Optimizing Automated KCD Coding: A Retrieval-Verification Approach
Citations

WEB OF SCIENCE

0
Citations

SCOPUS

0

초록

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.

키워드

Clinical codingEmbeddingKCDLanguage models
제목
Optimizing Automated KCD Coding: A Retrieval-Verification Approach
저자
Lee, SangjiCha, Won Chul
DOI
10.3233/SHTI250485
발행일
2025-05
유형
Article
저널명
Studies in health technology and informatics
327
페이지
872 ~ 873