EUVIMEDObjevte EUVIMED
Open access

Integrating a Large Language Model to Streamline Nursing Handover Documentation Across Multiple Hospitals in Taiwan: Development and Implementation Study

Integration eines Large Language Model zur Vereinfachung der Dokumentation von Pflegeübergaben in mehreren Krankenhäusern in Taiwan: Entwicklungs- und Implementierungsstudie

Ray-Jade Chen iD, Mai-Szu Wu iD, Lung-Wen Tsai iD, Shy-Shin Chang iD, Shu-Tai Shen Hsiao iD, Yu-Sheng Lo iD

Journal of Medical Internet Research · 2026-03-12 · 28 · e81604

DOI: 10.2196/81604 ↗

Auf einen Blick

Die Integration eines LLM in ein Pflegedokumentationssystem war in 3 Krankenhäusern mit kürzeren Dokumentationszeiten pro Patient:in verbunden. Die Autor:innen berichten zudem einen positiven Nettoarbeitswert.

Fragestellung

Untersucht wurde, ob die Integration eines LLM in ein pflegerisches Informationssystem die Zeit und den Aufwand für die Dokumentation von Pflegeübergaben reduziert.

Methode

Entwicklungs- und Implementierungsstudie mit Analyse von NIS-Logdaten vor und nach der LLM-Implementierung in 3 Krankenhäusern in Taiwan.

Ergebnisse

Vor Integration lag die mittlere Bearbeitungszeit pro Patient:in bei 3,45 (SD 3,82) bis 4,32 (SD 4,48) Minuten. Nach Integration bei 1,17 (SD 1,86) bis 2,54 (SD 2,82) Minuten; geschätzte Einsparung 474-981 Stunden pro Monat.

Einschränkungen

Prompts waren eingeschränkt; Pflegefachpersonen mussten die Ausgabe überprüfen. Weitere Logdaten zu Reliabilität und Überarbeitungen sollen erhoben werden.

Schlussfolgerung der Autor:innen

Die Integration eines LLM in ein NIS erzeugte Pflegeübergabedokumente ohne Änderung der bestehenden Abläufe; sie war mit kürzerer Dokumentationszeit und positivem Nettoarbeitswert verbunden.

Kernaussagen

  • Dokumentationszeit pro Patient:in war nach LLM-Integration geringer.
  • Geschätzte Einsparung: 474-981 Stunden pro Monat.
  • Nurse verification war erforderlich, um Halluzinationen zu begrenzen.

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

At a glance

Journal article in Journal of Medical Internet Research, published online on 2026-03-12. Written by Ray-Jade Chen and 5 co-authors. Institution: Department of Surgery, School of Medicine, College of Medicine, Taipei Medical University, Taipei, Taiwan. Major MEDLINE topics: Large Language Models, Patient Handoff, Documentation. Cited 15 times so far (Crossref); 49 references. The full text is freely available in PubMed Central.

Auf einen BlickAbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Background

The global nursing shortage, exacerbated by heavy workloads and high turnover rates associated with the COVID-19 pandemic, continues to undermine care quality and nurse well-being. Although digital health technologies have enhanced coordination, improved communication, and reduced clinical errors in nursing practice, they have also increased nurses’ documentation burden. Advances in large language models (LLMs) and other generative artificial intelligence (GenAI) tools facilitate the generation of accurate reports from electronic medical records (EMRs), thereby streamlining documentation workflows, saving time, and reducing nurses’ workloads. Accordingly, integrating LLMs into electronic nursing documentation systems warrants further exploration.

Objective

This study examines the integration of an LLM into an in-house nursing information system (NIS) implemented across 3 hospitals in Taiwan to reduce the time and effort required for nursing handover documentation and to preliminarily assess the operational and economic implications of GenAI-assisted workflows.

Methods

A multidisciplinary team of nursing specialists and information technology experts at Taipei Medical University (TMU) restructured the organization’s existing nursing handover documentation process to facilitate interaction with the LLM. The team also developed prompt-based interfaces to automatically generate section-specific content for the nursing handover document. The LLM-integrated NIS was subsequently deployed across 3 hospitals in Taiwan: Taipei Medical University Hospital (TMUH), Wan Fang Hospital (WFH), and Shuang Ho Hospital (SHH). We then extracted and analyzed NIS log data to compare documentation times before and after LLM implementation, thereby quantifying time savings.

