Interpretable ICD Code Embeddings with Self- and Mutual-Attention Mechanisms
This work addresses the need for interpretable and accurate embeddings in healthcare informatics, specifically for ICD code representation, though it is incremental as it builds on existing attention-based methods.
The authors tackled the problem of representing ICD codes for clinical procedure recommendation by developing an interpretable embedding method that uses self- and mutual-attention mechanisms, achieving state-of-the-art performance in procedure recommendation.
We propose a novel and interpretable embedding method to represent the international statistical classification codes of diseases and related health problems (i.e., ICD codes). This method considers a self-attention mechanism within the disease domain and a mutual-attention mechanism jointly between diseases and procedures. This framework captures the clinical relationships between the disease codes and procedures associated with hospital admissions, and it predicts procedures according to diagnosed diseases. A self-attention network is learned to fuse the embeddings of the diseases for each admission. The similarities between the fused disease embedding and the procedure embeddings indicate which procedure should potentially be recommended. Additionally, when learning the embeddings of the ICD codes, the optimal transport between the diseases and the procedures within each admission is calculated as a regularizer of the embeddings. The optimal transport provides a mutual-attention map between diseases and the procedures, which suppresses the ambiguity within their clinical relationships. The proposed method achieves clinically-interpretable embeddings of ICD codes, and outperforms state-of-the-art embedding methods in procedure recommendation.