Multitask Recalibrated Aggregation Network for Medical Code Prediction (2021-04-02T00:00:00.000000Z)

TL;DR

A multitask recalibrated aggregation network that shares information across different coding schemes and captures the dependencies between different medical codes is proposed to solve the challenges of encoding lengthy and noisy clinical documents and capturing code associations.

Abstract

Medical coding translates professionally written medical reports into standardized codes, which is an essential part of medical information systems and health insurance reimbursement. Manual coding by trained human coders is time-consuming and error-prone. Thus, automated coding algorithms have been developed, building especially on the recent advances in machine learning and deep neural networks. To solve the challenges of encoding lengthy and noisy clinical documents and capturing code associations, we propose a multitask recalibrated aggregation network. In particular, multitask learning shares information across different coding schemes and captures the dependencies between different medical codes. Feature recalibration and aggregation in shared modules enhance representation learning for lengthy notes. Experiments with a real-world MIMIC-III dataset show significantly improved predictive performance.

Authors

E. Cambria

25 papers

Shaoxiong Ji

7 papers

Wei Sun

2 papers

TL;DR

Abstract

Authors

References36 items

Leveraging data and information systems on the sustainable development goals

Does the Magic of BERT Apply to Medical Code Assignment? A Quantitative Study

Dilated Convolutional Attention Network for Medical Code Assignment from Clinical Text

HyperCore: Hyperbolic and Co-graph Representation for Automatic ICD Coding

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

Hierarchical Adaptive Multi-task Learning Framework for Patient Diagnoses and Diagnostic Category Classification

Publicly Available Clinical BERT Embeddings

Automatic ICD code assignment of Chinese clinical notes based on multilayer attention BiRNN

Multi-Task Deep Neural Networks for Natural Language Understanding

Position-aware deep multi-task learning for drug-drug interaction extraction

Explainable Prediction of Medical Codes from Clinical Text

Decoupled Weight Decay Regularization

Squeeze-and-Excitation Networks

Multi-Label Classification of Patient Notes a Case Study on ICD Code Assignment

A Survey on Multi-Task Learning

Evolutionary Multi-task Learning for Modular Training of Feedforward Neural Networks

Deep sparse multi-task learning for feature selection in Alzheimer’s disease diagnosis

MIMIC-III, a freely accessible critical care database

Doctor AI: Predicting Clinical Events via Recurrent Neural Networks

Automatic ICD-10 classification of cancers from free-text death certificates

Deep Model Based Transfer and Multi-Task Learning for Biological Image Analysis

Adam: A Method for Stochastic Optimization

How transferable are features in deep neural networks?

Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation

Diagnosis code assignment: models and evaluation metrics

Distributed Representations of Words and Phrases and their Compositionality

On the importance of initialization and momentum in deep learning

An Improved Multi-task Learning Approach with Applications in Medical Diagnosis

Intelligent information: a national system for monitoring clinical performance.

Measuring diagnoses: ICD code accuracy.

The Accuracy of ICD codes for Cerebrovascular Diseases in Medical Insurance Claims

Combining classifiers in text categorization

Deep Patient Representation of Clinical Notes via Multi-Task Learning for Mortality Prediction.

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Towards Automated ICD Coding Using Deep Learning

Multitask

Field of Study