Agentic education · Learning science

Actionable companion · Feedback & scaffolding

Learning with agency: Immersive Virtual Reality and AI (Generative Pretrained Transformer) to Enhance Student Preparedness for Objective Structured Clinical Examinations: Mixed Methods Study

AI-assisted editorial implementation guide, separate from the original research. Proposed actions are not claims or recommendations attributed to the source authors. No independent peer review of this guide is asserted.

Read original paperSearch paper agentCC BY 4.0

Evidence and context

Title and abstract screening; stage labels describe reported settings, not verified numerical ages. Design labels require full-text appraisal. Reported stage(s): Secondary school. Health-professions learning must be distinguished from K–12 instruction.

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

Abstract Background Immersive virtual reality (VR) and artificial intelligence have been used to determine whether a simulated clinical exam setting can reduce anxiety in first-year occupational therapy students preparing for objective structured clinical examinations (OSCEs). Test anxiety is common among postsecondary students, leading to negative outcomes such as increased dropout risk, lower grades, and limited employment opportunities. Students unfamiliar with specific testing environments are particularly prone to anxiety. VR simulations of OSCEs may allow students to become familiar with the exam setting and reduce anxiety. Objective This study aimed to assess the efficacy of a VR simulation depicting clinical settings to reduce student anxiety about a clinical exam while gathering perspectives on their first-year coursework experiences to better understand their learning environment. Methods An experimental, nonrandomized controlled trial compared state anxiety, trait test anxiety, and OSCE grades in 2 groups of first-year occupational therapy students analyzed using independent t tests (2-tailed). Group 1 (NoVR) was not exposed to the VR simulation and acted as a control group for group 2 (YesVR), who were exposed to the VR simulation. The VR used artificial intelligence in the form of a generative pretrained transformer to generate responses from virtual patients as students interacted with them in natural language. Self-reported psychometric scales measured anxiety levels 3 days before the OSCE. YesVR students completed perceived preparation surveys at 2 time points—3 weeks and 3 days before the OSCE—analyzed using dependent t tests. Semistructured interviews and focus groups were conducted within 1 week after the OSCE. Student perspectives on their classes and VR experiences were summarized using interpretative thematic analysis. Results In total, 60 students—32 (53%) in the NoVR group and 28 (47%) in the YesVR group—participated in the study, and the YesVR group showed a significant reduction in state anxiety (t58=3.96; P<.001; Cohen d=1.02). The mean difference was 11.96 units (95% CI 5.92-18.01). Trait test anxiety and OSCE scores remained static between groups. There was an increase in all perceived preparedness variables in the YesVR group. In total, 42% (25/60) of the participants took part in interviews and focus groups, providing major themes regarding factors that affect OSCE performance, including student experience and background, feedback and support, fear of unknown, self-consciousness, and knowledge of the exam environment. Conclusions Intolerance of uncertainty may lead students to interpret ambiguous exam situations as overly precarious. Findings suggest that VR simulation was associated with reduced state anxiety, although results from this small, nonrandomized sample should be interpreted cautiously. Qualitative data indicated that VR helped students gain familiarity with clinical exam settings, potentially decreasing uncertainty-based anxiety. Future research with larger or randomized samples is needed to confirm these findings and explore advanced VR tools offering feedback to enhance learning. Keywords: virtual reality, head-mounted display, immersive technology, artificial intelligence, generative pretrained transformer, occupational therapy, objective structured clinical examination, simulation, psychology, anxiety

What kind of evidence is this?

Supporting AI learning science · Randomized study reported

Stage: Secondary school. Screening labels describe reported context and study-design language. They are not a risk-of-bias rating or proof of effectiveness for an age band.

Study methods · source passage

This investigation was a mixed, cross-sectional, nonrandomized controlled trial involving 2 groups of participants, each comprising first-year OT students from the same class. This investigation attempted to replicate the difference in mean state anxiety between 2 groups of participants: students not exposed to a VR simulation (NoVR group), who acted as a control group for students who were exposed to VR (YesVR group). The University of Alberta Department of Occupational Therapy program had eased remote learning practice, which was established between the years of 2020 and 2022 in response to COVID-19 restrictions. First-year OT coursework remained consistent in terms of faculty infrastructure, course content, curricular sequencing, and instructors since the study by Concannon et al [1].

Limitations and uncertainty · source passage

This investigation did not use a double-blind, randomized controlled trial; thus, causation of immersive VR’s ability to reduce student anxiety cannot be inferred. Conducting a randomized controlled trial could have been challenging as it may have disrupted the student study routines while potentially segregating them from their study partners. In addition, this investigation could not match student responses to demographic factors such as sex. However, this study was able to test students from the same academic year, potentially reducing group differences due to student admission requirements.

Design the system before the pilot

Use this study to inform a learning mechanism or implementation question. It is not direct evidence that autonomous agents improve learning. Keep the proposed agent behavior separate from what the source actually tested.

  • Give feedback on the learner’s reasoning, then fade hints. Record whether the learner can complete the next task without that scaffold.
  • Use common rubrics, blind scoring where feasible and a fresh unaided reasoning task. Document permissible assistance and avoid treating AI-detector scores as proof of misconduct.

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. Ask learners to attempt a problem unaided, compare an agent hint, explain a revision and verify the final reasoning against a trusted source. Make the permitted use explicit for each assignment. 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. Measure unaided transfer and delayed retention, calibration of confidence and the ability to identify an incorrect AI explanation. Record whether help-seeking becomes answer copying. 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

Shaniff Esmail; Brendan Concannon. Immersive Virtual Reality and AI (Generative Pretrained Transformer) to Enhance Student Preparedness for Objective Structured Clinical Examinations: Mixed Methods Study. JMIR Serious Games (2025-04-30). https://doi.org/10.2196/69428

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.