Predicting persistent opioid use after hand surgery: a machine learning approach

Background: The aim of this study was to evaluate the use of machine learning to predict persistent opioid use after hand surgery. Methods: The authors trained 2 algorithms to predict persistent opioid use, first using a general surgery data set and then using a hand surgery data set, resulting in 4 trained models. Next, the authors tested each model’s performance using hand surgery data. Participants included adult surgery patients enrolled in a cohort study at an academic center from 2015 to 2018. The first algorithm (Michigan Genomics Initiative model) was designed to accommodate patient-reported data and patients with or without prior opioid use. The second algorithm (claims model) was designed for insurance claims data from patients who were opioid-naive only. The main outcome was model discrimination, measured by area under the receiver operating curve (AUC). Results: Of 889 hand surgery patients, 49% were opioid-naive and 21% developed persistent opioid use. Most patients underwent soft-tissue procedures (55%) or fracture repair (20%). The Michigan Genomics Initiative model had AUCs of 0.84 when trained only on hand surgery data, and 0.85 when trained on the full cohort of surgery patients. The claims model had AUCs of 0.69 when trained only on hand surgery data, and 0.52 when trained on the opioid-naive cohort of surgery patients. Conclusions: Opioid use is common after hand surgery. Machine learning has the potential to facilitate identification of patients who are at risk for prolonged opioid use, which can promote early interventions to prevent addiction.