Enhanced phenotypes for identifying opioid overdose in emergency department visit electronic health record data
JAMIA Open · 11.10.2023 · 6 (3)
DOI: 10.1093/jamiaopen/ooad081 ↗Kurz gefasst
Fachartikel in der Zeitschrift JAMIA Open, online erschienen am 11.09.2023. Verfasst von Ralph Ward und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Public Health Sciences, Medical University of South Carolina, Charleston, SC 29425, United States. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 16 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: NCATS NIH HHS, National Center for Advancing Translational Sciences of the National Institutes of Health.
Abstract (Originalsprache)
Background
Accurate identification of opioid overdose (OOD) cases in electronic healthcare record (EHR) data is an important element in surveillance, empirical research, and clinical intervention. We sought to improve existing OOD electronic phenotypes by incorporating new data types beyond diagnostic codes and by applying several statistical and machine learning methods. Materials and Methods We developed an EHR dataset of emergency department visits involving OOD cases or patients considered at risk for an OOD and ascertained true OOD status through manual chart reviews. We developed and validated prediction models using Random Forest, Extreme Gradient Boost, and Elastic Net models that incorporated 717 features involving primary and second diagnoses, chief complaints, medications prescribed, vital signs, laboratory results, and procedural codes. We also developed models limited to single data types.
Results
A total of 1718 records involving 1485 patients were manually reviewed; 541 (36.4%) patients had one or more OOD. Prediction performance was similar for all models; sensitivity varied from 94% to 97%; and area under the receiver operating characteristic curve (AUC) was 98% for all methods. The primary diagnosis and chief complaint were the most important contributors to AUC performance; primary diagnoses and medication class contributed most to sensitivity; chief complaint, primary diagnosis, and vital signs were most important for specificity. Models limited to decision support data types available in real time demonstrated robust prediction performance.
Conclusions
Substantial prediction performance improvements were demonstrated for identifying OODs in EHR data. Our e-phenotypes could be applied in surveillance, retrospective empirical applications, or clinical decision support systems.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Public Health Sciences, Medical University of South Carolina, Charleston, SC 29425, United States.
- Biomedical Informatics Center, Medical University of South Carolina, Charleston, SC 29425, United States.
- Department of Emergency Medicine, Medical University of South Carolina, Charleston, SC 29425, United States.
- College of Medicine, Medical University of South Carolina, Charleston, SC 29425, United States.
- School of Medicine, Mercer University, Macon, GA 31207, United States.
- School of Medicine, University of Texas Rio Grande Valley, Edinburg, TX 78539, United States.
ORCID-Profile: Ralph Ward, Jihad S Obeid
Förderung
- NCATS NIH HHS
- National Center for Advancing Translational Sciences of the National Institutes of Health
Zitieren
APA
Ward, R., Obeid, J. S., Jennings, L., Szwast, E., Hayes, W. G., Pipaliya, R., Bailey, C., Faul, S., Polyak, B., Baker, G. H., McCauley, J. L., & Lenert, L. A. (2023). Enhanced phenotypes for identifying opioid overdose in emergency department visit electronic health record data. JAMIA Open, 6(3). https://doi.org/10.1093/jamiaopen/ooad081
Vancouver
Ward R, Obeid JS, Jennings L, Szwast E, Hayes WG, Pipaliya R, et al. Enhanced phenotypes for identifying opioid overdose in emergency department visit electronic health record data. JAMIA Open. 2023;6(3). doi:10.1093/jamiaopen/ooad081
BibTeX
@article{Ward2023,
author = {Ward, Ralph and Obeid, Jihad S and Jennings, Lindsey and Szwast, Elizabeth and Hayes, William Garrett and Pipaliya, Royal and Bailey, Cameron and Faul, Skylar and Polyak, Brianna and Baker, George Hamilton and McCauley, Jenna L and Lenert, Leslie A},
title = {Enhanced phenotypes for identifying opioid overdose in emergency department visit electronic health record data},
journal = {JAMIA Open},
year = {2023},
volume = {6},
number = {3},
doi = {10.1093/jamiaopen/ooad081}
}
EUVIMED