis used linear mixed models with participant as a random effect and time, group, randomisation sequence order, and time–group interaction as fixed effects; linear contrasts assessed within- and between-group changes. Analyses were performed in IBM SPSS version 29.0 with two-sided tests and p < 0.05.

Limitations

  • Stated by the paper: the small sample (n = 44) limits subgroup analyses by university, country, and cohort year and may limit generalisability; all measures assess perceived competence via self-report rather than objective clinical performance; English proficiency was not formally assessed although surveys were administered in English; the intervention duration and short study timeframe may have been insufficient to change CAS Behavior/Comfort with Interactions and Research Issues subscales; and no long-term follow-up was conducted.
  • Evident from the text: MAIRS-MS was not measured after the 360° VR simulation, so AI readiness cannot be directly compared between the two modalities; SET-M was measured only at T1, limiting comparison across time or crossover. The one-week washout may not fully eliminate carryover or sequence effects, which the authors themselves discuss as a possible explanation for Group B’s larger initial gains.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1186/s12912-025-03492-0

Cites

39 of 39 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Verification

Claims the paper makes

2 Valid · 5 Not valid · 3 Not checked · 107 Own results and interpretations

49 more claims

Create a free account to see all 117 claims and every source verdict.

See all claims — free account
  • It may state two separate claims as one. 39
  • Probably not a substantial claim. 36

Create a free account to see these claims.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

1 more claim about this paper

Create a free account to see every claim other papers make about this one.

See all claims — free account

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

5 of 9 · the rest aren’t loaded

4 more findings

Create a free account to see every finding of this check.

See all findings — free account

Citations

Cites

Show all 31 references

Research works printed but not linked: 2

  1. Herdman TH, Kamitsuru S, Lopes CT, editors. NANDA-I international nursing diagnoses: definitions & classification, 2024–2026. 13th ed. Thieme. 2024.
  2. Saunders WB, Jiang J, Nguyen T. (2007). Linear and generalized linear mixed models and their applications. New York: Springer

Cited by

See all 48

Metadata

Authors
Fung, T. C. J., Chan, S. L., Lam, C. F. M., Lam, C. Y., Cheng, C. C. W., Lai, M. H., Ho, C. C. J., Au, S. L., Mak, L. Y., Hu, S., Phetrasuwan, S., Granger, J., Yoon, J. M., Malik, G., Moreno, C. C., Kwok, M. H. P., & Lin, C.-C.
Affiliations
  • University of Hong Kong (HK)
  • Chinese University of Hong Kong (HK)
  • Hong Kong Baptist University (HK)
  • National Yang Ming Chiao Tung University (TW)
  • Mahidol University (TH)
  • Ewha Womans University (KR)
  • La Trobe University (AU)
  • Universidad de Navarra (ES)
  • Saint Francis University (HK)
Corresponding author
  • Fung, Tai Chun John
  • Lin, Chia-Chin
Venue
BMC Nursing
Published
2025-07-17
Volume
24
Issue
1
Pages
934-934
ISSN
1472-6955 (ISSN-L)
OpenAlex
W4412490786
Cited by
48
References
31
Citations by year
2026: 43 · 2025: 5
FWCI
30.59
Type
journal article
Language
en
Open access
Licence
Locations
  • BMC Nursing (publishedVersion, cc-by-nc-nd)
  • Research Square (acceptedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by-nc-nd)
  • PubMed (publishedVersion)
  • The HKU Scholars Hub (University of Hong Kong) (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
the HKU Teaching Development Grant (966)
Topics
  • Social Sciences › Education › Simulation-Based Education in Healthcare
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Health Sciences › Medicine › Surgery › Surgical Simulation and Training
Keywords
generative AI, patient simulation, virtual reality simulation, nursing students, clinical competence, cultural awareness, AI readiness, simulation effectiveness, nursing education, immersive simulation, crossover design, simulation-based debriefing, simulation-based feedback

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (gpt-6-sol).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Effects of generative artificial intelligence (GenAI) patient simulation on perceived clinical competency among global nursing undergraduates: a cross-over randomised controlled trial. https://app.cochat.ai/papers/10.1186/s12912-025-03492-0
The paper
Fung, T. C. J., Chan, S. L., Lam, C. F. M., Lam, C. Y., Cheng, C. C. W., Lai, M. H., Ho, C. C. J., Au, S. L., Mak, L. Y., Hu, S., Phetrasuwan, S., Granger, J., Yoon, J. M., Malik, G., Moreno, C. C., Kwok, M. H. P., & Lin, C.-C. (2025). Effects of generative artificial intelligence (GenAI) patient simulation on perceived clinical competency among global nursing undergraduates: a cross-over randomised controlled trial. BMC Nursing. https://doi.org/10.1186/s12912-025-03492-0

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.