A General Knowledge Injection Framework for ICD Coding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Xu, Zhang, Kun, Ma, Wenxin, Wang, Rongsheng, Wu, Chenxu, Li, Yingtai, Zhou, S. Kevin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908378711719936
author Zhang, Xu
Zhang, Kun
Ma, Wenxin
Wang, Rongsheng
Wu, Chenxu
Li, Yingtai
Zhou, S. Kevin
author_facet Zhang, Xu
Zhang, Kun
Ma, Wenxin
Wang, Rongsheng
Wu, Chenxu
Li, Yingtai
Zhou, S. Kevin
contents ICD Coding aims to assign a wide range of medical codes to a medical text document, which is a popular and challenging task in the healthcare domain. To alleviate the problems of long-tail distribution and the lack of annotations of code-specific evidence, many previous works have proposed incorporating code knowledge to improve coding performance. However, existing methods often focus on a single type of knowledge and design specialized modules that are complex and incompatible with each other, thereby limiting their scalability and effectiveness. To address this issue, we propose GKI-ICD, a novel, general knowledge injection framework that integrates three key types of knowledge, namely ICD Description, ICD Synonym, and ICD Hierarchy, without specialized design of additional modules. The comprehensive utilization of the above knowledge, which exhibits both differences and complementarity, can effectively enhance the ICD coding performance. Extensive experiments on existing popular ICD coding benchmarks demonstrate the effectiveness of GKI-ICD, which achieves the state-of-the-art performance on most evaluation metrics. Code is available at https://github.com/xuzhang0112/GKI-ICD.
format Preprint
id arxiv_https___arxiv_org_abs_2505_18708
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A General Knowledge Injection Framework for ICD Coding
Zhang, Xu
Zhang, Kun
Ma, Wenxin
Wang, Rongsheng
Wu, Chenxu
Li, Yingtai
Zhou, S. Kevin
Computation and Language
Artificial Intelligence
ICD Coding aims to assign a wide range of medical codes to a medical text document, which is a popular and challenging task in the healthcare domain. To alleviate the problems of long-tail distribution and the lack of annotations of code-specific evidence, many previous works have proposed incorporating code knowledge to improve coding performance. However, existing methods often focus on a single type of knowledge and design specialized modules that are complex and incompatible with each other, thereby limiting their scalability and effectiveness. To address this issue, we propose GKI-ICD, a novel, general knowledge injection framework that integrates three key types of knowledge, namely ICD Description, ICD Synonym, and ICD Hierarchy, without specialized design of additional modules. The comprehensive utilization of the above knowledge, which exhibits both differences and complementarity, can effectively enhance the ICD coding performance. Extensive experiments on existing popular ICD coding benchmarks demonstrate the effectiveness of GKI-ICD, which achieves the state-of-the-art performance on most evaluation metrics. Code is available at https://github.com/xuzhang0112/GKI-ICD.
title A General Knowledge Injection Framework for ICD Coding
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2505.18708