Hyperbolic graph convolutional neural network with contrastive learning for automated ICD coding

作     者：Wu, Yuzhou Chen, Xuechen Yao, Xin Yu, Yongang Chen, Zhigang 

作者机构：Cent South Univ Sch Comp Sci & Engn Changsha 410012 Peoples R China China Mobile Chengdu Ind Res Inst Chengdu 610041 Peoples R China 

出 版 物：《COMPUTERS IN BIOLOGY AND MEDICINE》 (生物学与医学中的计算机)

年 卷 期：2024年第168卷

页      面：107797-107797页

核心收录：

学科分类：0831[工学-生物医学工程（可授工学、理学、医学学位）] 0710[理学-生物学] 07[理学] 09[农学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Intelligent software and hardware system of the medical process assistant and its application belongs to "2030 Innovation Megaprojects"-New Generation Artificial Intelligence [2020AAA010 (9605)] Major special project of Changsha science and technology plan [kh2103016] 

主　　题：International classification of diseases Automatic ICD coding Code hierarchy Contrastive learning Imbalanced label distribution 

摘      要：The International Classification of Diseases (ICD) is a widely used criterion for disease classification, health monitoring, and medical data analysis. Deep learning-based automated ICD coding has gained attention due to the time-consuming and costly nature of manual coding. The main challenges of automated ICD coding include imbalanced label distribution, code hierarchy and noisy texts. Recent works have considered using code hierarchy or description for better label representation to solve the problem of imbalanced label distribution. However, these methods are still ineffective and redundant since they only interact with a constant label representation. In this work, we introduce a novel Hyperbolic Graph Convolutional Network with Contrastive Learning (HGCN-CL) to solve the above problems and the shortcomings of the previous methods. We adopt a Hyperbolic graph convolutional network on ICD coding to capture the hierarchical structure of codes, which can solve the problem of large distortions when embedding hierarchical structure with graph convolutional network. Besides, we introduce contrastive learning for automatic ICD coding by injecting code features into text encoder to generate hierarchical-aware positive samples to solve the problem of interacting with constant code features. We conduct experiments on the public MIMIC-III and MIMIC-II datasets. The results on MIMIC III show that HGCN-CL outperforms previous state-of-art methods for automatic ICD coding, which achieves a 2.7% and 3.6% improvement respectively compared to previous best results (Hypercore). We also provide ablation experiments and hierarchy visualization to verify the effectiveness of components in our model.