Control Matching via Discharge Code Sequences

TL;DR

This paper introduces a novel patient matching method using Word2Vec embeddings of discharge codes and a sequential matching algorithm, significantly improving accuracy in a large cancer patient cohort.

Contribution

The paper presents a new approach combining Word2Vec embeddings with sequential matching for patient similarity, enhancing accuracy over traditional methods.

Findings

Improved matching accuracy on clinical outcomes.

Effective large-scale application with over 220,000 patients.

Relevance for codified clinical information datasets.

Abstract

In this paper, we consider the patient similarity matching problem over a cancer cohort of more than 220,000 patients. Our approach first leverages on Word2Vec framework to embed ICD codes into vector-valued representation. We then propose a sequential algorithm for case-control matching on this representation space of diagnosis codes. The novel practice of applying the sequential matching on the vector representation lifted the matching accuracy measured through multiple clinical outcomes. We reported the results on a large-scale dataset to demonstrate the effectiveness of our method. For such a large dataset where most clinical information has been codified, the new method is particularly relevant.