From BERT to generative AI - Comparing encoder-only vs. large language models in a cohort of lung cancer patients for named entity recognition in unstructured medical reports.

Journal: Computers in biology and medicine
Published Date: Jun 23, 2025

Abstract

BACKGROUND: Extracting clinical entities from unstructured medical documents is critical for improving clinical decision support and documentation workflows. This study examines the performance of various encoder and decoder models trained for Named Entity Recognition (NER) of clinical parameters in pathology and radiology reports, highlighting the applicability of Large Language Models (LLMs) for this task.

Authors

  • Kamyar Arzideh
    Data Integration Center, Central IT Department, University Hospital Essen, Essen, Germany.
  • Henning Schäfer
    Department of Computer Science, University of Applied Sciences and Arts Dortmund (FH Dortmund), Emil-Figge-Straße 42, Dortmund, 44227, Germany; Institute for Transfusion Medicine, University Hospital Essen, Hufelandstraße 55, Essen, 45147, Germany. Electronic address: henning.schaefer@uk-essen.de.
  • Hector Allende-Cid
    Escuela de Ingeniería Informatica, Pontificia Universidad Católica de Valparaíso, Valparaíso, Chile.
  • Giulia Baldini
    Institute for Artificial Intelligence in Medicine, University Medicine Essen, Essen, Germany.
  • Thomas Hilser
    West German Cancer Center Essen, Department of Medical Oncology, University Hospital Essen, Essen, Germany.
  • Ahmad Idrissi-Yaghir
    Department of Computer Science, University of Applied Sciences and Arts Dortmund (FH Dortmund), Emil-Figge-Straße 42, Dortmund, 44227, Germany; Institute for Medical Informatics, Biometry and Epidemiology (IMIBE), University Hospital Essen, Hufelandstraße 55, Essen, 45147, Germany.
  • Katharina Laue
    West German Cancer Centre, University Hospital Essen, Essen, Germany.
  • Nilesh Chakraborty
    Fraunhofer IAIS, Sankt Augustin, Germany.
  • Niclas Doll
    Fraunhofer Institute for Intelligent Analysis and Information Systems (IAIS), Sankt Augustin, Germany.
  • Dario Antweiler
    Fraunhofer Institut für Intelligente Analyse und Informationssysteme IAIS, Abteilung Knowledge Discovery, Schloss Birlinghoven 1, 53757, Sankt Augustin, Deutschland. dario.antweiler@iais.fraunhofer.de.
  • Katrin Klug
    Fraunhofer IAIS, Sankt Augustin, Germany. katrin.klug@iais.fraunhofer.de.
  • Niklas Beck
    Fraunhofer Institute for Intelligent Analysis and Information Systems (IAIS), Sankt Augustin, Germany.
  • Sven Giesselbach
    Fraunhofer IAIS, Sankt Augustin, Germany.
  • Christoph M Friedrich
    Department of Computer Science, University of Applied Sciences and Arts Dortmund, Dortmund, Germany.
  • Felix Nensa
    Institute for AI in Medicine (IKIM), University Hospital Essen, 45131 Essen, Germany.
  • Martin Schuler
    Department of Medical Oncology, West German Cancer Center, University Hospital Essen (AöR), Essen, Germany.
  • René Hosch
    Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Germany.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals