Deep Label-Wise Attentive Temporal Convolutional Networks Improve Medical Coding

A deep neural model combining multi-layer temporal convolution networks with label-wise attention improves medical coding accuracy, achieving a 9% increase in F-1 scores and a 28% increase in recall over the previous state-of-the-art, according to a new arXiv preprint (2607.25129v1). The model addresses the challenge of aggregating information from different parts of clinical notes for each diagnosis and procedure code.

arXiv:2607.25129v1 Announce Type: new 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.