Results

Integration of the LLM into nursing handover documentation was associated with shorter per-patient documentation time in routine clinical use across TMUH, WFH, and SHH. Based on preintegration NIS logs (September 2024), the average handover document completion time per patient ranged from 3.45 (SD 3.82) to 4.32 (SD 4.48) minutes across hospitals and shifts, providing a preliminary baseline for subsequent comparisons. In postintegration NIS logs (October-December 2024), the overall handover document completion time per patient (mean) was substantially lower, ranging from 1.17 (SD 1.86) to 2.54 (SD 2.82) minutes across hospitals and shifts. Using monthly patient volume to estimate time savings, 113-273, 160-314, and 198-391 hours were saved per month at TMUH, WFH, and SHH, respectively, corresponding to aggregate savings of 474-981 hours per month across hospitals during the study period.

Conclusions

We integrated an LLM into an NIS to generate nursing handover documents without altering existing workflows. Across 3 hospitals within TMU’s health system, GenAI assistance was associated with shorter documentation time and a positive net labor value from October to December 2024. Prompts were constrained, and nurse verification was required to mitigate hallucinations. Future work will enhance logging to capture reliability and editing metrics, compare LLM-generated drafts with nurse-finalized notes to inform prompt refinement, and assess generalizability to other documentation workflows.

Subjects

MeSH terms (MEDLINE)

Large Language ModelsPatient HandoffDocumentationTaiwanHumansElectronic Health RecordsNursing Staff, HospitalCOVID-19HospitalsGenerative Artificial IntelligenceNursing Records

Author keywords

artificial intelligenceelectronic medical recordsgenerative artificial intelligencelarge language modelnursing information systemnursing shortage

Authors and institutions

  • Department of Surgery, School of Medicine, College of Medicine, Taipei Medical University, Taipei, Taiwan.
  • College of Medicine, Professional Master Program in Artificial Intelligence in Medicine, Taipei Medical University, Taipei, Taiwan.
  • Department of Surgery, Division of Pediatric Surgery, Taipei Medical University Hospital, Taipei, Taiwan.
  • Department of Internal Medicine, School of Medicine, College of Medicine, Taipei Medical University, Taipei, Taiwan.
  • Division of Nephrology, Department of Internal Medicine, Shuang Ho Hospital, New Taipei City, Taiwan.
  • Taipei Medical University Research Center of Urology and Kidney (TMU-RCUK), Taipei Medical University, Taipei, Taiwan.

ORCID profiles: Ray-Jade Chen, Mai-Szu Wu, Lung-Wen Tsai, Shy-Shin Chang, Shu-Tai Shen Hsiao, Yu-Sheng Lo

Cite

APA

Chen, R. J., Wu, M. S., Tsai, L. W., Chang, S. S., Shen Hsiao, S. T., & Lo, Y. S. (2026). Integrating a Large Language Model to Streamline Nursing Handover Documentation Across Multiple Hospitals in Taiwan: Development and Implementation Study. Journal of Medical Internet Research, 28, e81604. https://doi.org/10.2196/81604

Vancouver

Chen RJ, Wu MS, Tsai LW, Chang SS, Shen Hsiao ST, Lo YS. Integrating a Large Language Model to Streamline Nursing Handover Documentation Across Multiple Hospitals in Taiwan: Development and Implementation Study. Journal of Medical Internet Research. 2026;28:e81604. doi:10.2196/81604

BibTeX
@article{Chen2026,
  author = {Chen, Ray-Jade and Wu, Mai-Szu and Tsai, Lung-Wen and Chang, Shy-Shin and Shen Hsiao, Shu-Tai and Lo, Yu-Sheng},
  title = {Integrating a Large Language Model to Streamline Nursing Handover Documentation Across Multiple Hospitals in Taiwan: Development and Implementation Study},
  journal = {Journal of Medical Internet Research},
  year = {2026},
  volume = {28},
  pages = {e81604},
  doi = {10.2196/81604}
}
Start for free →