Optimizing Nursing Records: Exploring the Impact of AI-Enhanced Documentation
Studies in Health Technology and Informatics · 2025
DOI: 10.3233/shti250926 ↗Kurz gefasst
Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Ryoma Seto und 4 weiteren Autor:innen. Beteiligte Einrichtung: Health Informatics, Faculty of Healthcare, Tokyo Healthcare University, Japan. Hauptthemen laut MEDLINE: Nursing Records, Electronic Health Records, Documentation, Artificial Intelligence. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
The standardization of medical records through structured templates has gained importance in improving the quality and safety of patient care. The results showed that missing rates ranged from 40.0% (fever reduction) to 43.9% (pain), while redundant entries ranged from 11.7% (mild fever) to 20.0% (fever). Analysis of medication mentions revealed reliance on general classifications, such as “analgesics” (0.43%) and “antipyretics” (0.35%), over specific drugs like acetaminophen (0.44%) or bisacodyl (0.51%). Free-form documentation led to inefficiencies and ambiguities, whereas structured templates improved specificity, particularly for medications critical to patient safety. The findings highlight the need for user-friendly templates to reduce variability and enhance the completeness of nursing records. Structured templates can streamline documentation, reduce redundancy, and improve the quality of care by prompting detailed and accurate entries. Additionally, integrating advanced technologies like AI could further optimize adherence to templates, ensuring consistent and safe clinical practices. A deeper exploration of user experience and organizational factors is warranted in future studies to enhance implementation success. AI-based tools, such as intelligent assistants that prompt missing entries in real time, could further enhance template adherence and improve data completeness. This study analyzed 90,432 anonymized nursing records to evaluate adherence to predefined documentation templates across five key topics: mild fever, pain, fever, bowel control, and fever reduction. Text mining techniques identified missing items, redundant entries, and medication mentions.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Health Informatics, Faculty of Healthcare, Tokyo Healthcare University, Japan.
- Department of Pharmacy, Kyorin University Hospital, Tokyo, Japan.
- Seishinkai Inoue Hospital, Fukuoka, Japan.
- Show Chwan Health Care System, Taipei, Republic of China (Taiwan).
Zitieren
APA
Seto, R., Wakabayashi, S., Takeyama, Y., Inoue, T., & Liu, D. (2025). Optimizing Nursing Records: Exploring the Impact of AI-Enhanced Documentation. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti250926
Vancouver
Seto R, Wakabayashi S, Takeyama Y, Inoue T, Liu D. Optimizing Nursing Records: Exploring the Impact of AI-Enhanced Documentation. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti250926
BibTeX
@article{Seto2025,
author = {Seto, Ryoma and Wakabayashi, Susumu and Takeyama, Yuko and Inoue, Toshitaka and Liu, David},
title = {Optimizing Nursing Records: Exploring the Impact of AI-Enhanced Documentation},
journal = {Studies in Health Technology and Informatics},
year = {2025},
doi = {10.3233/shti250926}
}
EUVIMED