Multitask Balanced and Recalibrated Network for Medical Code Prediction

TL;DR

This paper introduces a novel neural network model that improves automated medical coding by addressing class imbalance, code association, and noise in clinical documents through multitask learning and a recalibrated feature extraction module.

Contribution

The paper proposes a multitask balanced and recalibrated neural network that captures code relationships and mitigates noise, advancing automated medical coding accuracy.

Findings

Outperforms baseline models on MIMIC-III dataset

Effectively handles class imbalance with focal loss

Enhances feature extraction from lengthy, noisy documents

Abstract

Human coders assign standardized medical codes to clinical documents generated during patients' hospitalization, which is error-prone and labor-intensive. Automated medical coding approaches have been developed using machine learning methods such as deep neural networks. Nevertheless, automated medical coding is still challenging because of the imbalanced class problem, complex code association, and noise in lengthy documents. To solve these issues, we propose a novel neural network called Multitask Balanced and Recalibrated Neural Network. Significantly, the multitask learning scheme shares the relationship knowledge between different code branches to capture the code association. A recalibrated aggregation module is developed by cascading convolutional blocks to extract high-level semantic features that mitigate the impact of noise in documents. Also, the cascaded structure of the recalibrated module can benefit the learning from lengthy notes. To solve the class imbalanced problem, we deploy the focal loss to redistribute the attention of low and high-frequency medical codes. Experimental results show that our proposed model outperforms competitive baselines on a real-world clinical dataset MIMIC-III.