Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper addresses the complex challenge of medical coding by modeling it as a multi-label text classification task, leveraging a deep neural architecture that combines multi-layer temporal convolution networks (TCNs) with label-wise attention mechanisms. The proposed model effectively captures long-range dependencies in medical notes while allowing for focused attention on relevant sections for each diagnosis and procedure code. The results show a significant improvement over the previous state-of-the-art, with a 9% increase in F-1 scores and a notable 28% increase in recall, underscoring its potential impact on clinical decision support systems.
Achieving a 28% boost in recall for medical coding could transform how healthcare systems automate and improve diagnostic accuracy.
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.