EUVIMEDOdkrijte EUVIMED
Crossref

Large Language Model–Powered AI-Assisted Simulated Patient for Nursing Education: Quasi-Experimental Study

Max Chun Ming Chan, Danny Chun Kit Hung, Tyrone Tai-On Kwok, Janet Yuen Ha Wong

JMIR Nursing · 2026-11-19 · 9 · e98543-e98543

DOI: 10.2196/98543 ↗

At a glance

Journal article in JMIR Nursing, published online on 2026-11-19. Written by Max Chun Ming Chan and 3 co-authors. 35 references.

PovzetekBibliografski podatkiCiteRelated studies

Abstract (original language)

Background

Large language model (LLM)–powered virtual patient systems are gaining popularity in nursing education but also face persistent challenges, such as hallucinations and role inconsistency.

Objective

This paper reports the model architecture design, technical considerations, implementation challenges, and evaluation of an LLM-powered AI-assisted simulated-patient system integrated into a nursing triage simulation game.

Methods

The system integrated a Unity-based game client, with GPT-4o hosted through Microsoft AI Foundry to support real-time simulated-patient dialogue in Traditional Chinese using Cantonese syntax. This developmental study comprised exploratory model selection, formative student feedback–informed enhancement from Version 1 to Version 2, development-stage script-fidelity evaluation, and evaluation of system usability and the Net Promoter Score in 2 tutorial cohorts of nursing students.

Results

Key technical contributions include a layered hallucination mitigation architecture that combines grounded prompt inclusion, few-shot conversational exemplars, negative role constraints, and calibrated model parameters. In the predefined script-fidelity evaluation, script-inconsistent responses occurred in 78 of 125 (62.4%) Version 1 outputs and 21 of 125 (16.8%) Version 2 outputs—an absolute difference of 45.6 percentage points. The implementation process also addresses stateless API memory management, cloud-based safety filter calibration for domain-specific clinical prompts, and prompt engineering strategies to prevent role drift and hidden scenario information leakage. GPT-4o was selected as the production model through exploratory development testing that considered script consistency, Cantonese-language suitability, response latency, technical reliability, deployment feasibility, cost considerations, and Unity integration compatibility; 45 of 50 (90%) assessed GPT-4o responses were rated fully script-consistent.

Conclusions

This study demonstrates the development and real-world tutorial deployment of a Cantonese-language, LLM-powered simulated-patient system for nursing triage education. Integrating formative student feedback with structured technical debugging enabled iterative refinement of dialogue fidelity, role consistency, protected-information handling, and game interaction functions. The resulting Version 2 system provides a practical, contextually tailored approach to supporting scalable simulated-patient dialogue in nursing education.

Cite

APA

Chan, M. C. M., Hung, D. C. K., Kwok, T. T., & Wong, J. Y. H. (2026). Large Language Model–Powered AI-Assisted Simulated Patient for Nursing Education: Quasi-Experimental Study. JMIR Nursing, 9, e98543-e98543. https://doi.org/10.2196/98543

Vancouver

Chan MCM, Hung DCK, Kwok TT, Wong JYH. Large Language Model–Powered AI-Assisted Simulated Patient for Nursing Education: Quasi-Experimental Study. JMIR Nursing. 2026;9:e98543-e98543. doi:10.2196/98543

BibTeX
@article{Chan2026,
  author = {Chan, Max Chun Ming and Hung, Danny Chun Kit and Kwok, Tyrone Tai-On and Wong, Janet Yuen Ha},
  title = {Large Language Model–Powered AI-Assisted Simulated Patient for Nursing Education: Quasi-Experimental Study},
  journal = {JMIR Nursing},
  year = {2026},
  volume = {9},
  pages = {e98543--e98543},
  doi = {10.2196/98543}
}
Start for free →