Patient-Reported Data Augment Prediction Models of Persistent Opioid Use after Elective Upper Extremity Surgery.

MedStar author(s):
Citation: Plastic & Reconstructive Surgery. 152(2):358e-366e, 2023 Aug 01.PMID: 36780362Institution: Curtis National Hand Center | Curtis National Hand Center | MedStar Health Research Institute | MedStar Health Research Institute | MedStar Health Research Institute | MedStar Health Research Institute, VirginiaForm of publication: Journal ArticleMedline article type(s): Journal ArticleSubject headings: *Analgesics, Opioid | *Opioid-Related Disorders | Analgesics, Opioid/tu [Therapeutic Use] | Humans | Opioid-Related Disorders/ep [Epidemiology] | Opioid-Related Disorders/et [Etiology] | Opioid-Related Disorders/pc [Prevention & Control] | Pain, Postoperative/di [Diagnosis] | Pain, Postoperative/dt [Drug Therapy] | Pain, Postoperative/et [Etiology] | Patient Reported Outcome Measures | Retrospective Studies | Upper Extremity/su [Surgery]Year: 2023ISSN:
  • 0032-1052
Name of journal: Plastic and reconstructive surgeryAbstract: BACKGROUND: Opioids play a role in pain management after surgery, but prolonged use contributes to developing opioid use disorder. Identifying patients at risk of prolonged use is critical for deploying interventions that reduce or avoid opioids; however, available predictive models do not incorporate patient-reported data (PRD), and it remains unclear whether PRD can predict postoperative use behavior. The authors used a machine learning approach leveraging preoperative PRD and electronic health record data to predict persistent opioid use after upper extremity surgery.CLINICAL QUESTION/LEVEL OF EVIDENCE: Risk, III. Copyright © 2023 by the American Society of Plastic Surgeons.CONCLUSIONS: This opioid use prediction model using preintervention data had good discriminative performance. PRD variables augmented electronic health record-based machine learning algorithms in predicting postsurgical use behaviors and were some of the strongest predictors. PRD should be used in future efforts to guide proper opioid stewardship.METHODS: Included patients underwent upper extremity surgery, completed preoperative PRD questionnaires, and were prescribed opioids after surgery. The authors trained models using a 2018 cohort and tested in a 2019 cohort. Opioid use was determined by patient report and filled prescriptions up to 6 months after surgery. The authors assessed model performance using area under the receiver operating characteristic, sensitivity, specificity, and Brier score.RESULTS: Among 1656 patients, 19% still used opioids at 6 weeks, 11% at 3 months, and 9% at 6 months. The XGBoost model trained on PRD plus electronic health record data achieved area under the receiver operating characteristic 0.73 at 6 months. Factors predictive of prolonged opioid use included income; education; tobacco, drug, or alcohol abuse; cancer; depression; and race. Protective factors included preoperative Patient-Reported Outcomes Measurement Information System Global Physical Health and Upper Extremity scores.All authors: Belouali A, Giladi AM, Gupta S, Madhavan S, Miller KE, Sanghavi KK, Shipp MM, Zhang GFiscal year: FY2024Digital Object Identifier: Date added to catalog: 2023-10-04
Holdings
Item type Current library Collection Call number Status Date due Barcode
Journal Article MedStar Authors Catalog Article 36780362 Available 36780362

BACKGROUND: Opioids play a role in pain management after surgery, but prolonged use contributes to developing opioid use disorder. Identifying patients at risk of prolonged use is critical for deploying interventions that reduce or avoid opioids; however, available predictive models do not incorporate patient-reported data (PRD), and it remains unclear whether PRD can predict postoperative use behavior. The authors used a machine learning approach leveraging preoperative PRD and electronic health record data to predict persistent opioid use after upper extremity surgery.

CLINICAL QUESTION/LEVEL OF EVIDENCE: Risk, III. Copyright © 2023 by the American Society of Plastic Surgeons.

CONCLUSIONS: This opioid use prediction model using preintervention data had good discriminative performance. PRD variables augmented electronic health record-based machine learning algorithms in predicting postsurgical use behaviors and were some of the strongest predictors. PRD should be used in future efforts to guide proper opioid stewardship.

METHODS: Included patients underwent upper extremity surgery, completed preoperative PRD questionnaires, and were prescribed opioids after surgery. The authors trained models using a 2018 cohort and tested in a 2019 cohort. Opioid use was determined by patient report and filled prescriptions up to 6 months after surgery. The authors assessed model performance using area under the receiver operating characteristic, sensitivity, specificity, and Brier score.

RESULTS: Among 1656 patients, 19% still used opioids at 6 weeks, 11% at 3 months, and 9% at 6 months. The XGBoost model trained on PRD plus electronic health record data achieved area under the receiver operating characteristic 0.73 at 6 months. Factors predictive of prolonged opioid use included income; education; tobacco, drug, or alcohol abuse; cancer; depression; and race. Protective factors included preoperative Patient-Reported Outcomes Measurement Information System Global Physical Health and Upper Extremity scores.

English

Powered by Koha