EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

NERFlow: A Workflow-Based Subsystem of FIT4NER for LLM-Assisted Medical Named Entity Recognition

Florian Freund, Philippe Tamla, Bao Tran, Matthias Hemmje

Electronics · 06.08.2026 · 15 (15) · 3484

DOI: 10.3390/electronics15153484 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 06.08.2026. Verfasst von Florian Freund und 3 weiteren Autor:innen. Die Arbeit nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Preparing training data for domain-specific medical Named Entity Recognition (NER) involves a trade-off between annotation quality, expert effort, and data privacy: manual annotation is costly, whereas cloud-based Large Language Models (LLMs) raise concerns about the control of sensitive clinical text. This article introduces NERFlow, a workflow-driven subsystem of the FIT4NER project whose contribution is an abstraction layer that makes rule-based, model-based, and LLM-based annotation interchangeable and comparable within one configurable workflow environment. Open-source LLMs are integrated as exchangeable annotation services, deployable locally or in cloud-agnostic infrastructures via Kubernetes, and embedded into the KM-EP knowledge management system. NERFlow was evaluated qualitatively, through a cognitive walkthrough, an IEEE 1028 technical review, and a user-centered survey with 18 participants, and quantitatively on the CRAFT corpus with seven open-source and hosted LLMs run through an identical pipeline. The results support its use as LLM-assisted pre-annotation with expert correction, with locally deployable open-source models as the more reliable basis for reproducible operation.

Zitieren

APA

Freund, F., Tamla, P., Tran, B., & Hemmje, M. (2026). NERFlow: A Workflow-Based Subsystem of FIT4NER for LLM-Assisted Medical Named Entity Recognition. Electronics, 15(15), 3484. https://doi.org/10.3390/electronics15153484

Vancouver

Freund F, Tamla P, Tran B, Hemmje M. NERFlow: A Workflow-Based Subsystem of FIT4NER for LLM-Assisted Medical Named Entity Recognition. Electronics. 2026;15(15):3484. doi:10.3390/electronics15153484

BibTeX
@article{Freund2026,
  author = {Freund, Florian and Tamla, Philippe and Tran, Bao and Hemmje, Matthias},
  title = {NERFlow: A Workflow-Based Subsystem of FIT4NER for LLM-Assisted Medical Named Entity Recognition},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {15},
  pages = {3484},
  doi = {10.3390/electronics15153484}
}
Kostenlos starten →