Deep Label-Wise Attentive Temporal Convolutional Networks Improve Medical Coding

2026/07/27 by Muhammed Yavuz Nuzumlalı, Alexander Fabbri, Irene Li +1
#cs.CL #cs.LG

paper · pdf

Abstract

Medical coding is the task of assigning a set of diagnosis and procedure codes for a hospitalization using recorded notes. It requires aggregating information from different parts of the text and focus to different sections for each individual code, making it a very difficult problem even for professional human coders. We model the task as a multi-label text classification problem. To overcome the mentioned difficulties, we propose a deep neural model consisting of a multi-layer temporal convolution network (TCN) followed by label-wise attention. While multi-layer TCN helps extract a global document representation with the ability to learn relations over very long sequences, label-specific attention mechanism allows the model to focus on different aspects of the same document for each individual label. Our method achieves significantly better F-1 scores (9% increase) compared to the previous state-of-the-art model, with a remarkable increase in recall score (28% increase), which we believe is the more important metric for a clinical decision support setting.

Citations

• Multimodal Machine Learning for Automated ICD Coding
• On the Importance of Attention in Meta-Learning for Few-Shot Text Classification
• Joint Embedding of Words and Labels for Text Classification
• An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
• Explainable Prediction of Medical Codes from Clinical Text
• Multi-Label Classification of Patient Notes a Case Study on ICD Code Assignment
• Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks
• Adam: A Method for Stochastic Optimization
• Distributed Representations of Words and Phrases and their Compositionality

Related

• Explainable Automated Coding of Clinical Notes using Hierarchical Label-wise Attention Networks and Label Embedding Initialisation
• An Automatic ICD Coding Network Using Partition-Based Label Attention
• An Explainable CNN Approach for Medical Codes Prediction from Clinical Text
• Medical code prediction with multi-view convolution and description-regularized label-dependent attention
• Explainable Prediction of Medical Codes from Clinical Text