Precision medicine is at the forefront of biomedical research. Cancer registries provide rich perspectives and electronic health records (EHRs) 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, the 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 with 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 of the perspectives offered) are necessary to derive robust EHR-based precision medicine phenotypes.
Bibliographical noteFunding Information:
Acknowledgments. This work was supported by the National Cancer Institute-sponsored Mayo Clinic Cancer Genetic Epidemiology Training Program (R25 CA092049). The authors thank James R. Cerhan, MD, PhD, for the substantial editorial feedback provided in the development of this article. Further, the researchers thank the nurse abstraction group led by Wendy Gay for their contributions to chart review and cohort integrity assurance, and Xiaoyang Ruan, PhD, for assistance in deployment of natural language processing algorithms.
© 2017 The Authors. Clinical and Translational Science published by Wiley Periodicals, Inc. on behalf of American Society for Clinical Pharmacology and Therapeutics.