Assigning Medical Codes at the Encounter Level by Paying Attention to Documents
This addresses a real-world medical coding challenge for healthcare professionals, but it is incremental as it adapts existing attention mechanisms to a specific hierarchical structure.
The paper tackles the problem of assigning medical codes at the clinical encounter level, which involves multiple documents, by introducing encounter-level document attention networks. The result shows improvements in coding accuracy and helps human reviewers identify relevant documents, though no concrete numbers are provided in the abstract.
The vast majority of research in computer assisted medical coding focuses on coding at the document level, but a substantial proportion of medical coding in the real world involves coding at the level of clinical encounters, each of which is typically represented by a potentially large set of documents. We introduce encounter-level document attention networks, which use hierarchical attention to explicitly take the hierarchical structure of encounter documentation into account. Experimental evaluation demonstrates improvements in coding accuracy as well as facilitation of human reviewers in their ability to identify which documents within an encounter play a role in determining the encounter level codes.