HieNet: Bidirectional Hierarchy Framework for Automated ICD Coding

TL;DR

HieNet is a novel bidirectional hierarchy framework that improves automated ICD coding by capturing code relationships and hierarchies, significantly enhancing prediction accuracy on public datasets.

Contribution

The paper introduces a new framework combining personalized PageRank, hierarchy encoding, and progressive prediction for better ICD code assignment.

Findings

Significant performance improvement over state-of-the-art methods.

Effective modeling of code relationships and hierarchies.

Validated on two public datasets with large margin improvements.

Abstract

International Classification of Diseases (ICD) is a set of classification codes for medical records. Automated ICD coding, which assigns unique International Classification of Diseases codes with each medical record, is widely used recently for its efficiency and error-prone avoidance. However, there are challenges that remain such as heterogeneity, label unbalance, and complex relationships between ICD codes. In this work, we proposed a novel Bidirectional Hierarchy Framework(HieNet) to address the challenges. Specifically, a personalized PageRank routine is developed to capture the co-relation of codes, a bidirectional hierarchy passage encoder to capture the codes' hierarchical representations, and a progressive predicting method is then proposed to narrow down the semantic searching space of prediction. We validate our method on two widely used datasets. Experimental results on two authoritative public datasets demonstrate that our proposed method boosts state-of-the-art performance by a large margin.