IMMERSIVE VIRTUAL REALITY AND ARTIFICIAL INTELLIGENCE FOR ENHANCING STUDENT PREPAREDNESS FOR CLINICAL EXAMS
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Introduction: Test anxiety is a common issue among post-secondary students, leading to negative consequences such as the increased risk of dropout, lower grades, and limited employment opportunities.Students unfamiliar with the test-taking environment are more likely to have test anxiety.This study aimed to explore virtual reality (VR) and artificial intelligence (AI) as potential solutions to reduce test anxiety in health science students preparing for clinical exams.By utilizing an AI-powered virtual testing environment with interactive virtual patients, students acted as medical professionals in a simulated clinical setting, allowing them to familiarize themselves with the environment and potentially reduce their anxiety levels.The study utilized AI in the form of a generative pre-trained transformer (GPT) to generate responses from virtual patients.System was evaluated on its ability to reduce test anxiety.Objective: To assess the efficacy of a VR simulation of a clinical setting in reducing student anxiety for a clinical exam and gather student perspectives on their VR simulation and coursework experiences to better understand their learning environment.Methods: First-year health science students were invited to participate in a VR session that took place three-days before their clinical exam.Students exposed to VR (YesVR) and those who opted out (NoVR) had their anxiety levels compared to one another using the State Trait Anxiety Inventory (STAI) and Test Anxiety Inventory (TAI).Immersive VR simulation included history-taking and cognitive assessment modules, allowing students to communicate with virtual patients in natural language in a virtual clinic.Virtual patient responses were generated by GPT, fine-tuned with transfer learning techniques based on real-world student and standardized patient video recordings.After completing their clinical exams, students were invited to participate in semi-structured interviews and focus groups.Results: A total of 108 students participated in the quantitative aspects of the study (mean aged 24.53 years, SD 2.64): 61 for the NoVR group (mean aged 24.52 years, SD 2.42) and 47 for the YesVR group (mean aged 24.54 years, SD 2.93).There was a significant difference in state anxiety scores between groups, with NoVR showing greater anxiety scores (mean 51.69, SD 11.87) than YesVR (mean 39.79, SD 12.21) (t106=5.10,P=<.001, Cohen d = 0.99).The mean difference was 11.90 units (95% CI 7. 28-16.53).A total of 25 students participated in the interviews and focus groups -16 from interviews and 9 from focus groups.The major themes emerging from focus groups and interviews were overall student background, exam feedback, fear of the unknown, self-consciousness, and the exam environment.Conclusion: This study highlights the potential of AI-enhanced VR as an effective tool for reducing test anxiety and increasing student familiarity with clinical exam environments.The results suggest that VR may reduce ambiguity and uncertainty, which are key contributors to test anxiety.The findings provide valuable insights into the potential of VR and AI in addressing test anxiety.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it