Towards Automated ICD Coding Using Deep Learning

TL;DR

This paper presents a hierarchical deep learning model with attention mechanisms for automating ICD coding from diagnosis descriptions, demonstrating promising results that outperform previous methods.

Contribution

The paper introduces a novel deep learning framework combining character-aware models and attention mechanisms for automatic ICD code assignment.

Findings

Achieved 0.53 F1 score and 0.90 AUC, outperforming previous methods.

Demonstrated the effectiveness of attention mechanisms in matching diagnosis descriptions to codes.

Proved the potential of deep learning for automated ICD coding in healthcare.

Abstract

International Classification of Diseases(ICD) is an authoritative health care classification system of different diseases and conditions for clinical and management purposes. Considering the complicated and dedicated process to assign correct codes to each patient admission based on overall diagnosis, we propose a hierarchical deep learning model with attention mechanism which can automatically assign ICD diagnostic codes given written diagnosis. We utilize character-aware neural language models to generate hidden representations of written diagnosis descriptions and ICD codes, and design an attention mechanism to address the mismatch between the numbers of descriptions and corresponding codes. Our experimental results show the strong potential of automated ICD coding from diagnosis descriptions. Our best model achieves 0.53 and 0.90 of F1 score and area under curve of receiver operating characteristic respectively. The result outperforms those achieved using character-unaware encoding method or without attention mechanism. It indicates that our proposed deep learning model can code automatically in a reasonable way and provide a framework for computer-auxiliary ICD coding.