Multi-Label Classification of Patient Notes a Case Study on ICD Code Assignment
arXiv:1709.09587
Abstract
In the context of the Electronic Health Record, automated diagnosis coding of patient notes is a useful task, but a challenging one due to the large number of codes and the length of patient notes. We investigate four models for assigning multiple ICD codes to discharge summaries taken from both MIMIC II and III. We present Hierarchical Attention-GRU (HA-GRU), a hierarchical approach to tag a document by identifying the sentences relevant for each label. HA-GRU achieves state-of-the art results. Furthermore, the learned sentence-level attention layer highlights the model decision process, allows easier error analysis, and suggests future directions for improvement.
References in corpus (6)
- Learning to Diagnose with LSTM Recurrent Neural Networks
- DyNet: The Dynamic Neural Network Toolkit
- Doctor AI: Predicting Clinical Events via Recurrent Neural Networks
- Effective Use of Word Order for Text Categorization with Convolutional Neural Networks
- Structured prediction models for RNN based sequence labeling in clinical text
- Hierarchical Question Answering for Long Documents
Cited by in corpus (10)
- Deep EHR: Chronic Disease Prediction Using Medical Notes
- A Neural Topic-Attention Model for Medical Term Abbreviation Disambiguation
- Read, Attend, and Code: Pushing the Limits of Medical Codes Prediction from Clinical Notes by Machines
- Improved Hierarchical Patient Classification with Language Model Pretraining over Clinical Notes
- Multitask Recalibrated Aggregation Network for Medical Code Prediction
- Predicting Multiple ICD-10 Codes from Brazilian-Portuguese Clinical Notes
- Interpretable ICD Code Embeddings with Self- and Mutual-Attention Mechanisms
- DeepTag: inferring all-cause diagnoses from clinical notes in under-resourced medical domain
- Inheritance-guided Hierarchical Assignment for Clinical Automatic Diagnosis
- Graph-Driven Generative Models for Heterogeneous Multi-Task Learning