Prediction of Future Chronic Opioid Use Among Hospitalized Patients
Opioids are commonly prescribed in the hospital; yet, little is known about which patients will progress to chronic opioid therapy (COT) following discharge. We defined COT as receipt of ≥ 90-day supply of opioids with < 30-day gap in supply over a 180-day period or receipt of ≥ 10 opioid prescriptions over 1 year. Predictive tools to identify hospitalized patients at risk for future chronic opioid use could have clinical utility to improve pain management strategies and patient education during hospitalization and discharge.
The objective of this study was to identify a parsimonious statistical model for predicting future COT among hospitalized patients not on COT before hospitalization.
Retrospective analysis electronic health record (EHR) data from 2008 to 2014 using logistic regression.
Hospitalized patients at an urban, safety net hospital.
Independent variables included medical and mental health diagnoses, substance and tobacco use disorder, chronic or acute pain, surgical intervention during hospitalization, past year receipt of opioid or non-opioid analgesics or benzodiazepines, opioid receipt at hospital discharge, milligrams of morphine equivalents prescribed per hospital day, and others.
Model prediction performance was estimated using area under the receiver operator curve, accuracy, sensitivity, and specificity. A model with 13 covariates was chosen using stepwise logistic regression on a randomly down-sampled subset of the data. Sensitivity and specificity were optimized using the Youden’s index. This model predicted correctly COT in 79% of the patients and no COT correctly in 78% of the patients.
Our model accessed EHR data to predict 79% of the future COT among hospitalized patients. Application of such a predictive model within the EHR could identify patients at high risk for future chronic opioid use to allow clinicians to provide early patient education about pain management strategies and, when able, to wean opioids prior to discharge while incorporating alternative therapies for pain into discharge planning.
KEY WORDShospital medicine statistical modeling prediction rules
Funders: The authors would like to acknowledge the University of Colorado, Department of Medicine, Division of General Internal Medicine Small Grants Program for their generous grant which funded this project. Dr. Binswanger was supported by the National Institute On Drug Abuse of the National Institutes of Health under Award Numbers R34DA035952 and R01DA042059. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.
Prior Presentations: This work was presented at the National Society of General Internal Medicine Conference on April 21, 2017.
Compliance with Ethical Standards
This study was approved by the Colorado Multiple Institutional Review Board and adhered to the Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD) statement on reporting predictive models.21
Conflict of Interest
The authors declare that they do not have a conflict of interest.
- 1.Center for Behavioral Health Statistics and Quality, Results from the 2015 National Survey on Drug Use and Health 2016, Substance Abuse and Mental Health Services Administration: Rockville, MD. Available from: https://www.samhsa.gov/data/sites/default/files/NSDUH-DetTabs-2015/NSDUH-DetTabs-2015/NSDUH-DetTabs-2015.pdfAccessed 12/11/2017. Accessed 12/11/2017.
- 27.CDC, Classification of Diseases, Functioning, and Disability. 2013. Available from: https://www.cdc.gov/nchs/icd/index.htm. Accessed 12/11/2017.
- 29.Colorado, S.O., Colorado Amendment 20. Legalization of Medicinal Marijuana. 2000. Available from: https://www.colorado.gov/pacific/sites/default/files/CHEIS_MMJ_Colorado-Constitution-Article-XVIII.pdf. Accessed 12/11/2017.
- 35.Foundation, T.R. What is R? [cited 2017 11/3/2017]; Available from: https://www.r-project.org/about.html. Accessed 12/11/2017.
- 38.Inacio M. C., et al., Risk factors for persistent and new chronic opioid use in patients undergoing total hip arthroplasty: a retrospective cohort study. BMJ Open, 2016. 6(4): p. e010664.Google Scholar
- 43.Casanova R., et al., Prediction of incident diabetes in the Jackson Heart Study using high-dimensional machine learning. PLoS One, 2016. 11(10): p. e0163942.Google Scholar