Using Prompt Engineering to Optimize a RAG Pipeline for EHR-Nursing Data Standardization
Studies in Health Technology and Informatics · 21.05.2026
DOI: 10.3233/shti260302 ↗Kurz gefasst
Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, erschienen am 21.05.2026. Verfasst von Tamara G R Macieira und 5 weiteren Autor:innen. Beteiligte Einrichtung: University of Florida, College of Nursing, Gainesville FL USA. Hauptthemen laut MEDLINE: Electronic Health Records, Nursing Records, Standardized Nursing Terminology, Nursing Informatics. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Standardizing nursing care plan data from electronic health records is critical for interoperability and large-scale research but is often hindered by the heterogeneity of local terminologies. This study evaluates an optimized Retrieval-Augmented Generation (RAG) pipeline using large language models to map local care plan problems, goals, and interventions from two health systems to standardized nursing terminologies. We compared multiple prompt engineering techniques. Structured Prompts combined with Few-Shot Learning achieved the highest performance, with moderate accuracy (45-70%). Although full automation remains out of reach, this approach reduced human workload and supports scalable, human-in-the-loop semantic interoperability of nursing data.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- University of Florida, College of Nursing, Gainesville FL USA.
- University of Florida, Department of Computer and Information Science and Engineering, Gainesville FL USA.
- University of South Florida, Department of Industrial & Management Systems Engineering, Tampa FL USA.
Zitieren
APA
Macieira, T. G. R., Upganlawar, V., Semenov, A., Bjarnadottir, R. I., Keenan, G., & Yao, Y. (2026). Using Prompt Engineering to Optimize a RAG Pipeline for EHR-Nursing Data Standardization. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti260302
Vancouver
Macieira TGR, Upganlawar V, Semenov A, Bjarnadottir RI, Keenan G, Yao Y. Using Prompt Engineering to Optimize a RAG Pipeline for EHR-Nursing Data Standardization. Studies in Health Technology and Informatics. 2026. doi:10.3233/shti260302
BibTeX
@article{Macieira2026,
author = {Macieira, Tamara G R and Upganlawar, Vedant and Semenov, Alexander and Bjarnadottir, Ragnhildur I and Keenan, Gail and Yao, Yingwei},
title = {Using Prompt Engineering to Optimize a RAG Pipeline for EHR-Nursing Data Standardization},
journal = {Studies in Health Technology and Informatics},
year = {2026},
doi = {10.3233/shti260302}
}
EUVIMED