Graph Representation of Postoperative Patients for Opioids Refill Prediction: A Real-World Case Study.

Abstract

Increased awareness of the opioid epidemic has resulted in the need to significantly reduce the number of opioids prescribed after surgery. However, up to one in five patients require a refill after discharge. Accurate identification of patients at risk of needing a refill after surgery is critically important, as it has the potential to improve pain control and patient experience while avoiding overprescription of opioids after surgery. In this paper, two graph representation learning methods are proposed for predicting opioid refills in postoperative patients. The first approach represents patients as nodes in a graph and performs node classification. The second approach is based on graph classification where each patient is represented as a graph. Performance results on a real-world retrospective cohort of postoperative patients show that a node classification approach with graph sample and aggregation (GraphSAGE) achieves the best performance in prediction of opioid refill.