An Encoder-Decoder Model for ICD-10 Coding of Death Certificates

TL;DR

This paper presents an encoder-decoder neural network model for automatically assigning ICD-10 codes to death certificate texts, achieving high accuracy and outperforming previous methods.

Contribution

The work introduces a novel end-to-end neural architecture with knowledge integration for ICD-10 coding from death certificates.

Findings

Achieved 85.01% F-measure on benchmark dataset

Significant improvement over average participant scores

Demonstrated effectiveness of encoder-decoder models in medical coding

Abstract

Information extraction from textual documents such as hospital records and healthrelated user discussions has become a topic of intense interest. The task of medical concept coding is to map a variable length text to medical concepts and corresponding classification codes in some external system or ontology. In this work, we utilize recurrent neural networks to automatically assign ICD-10 codes to fragments of death certificates written in English. We develop end-to-end neural architectures directly tailored to the task, including basic encoder-decoder architecture for statistical translation. In order to incorporate prior knowledge, we concatenate cosine similarities vector among the text and dictionary entry to the encoded state. Being applied to a standard benchmark from CLEF eHealth 2017 challenge, our model achieved F-measure of 85.01% on a full test set with significant improvement as compared to the average score of 62.2% for all official participants approaches.