Skip to main content
Michigan OPEN

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

  • Potential predictors included sociodemographic data, comorbidities, and prescriptions within one year prior to surgery.
  • 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.
  • Preoperative patient attributes from insurance claims could potentially be useful in guiding prescription practices for opioid-naïve patients.


Visit Website

Hur J; Tang S; Gunaseelan V; Vu J; Brummett CM; Englesbe MJ; Waljee JF; Wiens J. Predicting postoperative opioid use with machine learning and insurance claims in opioid-naïve patients. American Journal of Surgery. Published online 26 March 2021. DOI: https://doi.org/10.1016/j.amjsurg.2021.03.058