EUVIMEDEUVIMED entdecken
Open Access

Coexistence of AI Nurse and AI-Simulated Patient in Nursing Education Using a Bidirectional Fine-Tuning Pipeline: Development and Content Analysis Study

Takeshi Koike, Yukie Majima

JMIR Biomedical Engineering · 06.11.2026 · 11 · e100778-e100778

DOI: 10.2196/100778 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JMIR Biomedical Engineering, online erschienen am 06.11.2026. Verfasst von Takeshi Koike und 1 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Nursing, Seirei Christopher University, 3453 Mikatahara-cho, Chuo-ku, Hamamatsu, Japan, 81 053-439-1401. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Simulated patient systems are essential in nursing education but face actor scarcity, instructor burden, cost, and disrupted continuity where in-person simulation cannot be sustained. Existing large language model (LLM)–based systems address these issues but treat the dialogic partner—the AI nurse—as a static prompt or unspecialized model, compromising data collection quality and pedagogical applicability.

Objective

We report (1) the construction of 2 specialized fine-tuned models, NURSE-ONE (AI nurse) and PATIENT-ONE (AI-simulated patient), via a 5-step bidirectional fine-tuning pipeline; (2) their evaluation using Berelson content analysis validated by independent human coders; (3) an exploratory third-party evaluation by nursing faculty; and (4) the design of a coexistence simulation ecosystem supporting 3 operating modes, including offline disaster preparedness applicability.

Methods

On a single consumer-grade graphics processing unit (NVIDIA RTX 4090; 24 GB video random access memory), the multimodal base model gemma4-E4B-it was fine-tuned via low-rank adaptation in five steps: (1) a 251-scenario base from 29 institutionally authored nursing care plans and 20 items from the 115th Japanese National Nursing Examination; (2) a provisional dialogue system (AutoGen v18, maxmsg=25) to collect training dialogues; (3) NURSE-ONE fine-tuning across 3 training volume conditions (245, 735, and 1225 cases); (4) 4-condition Berelson comparison; and (5) PATIENT-ONE fine-tuning on NURSE-ONE–generated dialogues with a 3-condition comparison. Interrater reliability was confirmed by 2 independent nursing experts (196 blinded utterances, κ=0.770) and corroborated by 2 LLM raters (κ=0.742). Ten nursing faculty evaluated 3 coexistence modes in a working web user interface (21-item rubric; item-level content validity index=1.00).

Results

Four-condition Berelson analysis ( χ 2 15 =42.0, P

Schlagwörter

Stichwörter der Autor:innen

AI nurseBerelson content analysisLoRA fine-tuningbidirectional fine-tuningdisaster preparedness educationfunctional asymmetrylarge language modellow-rank adaptationnursing educationsimulated patientsimulation ecosystem

Autor:innen und Institutionen

  • Faculty of Nursing, Seirei Christopher University, 3453 Mikatahara-cho, Chuo-ku, Hamamatsu, Japan, 81 053-439-1401.
  • Graduate School of Informatics, Osaka Metropolitan University, Osaka, Japan.

Zitieren

APA

Koike, T., & Majima, Y. (2026). Coexistence of AI Nurse and AI-Simulated Patient in Nursing Education Using a Bidirectional Fine-Tuning Pipeline: Development and Content Analysis Study. JMIR Biomedical Engineering, 11, e100778-e100778. https://doi.org/10.2196/100778

Vancouver

Koike T, Majima Y. Coexistence of AI Nurse and AI-Simulated Patient in Nursing Education Using a Bidirectional Fine-Tuning Pipeline: Development and Content Analysis Study. JMIR Biomedical Engineering. 2026;11:e100778-e100778. doi:10.2196/100778

BibTeX
@article{Koike2026,
  author = {Koike, Takeshi and Majima, Yukie},
  title = {Coexistence of AI Nurse and AI-Simulated Patient in Nursing Education Using a Bidirectional Fine-Tuning Pipeline: Development and Content Analysis Study},
  journal = {JMIR Biomedical Engineering},
  year = {2026},
  volume = {11},
  pages = {e100778--e100778},
  doi = {10.2196/100778}
}
Kostenlos starten →