Inheritance-guided Hierarchical Assignment for Clinical Automatic Diagnosis

TL;DR

This paper introduces a novel inheritance-guided hierarchical framework with graph propagation and attention mechanisms to improve automatic clinical diagnosis from notes, addressing code imbalance and correlation challenges.

Contribution

It proposes a new hierarchical prediction method combined with graph neural networks and attention to enhance diagnosis accuracy in clinical text mining.

Findings

Outperforms existing methods on MIMIC-III dataset

Effectively handles unbalanced diagnosis code distribution

Captures diagnosis code correlations through graph propagation

Abstract

Clinical diagnosis, which aims to assign diagnosis codes for a patient based on the clinical note, plays an essential role in clinical decision-making. Considering that manual diagnosis could be error-prone and time-consuming, many intelligent approaches based on clinical text mining have been proposed to perform automatic diagnosis. However, these methods may not achieve satisfactory results due to the following challenges. First, most of the diagnosis codes are rare, and the distribution is extremely unbalanced. Second, existing methods are challenging to capture the correlation between diagnosis codes. Third, the lengthy clinical note leads to the excessive dispersion of key information related to codes. To tackle these challenges, we propose a novel framework to combine the inheritance-guided hierarchical assignment and co-occurrence graph propagation for clinical automatic diagnosis. Specifically, we propose a hierarchical joint prediction strategy to address the challenge of unbalanced codes distribution. Then, we utilize graph convolutional neural networks to obtain the correlation and semantic representations of medical ontology. Furthermore, we introduce multi attention mechanisms to extract crucial information. Finally, extensive experiments on MIMIC-III dataset clearly validate the effectiveness of our method.