DeepAI AI Chat
Log In Sign Up

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

by   Han-Chin Shing, et al.
University of Maryland

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.


page 1

page 2

page 3

page 4


Multi-task Balanced and Recalibrated Network for Medical Code Prediction

Human coders assign standardized medical codes to clinical documents gen...

Entity Anchored ICD Coding

Medical coding is a complex task, requiring assignment of a subset of ov...

Multitask Recalibrated Aggregation Network for Medical Code Prediction

Medical coding translates professionally written medical reports into st...

Scholastic: Graphical Human-Al Collaboration for Inductive and Interpretive Text Analysis

Interpretive scholars generate knowledge from text corpora by manually s...

Entropic Measures of Complexity in a New Medical Coding System

Background: Transitioning from an old medical coding system to a new one...

AutoMap: Automatic Medical Code Mapping for Clinical Prediction Model Deployment

Given a deep learning model trained on data from a source site, how to d...

Document Image Coding and Clustering for Script Discrimination

The paper introduces a new method for discrimination of documents given ...