Electronic Health Record Phenotypes for Precision Medicine: Perspectives and Caveats from Treatment of Breast Cancer at a Single Institution

Abstract

Precision medicine is at the forefront of biomedical research. Cancer registries provide rich perspectives and electronic health record(EHR)s are commonly utilized to gather additional clinical data elements needed for translational research. However, manual annotation is resource-intense and not readily scalable. Informatics-based phenotyping presents an ideal solution, but perspectives obtained can be impacted by both data source and algorithm selection. We derived breast cancer(BC) receptor status phenotypes from structured and unstructured EHR data using rule-based algorithms, including natural language processing(NLP). Overall, use of NLP increased BC receptor status coverage by 39.2% from 69.1% with structured medication information alone. Using all available EHR data, estrogen receptor-positive BC cases were ascertained with high precision(P = 0.976) and recall(R = 0.987) compared to gold standard chart-reviewed patients. However, status negation(R = 0.591), decreased 40.2% when relying on structured medications alone. Using multiple EHR data types (and thorough understanding perspectives offered) are necessary to derive robust EHR-based precision medicine phenotypes.

This article is protected by copyright. All rights reserved

http://ift.tt/2zT22bt