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 accessPublished 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
Cites
Statistics
Verification
Claims the paper makes
2 Valid · 5 Not valid · 3 Not checked · 107 Own results and interpretations
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Students exposed to GenAI-generated cases exhibit improved clinical reasoning compared to those trained through traditional methods [19].”
§ Effects of generative artificial intelligence (GenAI) patient simulation on perceived clinical competency among global nursing undergraduates: a cross-over randomised controlled trial > Background
What the sources say
- Could not verifycites [19] Krive J, Isola M, Chang L, Patel T, Anderson M, Sreedhar R. Grounded in reality: artificial intelligence in medical education. JAMIA Open. 2023;6(2):ooad037. 37273962 PMC10234762 sourceExperimental — accuracy not yet measured
The Methods (Design; page unavailable) describe assignments based on simulated patient-care scenarios, and the Abstract (Results; page unavailable) reports improved AI knowledge and skills. Neither passage says the cases were GenAI-generated or reports a comparison with traditional training on clinical reasoning. Searches for GenAI-generated cases and a traditional-methods comparison found no supporting passage in our copy. (LLM, conf=0.76)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“pilot studies have demonstrated that integrating 360° VR simulation with structured debriefing through learning management systems (LMS) can enhance students’ clinical competence and confidence in decision-making [9, 10].”
§ Effects of generative artificial intelligence (GenAI) patient simulation on perceived clinical competency among global nursing undergraduates: a cross-over randomised controlled trial > Background
What the sources say
- Partly supportedcites [9] Alammary MA, Halliday L, Konstantinidis ST. 360-degree virtual reality utilising head-mounted devices in undergraduate nursing and midwifery education: A scoping review. Virtual Worlds. 2023;2(4):396–421. sourceExperimental — accuracy not yet measured
The Discussion (section 6; page unavailable) reports that structured debriefing can improve learning outcomes and that computer debriefing improved midwifery students’ self-efficacy, knowledge, and nontechnical skills. It does not report pilot studies combining 360° VR with structured debriefing through an LMS, or establish improvements in clinical competence and confidence specifically in decision-making. Section 5.3.7 also notes that many reviewed studies did not specify their debriefing method. (LLM, conf=0.84)
- Not checked — no full text of the sourcecites [10] Lee E, Baek G. Development and effects of a virtual reality simulation nursing education program combined with clinical practice based on an information processing model. CIN: Computers Inf Nurs. 2023;41(12):1016–25. 37647622 source
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Both groups demonstrated significant within-group improvements in perceived clinical competence at T1 and T2.”
§ Effects of generative artificial intelligence (GenAI) patient simulation on perceived clinical competency among global nursing undergraduates: a cross-over randomised controlled trial > Results > Effects of the interventions on CCQ
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“most participants (72.7%, n = 32) strongly agreed that they were confident in using evidence-based practice to provide nursing care.”
§ Effects of generative artificial intelligence (GenAI) patient simulation on perceived clinical competency among global nursing undergraduates: a cross-over randomised controlled trial > Results > Effect of the interventions on SET-M
plainn = 32- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Both groups demonstrated improvements in cultural awareness.”
§ Effects of generative artificial intelligence (GenAI) patient simulation on perceived clinical competency among global nursing undergraduates: a cross-over randomised controlled trial > Results > Effects of the interventions on CAS
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
49 more claims
Create a free account to see all 117 claims and every source verdict.
- It may state two separate claims as one. 39
- Probably not a substantial claim. 36
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The CCQ showed significant improvement in one study (Group B improved by 47.68 points; P=.02) [38].”
From AI-Powered Simulation for Nursing Education: Mixed Methods Systematic Review (2026) · cites this paper as [38]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Concerns regarding realism, bias, and long-term transfer to practice have also been reported [4,8,9].”
From Artificial Intelligence-Based Adaptive Simulation Integrated With a Workforce Decision-Support System to Improve Simulated Nursing Leadership Performance: A Randomized Controlled Study (2026) · cites this paper as [9]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Studies involving AI-supported virtual, narrative, and generative simulations have reported improvements in self-efficacy, communication knowledge, perceived competence, diagnostic reasoning, and clinical decision-making.”
From Artificial Intelligence-Based Adaptive Simulation Integrated With a Workforce Decision-Support System to Improve Simulated Nursing Leadership Performance: A Randomized Controlled Study (2026) · cites this paper as [9]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“However, findings vary across outcomes, with some studies reporting stronger effects for structured cognitive tasks than for complex interpersonal or psychomotor performance.”
