Generative AI · Education leadership

Actionable companion · Assessment and evidence of learning

From evidence to district action: Effects of ChatGPT-generated immediate feedback integrated into VR-based OSCEs on nursing students’ performance: a randomized crossover study

AI-assisted editorial implementation guide. The district actions are proposed applications, not findings or recommendations attributed to the original authors. No additional peer review is asserted.

Read original paperSearch paper agentCC BY 4.0

Evidence and context

Health-professions education context: test transfer to K–12 rather than assuming it.

Original authors’ abstract, reproduced under the linked source license:

Abstract Background The Objective Structured Clinical Examination (OSCE) is a gold-standard assessment in nursing education, yet traditional and virtual reality (VR) formats often lack timely, individualized feedback, potentially limiting gains in higher-order competencies such as communication and decision-making. Advances in artificial intelligence (AI), particularly ChatGPT, offer opportunities to address this gap. To evaluate the impact of ChatGPT-generated immediate feedback integrated into VR-based OSCE stations on nursing students’ communication performance, clinical decision-making accuracy, and related learning outcomes. Methods A randomized, two-period crossover trial was conducted among 65 final-year nursing students at a tertiary teaching hospital in China between March and May 2025. Participants completed two matched OSCE stations under VR-only and VR + ChatGPT conditions, with a one-week washout period between the two study phases. Primary outcomes included OSCE communication scores, clinical decision-making accuracy, and task completion time. Secondary outcomes comprised learning satisfaction, acceptance of AI-assisted feedback, academic and communication self-efficacy, reflection quality, and cognitive workload. Data were analyzed using paired statistical comparisons and linear mixed-effects models adjusting for sequence and period effects. Results Compared with VR-only, VR + ChatGPT significantly improved communication scores (mean difference [MD] = 3.38, 95% CI: 2.12–4.64, P < 0.001, Cohen’s d = 0.63) and decision accuracy (MD = 3.91%, 95% CI: 2.09–5.72, P < 0.001, Cohen’s d = 0.49), while reducing completion time (MD = − 0.78 min, 95% CI: − 1.12 to − 0.44, P < 0.001, Cohen’s d = − 0.62). VR + ChatGPT also yielded higher learning satisfaction (MD = 0.31, P < 0.001), greater reflection quality (MD = 0.62, P < 0.001), lower cognitive workload (MD = − 5.7, P = 0.001), and significant gains in academic and communication self-efficacy (both P < 0.001). No severe adverse events occurred. Effects were consistent across subgroups defined by prior VR experience and digital literacy. Conclusions Integrating ChatGPT-generated immediate feedback into VR OSCE scenarios significantly enhances nursing students’ communication and decision-making performance, accelerates skill acquisition, and reduces cognitive strain, without compromising safety. Clinical trial number Not applicable. Supplementary Information The online version contains supplementary material available at 10.1186/s12912-026-04633-9. Keywords: ChatGPT, Virtual reality, Objective structured clinical examination, Communication skills, Nursing education, Immediate feedback, Artificial intelligence-assisted learning

A 90-day district pilot

  1. Days 1–15 · Appraise. Have the curriculum lead and a teacher read the methods and limitations. Record the study design, sample, comparator, outcomes and evidence gaps. Define a local question that the study can help inform.
  2. Days 16–30 · Design. Redesign one low-stakes assessment: require a first attempt, an AI-assisted revision, a source-check log and a short oral explanation. Use the same rubric for the comparison task. Name an accountable owner and set the baseline, success threshold and budget before implementation.
  3. Days 31–60 · Test. Start with a small voluntary cohort, preserve an accessible non-AI route and require teacher review. Use synthetic or de-identified examples; approve data handling and tool terms through district processes.
  4. Days 61–90 · Decide. Blind-score reasoning, factual accuracy and unaided transfer on a fresh task. Record suspected misconduct separately from demonstrated evidence. Compare with baseline, document uncertainty and stop or revise if learning worsens, access is unequal or critical errors persist.

The board decision brief

Report the learning problem, evidence quality, participating population, total cost including review time, measured benefit, errors, access differences and remaining uncertainties. Make a dated recommendation to stop, revise or expand. A positive perception survey alone does not establish learning improvement.

Attribution and reuse

Xinjia Dai; Yaodong Gong; Ling-Yun Ma. Effects of ChatGPT-generated immediate feedback integrated into VR-based OSCEs on nursing students’ performance: a randomized crossover study. BMC Nursing (2026-04-13). https://doi.org/10.1186/s12912-026-04633-9

Companion prepared 2026-10-30. Original authorship and DOI are preserved. The abstract is an attributed source extract; the implementation plan is new AI-assisted editorial material, offered under the same CC BY 4.0 license. This guide has not undergone independent peer review.