Bias and fairness assessment of a natural language processing opioid misuse classifier: detection and mitigation of electronic health record data disadvantages across racial subgroups.

Journal: Journal of the American Medical Informatics Association : JAMIA

Published Date: Oct 12, 2021

OBJECTIVES: To assess fairness and bias of a previously validated machine learning opioid misuse classifier.

Hale M Thompson

Department of Psychiatry & Behavioral Sciences, Rush University Medical Center, Chicago, Illinois, USA.
Brihat Sharma

Department of Computer Science, Loyola University Chicago, Chicago, IL, USA.
Sameer Bhalla

Department of Psychiatry & Behavioral Sciences, Rush University Medical Center, Chicago, Illinois, USA.
Randy Boley

Department of Psychiatry & Behavioral Sciences, Rush University Medical Center, Chicago, Illinois, USA.
Connor McCluskey

Department of Psychiatry & Behavioral Sciences, Rush University Medical Center, Chicago, Illinois, USA.
Dmitriy Dligach

Department of Public Health Sciences, Stritch School of Medicine, Loyola University Chicago, Maywood, IL.
Matthew M Churpek

Department of Medicine, University of Wisconsin-Madison, Madison, WI, United States.
Niranjan S Karnik

Department of Psychiatry, Rush University Medical Center, Chicago, IL, USA.
Majid Afshar

Loyola University Chicago, Chicago, IL.

Electronic Health Records Hispanic or Latino Humans Machine Learning Natural Language Processing Opioid-Related Disorders

View on PubMed Access via DOI PubMed (34383925)