A Label Attention Model for ICD Coding from Clinical Text

TL;DR

This paper introduces a label attention model for automatic ICD coding from clinical notes, effectively handling variable text fragment lengths and code interdependence, while addressing data imbalance through hierarchical joint learning, achieving state-of-the-art results.

Contribution

The paper presents a novel label attention model with hierarchical joint learning to improve ICD coding accuracy, especially for infrequent codes, outperforming previous CNN-based models.

Findings

Achieves new state-of-the-art results on MIMIC datasets.

Effectively handles variable text fragment lengths and code interdependence.

Improves performance on infrequent ICD codes.

Abstract

ICD coding is a process of assigning the International Classification of Disease diagnosis codes to clinical/medical notes documented by health professionals (e.g. clinicians). This process requires significant human resources, and thus is costly and prone to error. To handle the problem, machine learning has been utilized for automatic ICD coding. Previous state-of-the-art models were based on convolutional neural networks, using a single/several fixed window sizes. However, the lengths and interdependence between text fragments related to ICD codes in clinical text vary significantly, leading to the difficulty of deciding what the best window sizes are. In this paper, we propose a new label attention model for automatic ICD coding, which can handle both the various lengths and the interdependence of the ICD code related text fragments. Furthermore, as the majority of ICD codes are not frequently used, leading to the extremely imbalanced data issue, we additionally propose a hierarchical joint learning mechanism extending our label attention model to handle the issue, using the hierarchical relationships among the codes. Our label attention model achieves new state-of-the-art results on three benchmark MIMIC datasets, and the joint learning mechanism helps improve the performances for infrequent codes.