Zero-Shot LLMs for Named Entity Recognition: Targeting Cardiac Function Indicators in German Clinical Texts
The results strongly recommend using open-source LLMs for extracting medical parameters from clinical texts, including those in German, due to their high accuracy and effectiveness even without specific fine-tuning.
Authors
- Philipp Neuhaus (ORCID: https://orcid.org/0000-0003-1028-2884)
- Julian Varghese (ORCID: https://orcid.org/0000-0002-7206-3719)
- Lucas Plagwitz (ORCID: https://orcid.org/0000-0001-7626-8853)
- Antonius Büscher (ORCID: https://orcid.org/0000-0003-1774-4252)
- Noah Losch
- Kemal Yildirim (ORCID: https://orcid.org/0009-0009-2129-0952)
Institutions
- University of Münster (DE)
- University Hospital Münster (DE)
Publication Details
- Journal
- Studies in health technology and informatics
- Published
- 2024-08-30
- DOI
- https://doi.org/10.3233/shti240861
- Citations
- 4
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 1.72