Aditya V Karhade1, Thomas D Cha2, Harold A Fogel2, Stuart H Hershman2, Daniel G Tobert2, Andrew J Schoenfeld3, Christopher M Bono2, Joseph H Schwab4. 1. Department of Orthopedic Surgery, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA; Department of Orthopedic Surgery, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA. 2. Department of Orthopedic Surgery, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA. 3. Department of Orthopedic Surgery, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA. 4. Department of Orthopedic Surgery, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA. Electronic address: jhschwab@mgh.harvard.edu.
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.
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.
Authors: Iraklis E Tseregounis; Daniel J Tancredi; Susan L Stewart; Aaron B Shev; Andrew Crawford; James J Gasper; Garen Wintemute; Brandon D L Marshall; Magdalena Cerdá; Stephen G Henry Journal: Med Care Date: 2021-12-01 Impact factor: 2.983
Authors: Katherine E Pierce; Bhaveen H Kapadia; Sara Naessig; Waleed Ahmad; Shaleen Vira; Carl Paulino; Michael Gerling; Peter G Passias Journal: Int J Spine Surg Date: 2021-12
Authors: Chandrasekar Gopalakrishnan; Rishi J Desai; Jessica M Franklin; Yinzhu Jin; Joyce Lii; Daniel H Solomon; Jeffrey N Katz; Yvonne C Lee; Patricia D Franklin; Seoyoung C Kim Journal: Arthritis Care Res (Hoboken) Date: 2022-04-22 Impact factor: 5.178
Authors: Sarah A Palumbo; Kayleigh M Adamson; Sarathbabu Krishnamurthy; Shivani Manoharan; Donielle Beiler; Anthony Seiwell; Colt Young; Raghu Metpally; Richard C Crist; Glenn A Doyle; Thomas N Ferraro; Mingyao Li; Wade H Berrettini; Janet D Robishaw; Vanessa Troiani Journal: JAMA Netw Open Date: 2020-09-01
Authors: Daniel Lubelski; Andrew Hersh; Tej D Azad; Jeff Ehresman; Zachary Pennington; Kurt Lehner; Daniel M Sciubba Journal: Global Spine J Date: 2021-04