Writing habits and telltale neighbors: analyzing clinical concept usage patterns with sublanguage embeddings

TL;DR

This paper introduces a method using sublanguage embeddings to analyze and compare clinical concept usage patterns across different types of electronic health records, revealing meaningful semantic differences.

Contribution

It presents a novel approach for characterizing clinical concept usage differences through embedding neighborhood analysis, enhancing understanding of document type distinctions.

Findings

Captures clinically relevant concept usage differences

Provides an intuitive exploration tool for clinical document collections

Demonstrates effectiveness on MIMIC-III corpus

Abstract

Natural language processing techniques are being applied to increasingly diverse types of electronic health records, and can benefit from in-depth understanding of the distinguishing characteristics of medical document types. We present a method for characterizing the usage patterns of clinical concepts among different document types, in order to capture semantic differences beyond the lexical level. By training concept embeddings on clinical documents of different types and measuring the differences in their nearest neighborhood structures, we are able to measure divergences in concept usage while correcting for noise in embedding learning. Experiments on the MIMIC-III corpus demonstrate that our approach captures clinically-relevant differences in concept usage and provides an intuitive way to explore semantic characteristics of clinical document collections.