Large language models for data extraction from unstructured and semi-structured electronic health records: a multiple model performance evaluation.

Journal: BMJ health & care informatics
PMID: 39832824

Abstract

OBJECTIVES: We aimed to evaluate the performance of multiple large language models (LLMs) in data extraction from unstructured and semi-structured electronic health records.

Authors

  • Vasileios Ntinopoulos
    Department of Cardiac Surgery, University Hospital of Zurich, Zurich, Switzerland.
  • Hector Rodriguez Cetina Biefer
    Department of Cardiac Surgery, University Hospital of Zurich, Zurich, Switzerland.
  • Igor Tudorache
    Department of Cardiac Surgery, University Hospital of Zurich, Zurich, Switzerland.
  • Nestoras Papadopoulos
    Department of Cardiac Surgery, University Hospital of Zurich, Zurich, Switzerland.
  • Dragan Odavic
    Department of Cardiac Surgery, University Hospital of Zurich, Zurich, Switzerland.
  • Petar Risteski
    Department of Cardiac Surgery, University Hospital of Zurich, Zurich, Switzerland.
  • Achim Haeussler
    Department of Cardiac Surgery, University Hospital of Zurich, Zurich, Switzerland.
  • Omer Dzemali
    Department of Cardiac Surgery, University Hospital of Zurich, Zurich, Switzerland omer.dzemali@usz.ch.

Keywords

External Resources

Popular Topics
Recent Journals