Opioid Prescribing for Opioid-Naive Patients in Emergency Departments and Other Settings: Characteristics of Prescriptions and Association With Long-Term Use

Abstract

Study objective: We explore the emergency department (ED) contribution to prescription opioid use for opioid-naive patients by comparing the guideline concordance of ED prescriptions with those attributed to other settings and the risk of patients' continuing long-term opioid use.

Methods: We used analysis of administrative claims data (OptumLabs Data Warehouse 2009 to 2015) of opioid-naive privately insured and Medicare Advantage (aged and disabled) beneficiaries to compare characteristics of opioid prescriptions attributed to the ED with those attributed to other settings. Concordance with Centers for Disease Control and Prevention (CDC) guidelines and rate of progression to long-term opioid use are reported.

Results: We identified 5.2 million opioid prescription fills that met inclusion criteria. Opioid prescriptions from the ED were more likely to adhere to CDC guidelines for dose, days' supply, and formulation than those attributed to non-ED settings. Disabled Medicare beneficiaries were the most likely to progress to long-term use, with 13.4% of their fills resulting in long-term use compared with 6.2% of aged Medicare and 1.8% of commercial beneficiaries' fills. Compared with patients in non-ED settings, commercial beneficiaries receiving opioid prescriptions in the ED were 46% less likely, aged Medicare patients 56% less likely, and disabled Medicare patients 58% less likely to progress to long-term opioid use.

Conclusion: Compared with non-ED settings, opioid prescriptions provided to opioid-naive patients in the ED were more likely to align with CDC recommendations. They were shorter, written for lower daily doses, and less likely to be for long-acting formulations. Prescriptions from the ED are associated with a lower risk of progression to long-term use.

Figure 1:

Cohort flow chart

Figure 2:. Risk ratios for outcomes by source of prescription

Risk ratios with non-ED prescription source as the reference category; bars indicate 95% confidence intervals. Com=commercial population; Mcr=Medicare; Disab.=Disabled; ER=Extended Release. Logistic regression with binary outcomes was performed with independent variables representing beneficiary characteristics: beneficiary category (Commercial, aged Medicare, disabled Medicare); year of fill (continuous); beneficiary age, age-squared, age-cubed; indicators for each Elixhauser comorbidity and whether the beneficiary had any medical claims in the 6 months before the fill; female sex; and race/ethnicity. Adjusted proportions meeting each outcome were calculated for each beneficiary group using Stata’s marginal effects commands. Risk ratios were calculated from these adjusted proportions, with 95% CIs calculated using Stata’s nlcom command, which uses the delta method to produce standard errors.