Natural language processing tool for extracting information about opioid overdoses in the USA from case narratives in the violent death reporting system
Injury Prevention · 2026
DOI: 10.1136/ip-2024-045314 ↗Kurz gefasst
Fachartikel in der Zeitschrift Injury Prevention, 2026. Verfasst von Elise Omaki und 3 weiteren Autor:innen. Beteiligte Einrichtung: Johns Hopkins Center for Injury Research and Policy, Johns Hopkins Bloomberg School of Public Health, Baltimore, Maryland, USA eperry@jhu.edu. Hauptthemen laut MEDLINE: Natural Language Processing, Opiate Overdose, Drug Overdose, Violence. Die Arbeit nennt 16 Literaturangaben. Gefördert von: Johns Hopkins University, American Public Health Association.
Abstract (Originalsprache)
Background
Improving the infrastructure for drug overdose surveillance is critical for identifying new threats and responding to emerging trends. We aimed to develop a prototype tool using the principles of natural language processing that can extract information from the death records of drug overdose victims.
Methods
Data were obtained from the Violent Death Reporting System on drug overdose deaths. Narratives were manually labelled for 12 attributes of interest, totalling 82 labels about the circumstances of the overdose. Narratives were passed through the ‘Excel Extractor’ to identify and extract a target phrase and subsequently map the extracted phrase to predetermined code values. The output from the Excel Extractor was compared with manually labelled data to determine accuracy. Performance was compared against multiple machine learning models.
Results
The Excel Extractor performed well across the attributes of interest, achieving an F1 Score over 0.8 on nine of the 12 attributes. The Excel Extractor was the highest performing model on seven of the 12 attributes. The Excel Extractor achieved an F1 Score of 0.8 or higher on 46 of 82 (56%) of the labels, and a score of 0.9 or higher on nearly one-third (25 out of 82) of the labels.
Conclusion
This work demonstrates it is feasible to develop a spreadsheet-formula-based natural language processing tool to accurately extract information about drug overdose deaths from narratives; for most attributes, a rule-based search performs well or better than deep learning. The Excel Extractor has the potential to streamline data abstraction for epidemiologists gathering data about drug overdose deaths.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Johns Hopkins Center for Injury Research and Policy, Johns Hopkins Bloomberg School of Public Health, Baltimore, Maryland, USA eperry@jhu.edu.
- Virginia Tech, Blacksburg, Virginia, USA.
- Johns Hopkins Center for Injury Research and Policy, Johns Hopkins Bloomberg School of Public Health, Baltimore, Maryland, USA.
- Business Information Technology, Virginia Tech, Blacksburg, Virginia, USA.
Förderung
- Johns Hopkins University
- American Public Health Association
Zitieren
APA
Omaki, E., Restrepo, F., Shields, W. C., & Abrahams, A. (2026). Natural language processing tool for extracting information about opioid overdoses in the USA from case narratives in the violent death reporting system. Injury Prevention. https://doi.org/10.1136/ip-2024-045314
Vancouver
Omaki E, Restrepo F, Shields WC, Abrahams A. Natural language processing tool for extracting information about opioid overdoses in the USA from case narratives in the violent death reporting system. Injury Prevention. 2026. doi:10.1136/ip-2024-045314
BibTeX
@article{Omaki2026,
author = {Omaki, Elise and Restrepo, Felipe and Shields, Wendy C and Abrahams, Alan},
title = {Natural language processing tool for extracting information about opioid overdoses in the USA from case narratives in the violent death reporting system},
journal = {Injury Prevention},
year = {2026},
doi = {10.1136/ip-2024-045314}
}
EUVIMED