# Assigning Medical Codes at the Encounter Level by Paying Attention to Documents

arXiv: https://arxiv.org/abs/1911.06848 · HTML: https://mlsanity.com/paper/1911.06848/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Nov 2019.

## Built on by (most cited first, 2 of 2)

- [Neural Natural Language Processing for Unstructured Data in Electronic Health Records: a Review](https://mlsanity.com/paper/2107.02975/) (2021)
- [Entity Anchored ICD Coding](https://mlsanity.com/paper/2208.07444/) (2022)

## Abstract (arXiv)

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.