EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Assessing the Potential of an LLM-Powered System for Enhancing FHIR Resource Validation

Parinaz Tabari, Alfonso Piscitelli, Gennaro Costagliola, Mattia de Rosa

Studies in Health Technology and Informatics · 2025

DOI: 10.3233/shti250470 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Parinaz Tabari und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Informatics, University of Salerno, Italy. Hauptthemen laut MEDLINE: Natural Language Processing, Artificial Intelligence, Electronic Health Records. Die Arbeit wurde bisher 2-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large Language Models (LLMs) have gained significant popularity among healthcare professionals as tools for AI-driven interactions. These models can analyze large volumes of clinical data, including patient narratives, to assist in efficient decision-making. In this paper, we aim to evaluate how the use of a syntactic validator combined with an LLM can improve the accuracy of generating FHIR resources from natural language sentences. We compared zero-shot, one-shot, and few-shot prompting methods. The process involves a validator component that iteratively assesses whether the output of the LLM adheres to the syntactic requirements specified by FHIR before returning the final response to the user. One-shot and few-shot prompting methods generated 96% of syntactic validity, while it was 90% for the zero-shot strategy. According to the semantic analysis, one-shot prompting achieved the highest number of correct comparisons between the generated JSON and ground truth resource, with 25.82 comparisons per FHIR resource. This was followed by the few-shot strategy, with 25.50 correct comparisons per FHIR resource, and the zero-shot prompting approach, with 15.21 correct comparisons per FHIR resource.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Natural Language ProcessingArtificial IntelligenceElectronic Health RecordsSemanticsHumans

Stichwörter der Autor:innen

FHIRFast HealthcareGPT-4oInteroperability ResourcesLLMLarge Language ModelOpenAIPrompt EngineeringValidation

Autor:innen und Institutionen

  • Department of Informatics, University of Salerno, Italy.

Zitieren

APA

Tabari, P., Piscitelli, A., Costagliola, G., & de Rosa, M. (2025). Assessing the Potential of an LLM-Powered System for Enhancing FHIR Resource Validation. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti250470

Vancouver

Tabari P, Piscitelli A, Costagliola G, de Rosa M. Assessing the Potential of an LLM-Powered System for Enhancing FHIR Resource Validation. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti250470

BibTeX
@article{Tabari2025,
  author = {Tabari, Parinaz and Piscitelli, Alfonso and Costagliola, Gennaro and de Rosa, Mattia},
  title = {Assessing the Potential of an LLM-Powered System for Enhancing FHIR Resource Validation},
  journal = {Studies in Health Technology and Informatics},
  year = {2025},
  doi = {10.3233/shti250470}
}
Kostenlos starten →