Predicting postoperative opioid use with machine learning and insurance claims in opioid-naive patients

Background: The clinical impact of postoperative opioid use requires accurate prediction strategies to identify at-risk patients. We utilize preoperative claims data to predict postoperative opioid refill and new persistent use in opioid-naive patients. Methods: A retrospective study was conducted on 112,898 opioid-naive adult postoperative patients from Optum's de-identified Clinformatics (R) Data Mart database. Potential predictors included socio-demographic data, comorbidities, and prescriptions within one year prior to surgery. Results: Compared to linear models, non-linear models led to modest improvements in predicting refills - area under the receiver operating characteristics curve (AUROC) 0.68 vs. 0.67 (p < 0.05) - and performed identically in predicting new persistent use - AUROC = 0.66. Undergoing major surgery, opioid prescriptions within 30 days prior to surgery, and abdominal pain were useful in predicting refills; back/joint/head pain were the most important features in predicting new persistent use. Conclusions: Preoperative patient attributes from insurance claims could potentially be useful in guiding prescription practices for opioid-naive patients. (C) 2021 Elsevier Inc. All rights reserved.

Automated summary

By using preoperative claims data, this study aimed to predict postoperative opioid refill and new persistent use in opioid-naive patients. Non-linear models showed modest improvements in predicting refills compared to linear models, while they performed similarly in predicting new persistent use. Patient attributes such as undergoing major surgery, receiving opioid prescriptions within 30 days prior to surgery, and experiencing abdominal pain were useful in predicting refills, whereas back/joint/head pain were the most important features in predicting new persistent use.