Multiple Factors Drive Opioid Prescribing at the Time of Discharge

Research output: Contribution to journalArticle

Abstract

Multiple factors potentially influence pain intensity or frequency, and consequently the need for an opioid prescription. This study aims to identify factors associated with being discharged with an outpatient opioid prescription. We constructed a database containing clinical, non-clinical, and organizational variables from the EHR that are potentially relevant for ordering an opioid at discharge. Descriptive statistics of these variables and univariate association analysis reveal that all of the examined variables to be statistically significantly associated with opioid prescription at discharge. Further, we fitted a random forest model to examine the information content in the examined variables regarding whether a patient will be discharged with an opioid. The model resulted in a mean AUC of 0.84, suggesting the factors examined in this study in combination contain significant information regarding prescription of an opioid at discharge.

Original languageEnglish (US)
Pages (from-to)916-921
Number of pages6
JournalAMIA ... Annual Symposium proceedings. AMIA Symposium
Volume2018
StatePublished - Jan 1 2018

Fingerprint

Opioid Analgesics
Prescriptions
Area Under Curve
Drive
Outpatients
Databases
Pain

Cite this

@article{92b8e7af8aad4f879c632f2cb2ffe29c,
title = "Multiple Factors Drive Opioid Prescribing at the Time of Discharge",
abstract = "Multiple factors potentially influence pain intensity or frequency, and consequently the need for an opioid prescription. This study aims to identify factors associated with being discharged with an outpatient opioid prescription. We constructed a database containing clinical, non-clinical, and organizational variables from the EHR that are potentially relevant for ordering an opioid at discharge. Descriptive statistics of these variables and univariate association analysis reveal that all of the examined variables to be statistically significantly associated with opioid prescription at discharge. Further, we fitted a random forest model to examine the information content in the examined variables regarding whether a patient will be discharged with an opioid. The model resulted in a mean AUC of 0.84, suggesting the factors examined in this study in combination contain significant information regarding prescription of an opioid at discharge.",
author = "Lisiane Pruinelli and Sisi Ma and Westra, {Bonnie L.} and Johnson, {Steven G.} and {O'Conner Von}, Susan and Speedie, {Stuart M.}",
year = "2018",
month = "1",
day = "1",
language = "English (US)",
volume = "2018",
pages = "916--921",
journal = "AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium",
issn = "1559-4076",
publisher = "American Medical Informatics Association",

}

TY - JOUR

T1 - Multiple Factors Drive Opioid Prescribing at the Time of Discharge

AU - Pruinelli, Lisiane

AU - Ma, Sisi

AU - Westra, Bonnie L.

AU - Johnson, Steven G.

AU - O'Conner Von, Susan

AU - Speedie, Stuart M.

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Multiple factors potentially influence pain intensity or frequency, and consequently the need for an opioid prescription. This study aims to identify factors associated with being discharged with an outpatient opioid prescription. We constructed a database containing clinical, non-clinical, and organizational variables from the EHR that are potentially relevant for ordering an opioid at discharge. Descriptive statistics of these variables and univariate association analysis reveal that all of the examined variables to be statistically significantly associated with opioid prescription at discharge. Further, we fitted a random forest model to examine the information content in the examined variables regarding whether a patient will be discharged with an opioid. The model resulted in a mean AUC of 0.84, suggesting the factors examined in this study in combination contain significant information regarding prescription of an opioid at discharge.

AB - Multiple factors potentially influence pain intensity or frequency, and consequently the need for an opioid prescription. This study aims to identify factors associated with being discharged with an outpatient opioid prescription. We constructed a database containing clinical, non-clinical, and organizational variables from the EHR that are potentially relevant for ordering an opioid at discharge. Descriptive statistics of these variables and univariate association analysis reveal that all of the examined variables to be statistically significantly associated with opioid prescription at discharge. Further, we fitted a random forest model to examine the information content in the examined variables regarding whether a patient will be discharged with an opioid. The model resulted in a mean AUC of 0.84, suggesting the factors examined in this study in combination contain significant information regarding prescription of an opioid at discharge.

UR - http://www.scopus.com/inward/record.url?scp=85062381916&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062381916&partnerID=8YFLogxK

M3 - Article

VL - 2018

SP - 916

EP - 921

JO - AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium

JF - AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium

SN - 1559-4076

ER -