Development of a Synthetic Oncology Pathology Dataset for Large Language Model Evaluation in Medical Text Classification.

Journal: Studies in health technology and informatics
PMID: 40270415

Abstract

BACKGROUND: Large Language Models (LLMs) offer promising applications in oncology pathology report classification, improving efficiency, accuracy, and automation. However, the use of real patient data is restricted due to legal and ethical concerns, necessitating privacy-compliant alternatives.

Authors

  • Werner O Hackl
    Division for Digital Health and Telemedicine, UMIT TIROL - Private University for Health Sciences and Health Technology, Hall in Tirol, Austria.
  • Sabrina B Neururer
    Division for Digital Health and Telemedicine, UMIT TIROL - Private University for Health Sciences and Health Technology, Hall in Tirol, Austria.
  • Stefan Richter
    Division for Digital Health and Telemedicine, UMIT TIROL - Private University for Health Sciences and Health Technology, Hall in Tirol, Austria.
  • Hasan Taha
    Division for Digital Health and Telemedicine, UMIT TIROL - Private University for Health Sciences and Health Technology, Hall in Tirol, Austria.
  • Helmut Muehlboeck
    Department of Clinical Epidemiology, Tirol Kliniken GmbH, Innsbruck, Tirol, Austria.
  • Christoph Hickmann
    Department of Clinical Epidemiology, Tirol Kliniken GmbH, Innsbruck, Tirol, Austria.
  • Patricia Gscheidlinger
    Department of Clinical Epidemiology, Tirol Kliniken GmbH, Innsbruck, Tirol, Austria.
  • Martin Danler
    Division for Digital Health and Telemedicine, UMIT TIROL - Private University for Health Sciences and Health Technology, Hall in Tirol, Austria.
  • Marco Schweitzer
    Division for Digital Health and Telemedicine, UMIT TIROL - Private University for Health Sciences and Health Technology, Hall in Tirol, Austria.
  • Marko Ueberegger
    Department of Information Technology, Tirol Kliniken GmbH, Innsbruck, Austria.
  • Bernhard Pfeifer
    Division for Digital Health and Telemedicine, UMIT TIROL - Private University for Health Sciences and Health Technology, Hall in Tirol, Austria.

Keywords

External Resources

Popular Topics
Recent Journals