top of page

Natural Language Processing Tools to Identify Uncoded Opioid Abuse from EHRs

NLP Tools to Identify Uncoded Opioid Abuse from EHRS


Opioid misuse and dependence remain a major and escalating cause of preventable illness and death in the United States. In the last decade, there has been a significant rise in the number of people visiting emergency departments due to opioid-related overdoses, whether intentional or unintentional. Sadly, many of these individuals either die or experience another overdose within a year, and the public health expenses associated with opioid-related overdoses are substantial.


A clinical NLP pipeline has been developed through a collaborative effort between Melax Tech and the Medical University of South Carolina (MUSC). The primary objective of this pipeline is to detect cases of opioid overdose disorder (OOD) from ED notes. This innovative solution employs a blend of machine learning, deep learning, and context rules to identify uncoded OOD cases at the sentence level of EHR notes. The pipeline is designed to be incredibly versatile and easily customizable to meet the unique needs of various organizations.


The Accrual to Clinical Trials (ACT) Network has already implemented the NLP pipeline to assist in designing trials for emergency department (ED) patients who are opioid overdose survivors. Four institutions - the Medical University of South Carolina (MUSC), Dartmouth Medical School (DMS), University of Kentucky (UK), and University of California San Diego (UCSD) - collaborated to adapt the pipeline for use within the ACT network. To learn more about the NLP pipeline and its potential benefits, please request a demo today!

Details of the OOD NLP solution and ACT network progress can be found in this paper: Lenert LA, Zhu V, Jennings L, McCauley J, Obeid J, Ward R, Hassanpour S, Marsch LA, Hogarth M, Shipman P, Harris DR. Enhancing Research Data Infrastructure to Address the Opioid Epidemic: The Opioid Overdose Network (02-Net). medRxiv. 2021 Jan 1.

bottom of page