From Artificial Intelligence-Based Adaptive Simulation Integrated With a Workforce Decision-Support System to Improve Simulated Nursing Leadership Performance: A Randomized Controlled Study (2026) · cites this paper as [9]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“These outcomes are particularly evident when learners receive real-time feedback and repeated practice within psychologically safe learning environments [4,8-11].”
From Artificial Intelligence-Based Adaptive Simulation Integrated With a Workforce Decision-Support System to Improve Simulated Nursing Leadership Performance: A Randomized Controlled Study (2026) · cites this paper as [9]
Experimental — accuracy not yet measured
1 more claim about this paper
Create a free account to see every claim other papers make about this one.
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.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
“nursing professional behaviours (NP; 16 items, score range: 16–90)”
§ Effects of generative artificial intelligence (GenAI) patient simulation on perceived clinical competency among global nursing undergraduates: a cross-over randomised controlled trial > Methods > Data collection
Reported 90 · recomputed 80
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
“| Female | 37 (61.7) | 17 (77.3) | 20 (90.9) | |”
§ Effects of generative artificial intelligence (GenAI) patient simulation on perceived clinical competency among global nursing undergraduates: a cross-over randomised controlled trial > Methods > Data analysis
Reported 61.7 · recomputed 84.090909
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Effects of generative artificial intelligence (GenAI) patient simulation on perceived clinical competency among global nursing undergraduates: a cross-over randomised controlled trial > Results > Descriptive results
“Regarding the year of study, most participants were in Year 2 (34.1%), with no significant difference between groups (P = 0.627).”
§ Effects of generative artificial intelligence (GenAI) patient simulation on perceived clinical competency among global nursing undergraduates: a cross-over randomised controlled trial > Methods > Data analysis
“| Year 2 | 15 (34.1) | 6 (27.3) | 9 (40.9) | | | Year 3 | 27 (61.4) | 15 (68.2) | 12 (54.5) | |”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
“| Male | 7 (38.3) | 5 (22.7) | 2 (9.1) | |”
§ Effects of generative artificial intelligence (GenAI) patient simulation on perceived clinical competency among global nursing undergraduates: a cross-over randomised controlled trial > Methods > Data analysis
Reported 38.3 · recomputed 15.909091
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
“| No | 8 (36.4) | 8 (36.4) | 8 (36.4) | |”
§ Effects of generative artificial intelligence (GenAI) patient simulation on perceived clinical competency among global nursing undergraduates: a cross-over randomised controlled trial > Methods > Data analysis
Reported 36.4 · recomputed 18.181818
4 more findings
Create a free account to see every finding of this check.
Citations
Cites
Addressing bias in artificial intelligence in health care
Parikh, R. B., Teeple, S., & Navathe, A. S. (2019) · JAMA · doi:10.1001/jama.2019.18058 · Cited by 764 · cited 2×
“A significant between-group difference was noted (12.09, 95% CI [4.43, 19.75], p = 0.003), with Group B demonstrating greater improvement in AI readiness.”
InfluentialBias in medical AI: Implications for clinical decision-making
Cross, J. L., Choma, M. A., & Onofrey, J. A. (2024) · PLOS Digital Health · doi:10.1371/journal.pdig.0000651 · Cited by 607
Generative AI in Medicine and Healthcare: Promises, Opportunities and Challenges
Zhang, P., & Kamel Boulos, M. N. (2023) · Future Internet · doi:10.3390/fi15090286 · Cited by 411 · cited 1×
“This aligns with existing literature, which also supports the effectiveness of per-sonalised learning in enhancing clinical competence across both generalist and specialist nursing practice [33].”
Karaca, O., Çalışkan, S. A., & Demir, K. (2021) · BMC Medical Education · doi:10.1186/s12909-021-02546-6 · Cited by 377 · cited 2×
“It requires participants to rate their self-assessment on a 5-point Likert scale (ranging from 1 = ‘strongly disagree’ to 5 = ‘strongly agree’) on 22 statements regarding their AI readiness [25].”
The 3D Model of Debriefing: Defusing, Discovering, and Deepening
Zigmont, J. J., Kappus, L. J., & Sudikoff, S. N. (2011) · Seminars in Perinatology · doi:10.1053/j.semperi.2011.01.003 · Cited by 345 · cited 1×
“…participated in the same structured debrThey participated in the same structured debrThey participated in the same structured debriefing protocol utilizing the 3D debriefing model [29], using the same set of debrief questions and facilitated by trained staff to ensure consistency across all sites.”
Predicted Influences of Artificial Intelligence on Nursing Education: Scoping Review
Buchanan, C., Howitt, M. L., Wilson, R., Booth, R. G., Risling, T., & Bamford, M. (2021) · JMIR Nursing · doi:10.2196/23933 · Cited by 326 · cited 1×
“These findings advocate for urgent curricular reform to prepare nurses for AI practice, highlighting the need for a balanced approach that leverages AI’s potential while mitigating its risks [16, 17].”
Application Scenarios for Artificial Intelligence in Nursing Care: Rapid Review
Seibert, K., Domhoff, D., Bruch, D., Schulte-Althoff, M., Fürstenau, D., Biessmann, F., & Wolf-Ostermann, K. (2021) · Journal of Medical Internet Research · doi:10.2196/26522 · Cited by 314 · cited 1×
“The literature further emphasizes the importance of stakeholder engagement and a comprehensive understanding of AI’s clinical role [12].”
Nazar, M., Alam, M. M., Yafi, E., & Su'ud, M. M. (2021) · IEEE Access · doi:10.1109/access.2021.3127881 · Cited by 312 · cited 1×
“These findings advocate for urgent curricular reform to prepare nurses for AI practice, highlighting the need for a balanced approach that leverages AI’s potential while mitigating its risks [16, 17].”
Mirchi, N., Bissonnette, V., Yilmaz, R., Ledwos, N., Winkler-Schwartz, A., & Del Maestro, R. F. (2020) · PLOS ONE · doi:10.1371/journal.pone.0229596 · Cited by 296 · cited 1×
“Simulation-based GenAI learning has been shown to enhance AI readiness and reinforce core nursing concepts [18].”
Leighton, K., Ravert, P., Mudra, V., & Macintosh, C. (2015) · Nursing Education Perspectives · doi:10.5480/15-1671 · Cited by 295 · cited 2×
“Cronbach’s alpha for the overall SET-M was 0.94, with the reliability of each domain ranging from 0.83 to 0.91 [27].”
Influential
Research works printed but not linked: 2
- Herdman TH, Kamitsuru S, Lopes CT, editors. NANDA-I international nursing diagnoses: definitions & classification, 2024–2026. 13th ed. Thieme. 2024.
- Saunders WB, Jiang J, Nguyen T. (2007). Linear and generalized linear mixed models and their applications. New York: Springer
Cited by
He, H., Xu, X., Li, S. E., Bueno-Vesga, J. A., Duan, Y., & Gu, Y. (2026) · International Journal of Educational Technology in Higher Education · doi:10.1186/s41239-026-00587-9 · Cited by 10
Nasirun, H., Mulyono, S., Hapsari, A. W. D., Wiradinata, H. H., & Ratu, M. (2026) · Nurse Education in Practice · doi:10.1016/j.nepr.2026.104847 · Cited by 21
Almagharbeh, W. T., Ahmed, W. R., Alfanash, H. A., Alnawafleh, K. A., & Tajoury, O. H. (2026) · Journal of Professional Nursing · doi:10.1016/j.profnurs.2025.12.010 · Cited by 7
Lai, N. M., Lim, Y. S., Thein, W. M., Bhargava, P., Thomas, P., & Ong, Q. C. (2026) · JMIR Medical Education · doi:10.2196/88933 · Cited by 13
“Next, we included 7 crossover trials [47,48,53,66,74,80, 81], which may have additional concerns in their study design that we have not adequately addressed, because the newly established ROBUST-RCT tool has not been expanded to cover crossover design [29].”
Yan, X., Wang, Z., Chen, O., & Guo, Y. (2026) · Nurse Education Today · doi:10.1016/j.nedt.2026.107217 · Cited by 4
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
- ORCID
- Venue
- BMC Nursing
- Published
- 2025-07-17
- Volume
- 24
- Issue
- 1
- Pages
- 934-934
- ISSN
- 1472-6955 (ISSN-L)
- PMC
- PMC12272990
- OpenAlex
- W4412490786
- Cited by
- 48
- References
- 31
- Citations by year
- 2026: 43 · 2025: 5
- FWCI
- 30.59
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by-nc-nd
- creativecommons.org/licenses/by-nc-nd/4.0 (tdm)
- creativecommons.org/licenses/by-nc-nd/4.0 (vor)
- 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.