Evaluating electronic health record data sources and algorithmic approaches to identify hypertensive individuals.

Teixeira PL, Wei WQ, Cronin RM, Mo H, VanHouten JP, Carroll RJ, LaRose E, Bastarache LA, Rosenbloom ST, Edwards TL, Roden DM, Lasko TA, Dart RA, Nikolai AM, Peissig PL, Denny JC
J Am Med Inform Assoc. 2017 24 (1): 162-171

PMID: 27497800 · PMCID: PMC5201185 · DOI:10.1093/jamia/ocw071

OBJECTIVE - Phenotyping algorithms applied to electronic health record (EHR) data enable investigators to identify large cohorts for clinical and genomic research. Algorithm development is often iterative, depends on fallible investigator intuition, and is time- and labor-intensive. We developed and evaluated 4 types of phenotyping algorithms and categories of EHR information to identify hypertensive individuals and controls and provide a portable module for implementation at other sites.

MATERIALS AND METHODS - We reviewed the EHRs of 631 individuals followed at Vanderbilt for hypertension status. We developed features and phenotyping algorithms of increasing complexity. Input categories included International Classification of Diseases, Ninth Revision (ICD9) codes, medications, vital signs, narrative-text search results, and Unified Medical Language System (UMLS) concepts extracted using natural language processing (NLP). We developed a module and tested portability by replicating 10 of the best-performing algorithms at the Marshfield Clinic.

RESULTS - Random forests using billing codes, medications, vitals, and concepts had the best performance with a median area under the receiver operator characteristic curve (AUC) of 0.976. Normalized sums of all 4 categories also performed well (0.959 AUC). The best non-NLP algorithm combined normalized ICD9 codes, medications, and blood pressure readings with a median AUC of 0.948. Blood pressure cutoffs or ICD9 code counts alone had AUCs of 0.854 and 0.908, respectively. Marshfield Clinic results were similar.

CONCLUSION - This work shows that billing codes or blood pressure readings alone yield good hypertension classification performance. However, even simple combinations of input categories improve performance. The most complex algorithms classified hypertension with excellent recall and precision.

© The Author 2016. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For Permissions, please email: journals.permissions@oup.com.

MeSH Terms (15)

Aged Algorithms Blood Pressure Determination Clinical Coding Electronic Health Records Female Humans Hypertension Information Storage and Retrieval Machine Learning Male Middle Aged Natural Language Processing Phenotype ROC Curve

Connections (3)

This publication is referenced by other Labnodes entities:

Links