A predictive-modeling based screening tool for prolonged opioid use after surgical management of low back and lower extremity pain

• Published in: The spine journal 2020-08, Vol.20 (8), p.1184-1195
• Main Authors: Zhang, Yi, Fatemi, Parastou, Medress, Zachary, Azad, Tej D., Veeravagu, Anand, Desai, Atman, Ratliff, John K.
• Format: Article
• Language: English
• Subjects: Machine learning; Postoperative pain; Predictive model; Prolonged opioid use; Screening tool; Spine surgery
• ISSN: 1529-9430; 1878-1632
• DOI: 10.1016/j.spinee.2020.05.098

Outpatient postoperative pain management in spine patients, specifically involving the use of opioids, demonstrates significant variability. Using preoperative risk factors and 30-day postoperative opioid prescribing patterns, we developed models for predicting long-term opioid use in patients after elective spine surgery. This retrospective cohort study utilizes inpatient, outpatient, and pharmaceutical data from MarketScan databases (Truven Health). In all, 19,317 patients who were newly diagnosed with low back or lower extremity pain (LBP or LEP) between 2008 and 2015 and underwent thoracic or lumbar surgery within 1 year after diagnosis were enrolled. Some patients initiated opioids after diagnosis but all patients were opioid-naïve before the diagnosis. Long-term opioid use was defined as filling ≥180 days of opioids within one year after surgery. Using demographic variables, medical and psychiatric comorbidities, preoperative opioid use, and 30-day postoperative opioid use, we generated seven models on 80% of the dataset and tested the models on the remaining 20%. We used three regression-based models (full logistic regression, stepwise logistic regression, least absolute shrinkage and selection operator), support vector machine, two tree-based models (random forest, stochastic gradient boosting), and time-varying convolutional neural network. Area under the curve (AUC), Brier index, sensitivity, and calibration curves were used to assess the discrimination and calibration of the models. We identified 903 (4.6%) of patients who met criteria for long-term opioid use. The regression-based models demonstrated the highest AUC, ranging from 0.835 to 0.847, and relatively high sensitivities, predicting between 74.9% and 76.5% of the long-term opioid use patients in the test dataset. The three strongest positive predictors of long-term opioid use were high preoperative opioid use (OR 2.70; 95% confidence interval [CI] 2.27–3.22), number of days with active opioid prescription between postoperative days 15 to 30 (OR 1.10; 95%CI 1.07–1.12), and number of dosage increases between postoperative day 15 to 30 (OR 1.71, 95%CI 1.41–2.08). The strongest negative predictors were number of dosage decreases in the 30-day postoperative period. We evaluated several predictive models for postoperative long-term opioid use in a large cohort of patients with LBP or LEP who underwent surgery. A regression-based model with high sensitivity and AUC is provided online to screen