Using natural language processing of clinical text to enhance identification of opioid-related overdoses in electronic health records data.

Journal: Pharmacoepidemiology and drug safety

PMID: 31218780

Abstract

PURPOSE: To enhance automated methods for accurately identifying opioid-related overdoses and classifying types of overdose using electronic health record (EHR) databases.

Authors

Brian Hazlehurst

Center for Health Research, Kaiser Permanente Northwest, Portland, OR.
Carla A Green

Center for Health Research, Kaiser Permanente Northwest, Portland, OR.
Nancy A Perrin

Center for Health Research, Kaiser Permanente Northwest, Portland, OR.
John Brandes

Center for Health Research, Kaiser Permanente Northwest, Portland, OR.
David S Carrell

Group Health Research Institute, Seattle, WA, 98101, USA.
Andrew Baer

Kaiser Permanente of Washington Health Research Institute (formerly Group Health Research Institute), Seattle, WA, USA.
Angela DeVeaugh-Geiss

Epidemiology, Medical Affairs, Purdue Pharma, LP, Stamford, CT.
Paul M Coplan

Epidemiology, Medical Affairs, Purdue Pharma, LP, Stamford, CT.

Keywords

Analgesics, Opioid Datasets as Topic Drug Overdose Electronic Health Records Heroin Humans Natural Language Processing Opioid-Related Disorders Predictive Value of Tests Risk Self-Injurious Behavior Sensitivity and Specificity Washington

External Resources

View on PubMed Access via DOI PubMed (31218780)

Using natural language processing of clinical text to enhance identification of opioid-related overdoses in electronic health records data.

Abstract

Authors

Keywords

External Resources

Popular Topics

Recent Journals