Zero-Shot LLMs for Named Entity Recognition: Targeting Cardiac Function Indicators in German Clinical Texts.

Journal: Studies in health technology and informatics
PMID: 39234726

Abstract

INTRODUCTION: Large Language Models (LLMs) like ChatGPT have become increasingly prevalent. In medicine, many potential areas arise where LLMs may offer added value. Our research focuses on the use of open-source LLM alternatives like Llama 3, Gemma, Mistral, and Mixtral to extract medical parameters from German clinical texts. We concentrate on German due to an observed gap in research for non-English tasks.

Authors

  • Lucas Plagwitz
    Institute for Translational Psychiatry, University of Münster, Münster, Germany.
  • Philipp Neuhaus
    Institute of Medical Informatics, Westfälische Wilhelms-Universität, Münster, Germany.
  • Kemal Yildirim
    Institute of Medical Informatics, University of Münster, Münster, Germany.
  • Noah Losch
    Institute of Medical Informatics, University of Münster, Münster, Germany.
  • Julian Varghese
    Institute of Medical Data Science, Otto-von-Guericke University, Magdeburg, Germany.
  • Antonius Büscher
    Institute of Medical Informatics, University of Münster, Münster, Germany.

Keywords

External Resources

Popular Topics
Recent Journals