Retrieval-Augmented Generation for ICD-10 Coding in German Clinical Texts - A Technical Case Report.

Journal: Studies in health technology and informatics
Published Date:

Abstract

INTRODUCTION: Manual ICD-10 coding of German clinical texts is time-consuming and error-prone. This project aims to develop a semi-automated pipeline for efficient coding of unstructured medical documentation.

Authors

  • Mario Krumscheid
    Department of Computer Science, Kempten University of Applied Sciences, Kempten, Germany.
  • Johannes Blömer
    Charité - Universitätsmedizin Berlin, Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany.
  • Matthias Becker
    Department of Medical Informatics, University of Applied Sciences and Arts, Dortmund, Germany.