ICD Coding from Clinical Text Using Multi-Filter Residual Convolutional Neural Network

TL;DR

This paper introduces a Multi-Filter Residual CNN that effectively captures diverse text patterns for automated ICD coding, outperforming previous models on standard clinical datasets.

Contribution

The paper proposes a novel Multi-Filter Residual CNN architecture that enhances document representation for ICD coding by capturing varied text patterns and enlarging the receptive field.

Findings

Outperforms state-of-the-art models on MIMIC datasets

Effective in capturing diverse text patterns for ICD coding

Achieves superior evaluation metrics across multiple benchmarks

Abstract

Automated ICD coding, which assigns the International Classification of Disease codes to patient visits, has attracted much research attention since it can save time and labor for billing. The previous state-of-the-art model utilized one convolutional layer to build document representations for predicting ICD codes. However, the lengths and grammar of text fragments, which are closely related to ICD coding, vary a lot in different documents. Therefore, a flat and fixed-length convolutional architecture may not be capable of learning good document representations. In this paper, we proposed a Multi-Filter Residual Convolutional Neural Network (MultiResCNN) for ICD coding. The innovations of our model are two-folds: it utilizes a multi-filter convolutional layer to capture various text patterns with different lengths and a residual convolutional layer to enlarge the receptive field. We evaluated the effectiveness of our model on the widely-used MIMIC dataset. On the full code set of MIMIC-III, our model outperformed the state-of-the-art model in 4 out of 6 evaluation metrics. On the top-50 code set of MIMIC-III and the full code set of MIMIC-II, our model outperformed all the existing and state-of-the-art models in all evaluation metrics. The code is available at https://github.com/foxlf823/Multi-Filter-Residual-Convolutional-Neural-Network.