Evaluation of Embeddings of Laboratory Test Codes for Patients at a Cancer Center

TL;DR

This study trains and evaluates embeddings of laboratory test codes from EHR data at a cancer center, assessing their clinical relevance and utility in mortality prediction.

Contribution

It introduces embedding representations for LOINC codes, including outcome information, and evaluates their clinical similarity and predictive performance.

Findings

Embeddings show meaningful clinical similarities.

Including outcome info improves mortality prediction.

Embeddings preserve ordinality of test results.

Abstract

Laboratory test results are an important and generally high dimensional component of a patient's Electronic Health Record (EHR). We train embedding representations (via Word2Vec and GloVe) for LOINC codes of laboratory tests from the EHRs of about 80,000 patients at a cancer center. To include information about lab test outcomes, we also train embeddings on the concatenation of a LOINC code with a symbol indicating normality or abnormality of the result. We observe several clinically meaningful similarities among LOINC embeddings trained over our data. For the embeddings of the concatenation of LOINCs with abnormality codes, we evaluate the performance for mortality prediction tasks and the ability to preserve ordinality properties: i.e. a lab test with normal outcome should be more similar to an abnormal one than to the a very abnormal one.