Description
Accurate surveillance is needed to combat the growing opioid epidemic. To investigate the potential volume of missed opioid overdoses, we compare overdose encounters identified by ICD-10-CM codes and an NLP pipeline from two different medical systems. Our results show that the NLP pipeline identified a larger percentage of OOD encounters than ICD-10-CM codes. Thus, incorporating sophisticated NLP techniques into current diagnostic methods has the potential to improve surveillance on the incidence of opioid overdoses.
Learning Objective: Attendees will be able to identify attributes utilized by NLP to identify opioid overdose encounters in the emergency department from clinical notes.
Authors:
Amy Olex (Presenter)
Virginia Commonwealth University
Tamas Gal, Virginia Commonwealth University
Majid Afshar, Loyola University Chicago
Dmitriy Dligach, Loyola University Chicago
Niranjan Karnik, Rush University
Travis Oakes, Virginia Commonwealth University
Brihat Sharma, Loyola University Chicago
Meng Xie, Loyola University Chicago
Bridget McInnes, Virginia Commonwealth University
Julian Solway, University of Chicago
Abel Kho, Northwestern Medicine
William Cramer, Virginia Commonwealth University
F. Moeller, Virginia Commonwealth University
Presentation Materials: