Elsevier

The Spine Journal

Volume 20, Issue 6, June 2020, Pages 888-895
The Spine Journal

Clinical Study
Predicting prolonged opioid prescriptions in opioid-naïve lumbar spine surgery patients

https://doi.org/10.1016/j.spinee.2019.12.019Get rights and content

Abstract

IMPORTANCE

Preoperative determination of the potential for postoperative opioid dependence in previously naïve patients undergoing elective spine surgery may facilitate targeted interventions.

OBJECTIVE

The purpose of this study was to develop supervised machine learning algorithms for preoperative prediction of prolonged opioid prescription use in opioid-naïve patients following lumbar spine surgery.

DESIGN

Retrospective review of clinical registry data. Variables considered for prediction included demographics, insurance status, preoperative medications, surgical factors, laboratory values, comorbidities, and neighborhood characteristics. Five supervised machine learning algorithms were developed and assessed by discrimination, calibration, Brier score, and decision curve analysis.

SETTING

One healthcare entity (two academic medical centers, three community hospitals), 2000 to 2018.

PARTICIPANTS

Opioid-naïve patients undergoing decompression and/or fusion for lumbar disk herniation, stenosis, and spondylolisthesis.

MAIN OUTCOME

Sustained prescription opioid use exceeding 90 days after surgery.

RESULTS

Overall, of 8,435 patients included, 359 (4.3%) were found to have prolonged postoperative opioid prescriptions. The elastic-net penalized logistic regression achieved the best performance in the independent testing set not used for algorithm development with c-statistic=0.70, calibration intercept=0.06, calibration slope=1.02, and Brier score=0.039. The five most important factors for prolonged opioid prescriptions were use of instrumented spinal fusion, preoperative benzodiazepine use, preoperative antidepressant use, preoperative gabapentin use, and uninsured status. Individual patient-level explanations were provided for the algorithm predictions and the algorithms were incorporated into an open access digital application available here: https://sorg-apps.shinyapps.io/lumbaropioidnaive/.

CONCLUSION AND RELEVANCE

The clinician decision aid developed in this study may be helpful to preoperatively risk-stratify opioid-naïve patients undergoing lumbar spine surgery. The tool demonstrates moderate discriminative capacity for identifying those at greatest risk of prolonged prescription opioid use. External validation is required to further support the potential utility of this tool in practice.

Introduction

Mortality from unintentional drug overdoses is now the second-leading cause of accidental death in the United States [1]. In 2016, over 2 million individuals carried the diagnosis of an opioid use disorder and the majority of illicit heroin users started with prescription opioids [2,3]. The postoperative period after elective surgical procedures has been identified as a high-risk time for the development of opioid dependence, and orthopedic and neurosurgery patients have the highest rate of chronic opioid use [4], [5], [6], [7].

Prior studies of lumbar spine surgery patients have identified risk factors for prolonged postoperative use, but few studies have specifically studied opioid-naïve patients [8], [9], [10], [11], [12], [13], [14], [15], [16], [17], [18]. Furthermore, to our knowledge, there are no preoperative clinical decision aids available for risk-stratifying opioid-naïve patients with respect to the predilection for sustained prescription opioid use following a lumbar spine operation.

The purpose of this study was to develop a clinical decision aid for opioid-naïve patients undergoing lumbar spine surgery for disk herniation, stenosis, or spondylolisthesis. The utility of supervised machine learning algorithms was investigated for this predictive analytic task and the best performing algorithm was then deployed to allow for both prediction and an in-depth explanation of the quantified risk at the individual patient level.

Section snippets

Guidelines

The TRIPOD guidelines and the Guidelines for Developing and Reporting Machine Learning Models in Biomedical Research were followed for this analysis [19,20].

Data source

Institutional review board approval was granted for retrospective review of electronic health records at five medical centers affiliated with one healthcare entity. Criteria for inclusion were: (1) adult patients 18 years of age or older; (2) primary procedure of lumbar decompression with or without fusion between January 1, 2000 and May 1,

Results

Overall, 8,435 patients who were opioid-naïve before surgery were included in this investigation. Of these cases, the plurality underwent surgery for lumbar disk herniation (n=3,252, 38.6%), stenosis (n=3,052, 36.2%), or spondylolisthesis (n=1,840, 21.8%). Of these patients, 3,900 (46.2%) were female and the median age was 60 years (interquartile range=46–71; Table 1). The rate of sustained prescription opioid use (based on our operational definition) was 4.3% (n=359). Rates of prolonged

Discussion

Elective lumbar spine surgery in opioid-naïve patients may result in sustained prescription opioid use in nearly 1 in every 20 patients. Although this rate of sustained postoperative opioid use pales in comparison to that among preoperative opioid users [[11], [12], [13],18], the opioid-naïve population may be the most responsive to any preoperative interventions intended to prevent this adverse outcome. Furthermore, the risk of opioid dependence may be considered for inclusion in preoperative

Conclusion

The clinician decision aid developed in this study may be helpful to preoperatively risk-stratify opioid-naïve patients undergoing lumbar spine surgery. The tool demonstrates moderate discriminative capacity for identifying those at greatest risk of prolonged prescription opioid use. External validation is required to further support the potential utility of this tool in practice.

Acknowledgment

The authors report no funding disclosures for this study.

References (28)

  • S Okie

    A flood of opioids, a rising tide of deaths

    N Engl J Med

    (2010)
  • W Zhu et al.

    Initial opioid prescriptions among U.S. commercially insured patients, 2012-2017

    N Engl J Med

    (2019)
  • TJ Cicero et al.

    The changing face of heroin use in the United States: a retrospective analysis of the past 50 years

    JAMA Psychiatry

    (2014)
  • CM Brummett et al.

    New persistent opioid use after minor and major surgical procedures in US adults

    JAMA Surg

    (2017)
  • H Clarke et al.

    Rates and risk factors for prolonged opioid use after major surgery: population based cohort study

    BMJ

    (2014)
  • EC Sun et al.

    Incidence of and risk factors for chronic opioid use among opioid-naive patients in the postoperative period

    JAMA Intern Med

    (2016)
  • X Jiang et al.

    Chronic opioid usage in surgical patients in a large academic center

    Ann Surg

    (2017)
  • JT Anderson et al.

    Chronic opioid therapy after lumbar fusion surgery for degenerative disc disease in a workers' compensation setting

    Spine (Phila Pa 1976)

    (2015)
  • J Connolly et al.

    Predictors of long-term opioid use following lumbar fusion surgery

    Spine (Phila Pa 1976)

    (2017)
  • N Jain et al.

    Preoperative chronic opioid therapy: a risk factor for complications, readmission, continued opioid use and increased costs after one- and two-level posterior lumbar fusion

    Spine (Phila Pa 1976)

    (2018)
  • P Kalakoti et al.

    Opioid utilization following lumbar arthrodesis: trends and factors associated with long-term use

    Spine (Phila Pa 1976)

    (2018)
  • AV Karhade et al.

    Validating the stopping opioids after surgery (SOS) score for sustained postoperative prescription opioid use in spine surgical patients

    Spine J

    (2019)
  • AV Karhade et al.

    Development of machine learning algorithms for prediction of prolonged opioid prescription after surgery for lumbar disc herniation

    Spine J

    (2019)
  • D Lee et al.

    Preoperative opioid use as a predictor of adverse postoperative self-reported outcomes in patients undergoing spine surgery

    J Bone Joint Surg Am

    (2014)
  • Cited by (46)

    • Association of cash payment with intensity of opioid prescriptions

      2022, Journal of the American Pharmacists Association
    • Predicting persistent opioid use after surgery using electronic health record and patient-reported data

      2022, Surgery (United States)
      Citation Excerpt :

      Because the type of information conveyed as part of opioid counseling may differ substantially for opioid-naive and non-naive patients, being able to risk-stratify both groups of patients effectively is important to developing treatment pathways. Prior research in the development of models to predict POU has not evaluated model performance in both opioid-naive and non-naive patients, has been hindered by small sample sizes,16–20 used claims data only,21 was restricted to a military population,22 and has not been linked to prescription drug monitoring systems. Additionally, no prior models used patient-reported measures of subjective experience of pain and stress at the time of surgery.

    View all citing articles on Scopus

    FDA device/drug status: Not applicable.

    Author disclosures: AVK: Nothing to disclose. TDC: Consulting: GE Healthcare (B), NuVasive, K2M (B), Bio2 (B). HAF: Nothing to disclose. SHH: Nothing to disclose. DGT: Nothing to disclose. AJS: Royalties: Wolters Kluwer, Springer (B); Consulting: ArborMetrix (C); Trips/Travel: JBJS (A); Other Office: Journal of Bone and Joint Surgery (C); Research Support - Staff and/or Materials: CMS (D, Paid directly to institution/employer); Grants: Department of Defense (D, Paid directly to institution/employer), OREF (D, Paid directly to institution/employer), NIH (F, Paid directly to institution/employer). CMB: Royalties: Wolters Kluwer (A), Elsevier (B); Consulting: United Health Care (B); Other Office: The Spine Journal (D); Fellowship Support: OMEGA (D, Paid directly to institution/employer). JHS: Scientific Advisory Board: Chordoma Foundation (None); Speaking and/or Teaching Arrangements: AO Spine (Travel Expense Reimbursement), Stryker Spine (B).

    Ethics statement: This study was approved by our institutional review board.

    View full text