EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

A Real-Time Clinical Text Information Extractor via LLM

Giovanni Paolo Tobia, Federica Tomassini, Massimo Criscione, Chiara Dachena, Alice Luraschi, Andrea Rosati, Anna Fagotti, Massimo Bernaschi, Stefano Patarnello, Livia Lilli

Studies in Health Technology and Informatics · 2026

DOI: 10.3233/shti260303 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2026. Verfasst von Giovanni Paolo Tobia und 9 weiteren Autor:innen. Beteiligte Einrichtung: Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Rome, Italy. Hauptthemen laut MEDLINE: Large Language Models, Natural Language Processing, Data Mining, Electronic Health Records. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The extraction of structured information from unstructured clinical text is a critical requirement for real-time decision support and research applications in oncology. In this study, we present a modular pipeline leveraging locally deployed Large Language Model (LLM) for the automated extraction of clinically relevant entities from Italian gynecologic oncology reports. The system integrates hierarchical document segmentation, LLM-driven few-shot information extraction and post-processing. Validation is performed combining expert-annotated gold standards with an LLM-as-a-Judge framework. Evaluation across multiple LLM architectures (Gemma3:12b, Gemma3:27b, GPT-oss:20b, Mistral:7b) demonstrates a trade-off between extraction accuracy and computational latency. Normalized runtime analysis indicates that Gemma3:12b achieves lower latency with robust performance, while GPT-oss:20b exhibits higher latency, limiting real-time applicability. The proposed framework facilitates rapid, standardized information extraction from clinical reports, offering a scalable solution for integrating structured insights into healthcare workflows.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Large Language ModelsNatural Language ProcessingData MiningElectronic Health RecordsInformation Storage and RetrievalGenital Neoplasms, FemaleDecision Support Systems, ClinicalHumansFemaleItaly

Stichwörter der Autor:innen

Gynecology OncologyInformation ExtractionLarge Language ModelsNatural Language ProcessingReal-time Decision Support

Autor:innen und Institutionen

  • Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Rome, Italy.
  • Catholic University of the Sacred Heart, Rome, Italy.
  • UOC Ginecologia Oncologica, Dipartimento di Scienze della Salute della Donna, del Bambino e di Sanita Pubblica, Fondazione Policlinico Universitario A. Gemelli, IRCCS, Rome, Italy.
  • Gynecologic and Obstetric Clinic, Department of Medicine, Surgery and Pharmacy, University of Sassari, Sassari, Italy.
  • Istituto per le Applicazioni del Calcolo "Mauro Picone", Italian National Research Council, Rome, Italy.

Zitieren

APA

Tobia, G. P., Tomassini, F., Criscione, M., Dachena, C., Luraschi, A., Rosati, A., Fagotti, A., Bernaschi, M., Patarnello, S., & Lilli, L. (2026). A Real-Time Clinical Text Information Extractor via LLM. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti260303

Vancouver

Tobia GP, Tomassini F, Criscione M, Dachena C, Luraschi A, Rosati A, et al. A Real-Time Clinical Text Information Extractor via LLM. Studies in Health Technology and Informatics. 2026. doi:10.3233/shti260303

BibTeX
@article{Tobia2026,
  author = {Tobia, Giovanni Paolo and Tomassini, Federica and Criscione, Massimo and Dachena, Chiara and Luraschi, Alice and Rosati, Andrea and Fagotti, Anna and Bernaschi, Massimo and Patarnello, Stefano and Lilli, Livia},
  title = {A Real-Time Clinical Text Information Extractor via LLM},
  journal = {Studies in Health Technology and Informatics},
  year = {2026},
  doi = {10.3233/shti260303}
}
Kostenlos starten →