Optimizing Automated KCD Coding: A Retrieval-Verification Approach

Sangji Lee, Won Chul Cha

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This study proposes a two-step Retrieval-Verification system for automating the assignment of Korean Standard Classification of Diseases (KCD) codes to free-text diagnoses. The system uses SapBERT-XLMR for initial retrieval, followed by Llama 3.1 for final verification and code selection. Combining the two models improved accuracy to 82.3%. Future work aims to improve the system’s performance on abbreviations and conduct experiment with a larger dataset.

Original languageEnglish
Title of host publicationIntelligent Health Systems - From Technology to Data and Knowledge, Proceedings of MIE 2025
EditorsElisavet Andrikopoulou, Parisis Gallos, Theodoros N. Arvanitis, Rosalynn Austin, Arriel Benis, Ronald Cornet, Panagiotis Chatzistergos, Alexander Dejaco, Linda Dusseljee-Peute, Alaa Mohasseb, Pantelis Natsiavas, Haythem Nakkas, Philip Scott
PublisherIOS Press BV
Pages872-873
Number of pages2
ISBN (Electronic)9781643685960
DOIs
StatePublished - 15 May 2025
Event35th Medical Informatics Europe Conference, MIE 2025 - Glasgow, United Kingdom
Duration: 19 May 202521 May 2025

Publication series

NameStudies in Health Technology and Informatics
Volume327
ISSN (Print)0926-9630
ISSN (Electronic)1879-8365

Conference

Conference35th Medical Informatics Europe Conference, MIE 2025
Country/TerritoryUnited Kingdom
CityGlasgow
Period19/05/2521/05/25

Keywords

  • Clinical coding
  • Embedding
  • KCD
  • Language models

Fingerprint

Dive into the research topics of 'Optimizing Automated KCD Coding: A Retrieval-Verification Approach'. Together they form a unique fingerprint.

Cite this