Geospatial-Temporal and Demand Models for Opioid Admissions, Implications for Policy

Background: As the opioid epidemic continues, understanding the geospatial, temporal and demand patterns is important for policymakers to assign resources and interdict individual, organization, and country-level bad actors. Methods: GIS geospatial-temporal analysis, k-means cluster analysis, and extreme-gradient boosted random forests are used to evaluated ICD-10 F11 opioid-related admissions. The period of analysis was January 2016 through September 2018. Results: The analysis shows existing high-intensity areas in Chicago and New Jersey with emerging areas in Atlanta, Salt Lake City, Phoenix, and Las Vegas. Further, cluster analysis supports the current inflow from China through Mexico and Canada with another cluster in the Northeast likely associated with the Dominican flow. Explanatory models suggest that hospital overall workload and financial variables may be used for allocating opioid-related funds effectively, as the gradient-boosted random forest models accounted for 88% of the variability on a blinded test data set. Conclusions: Based on GIS analysis, the opioid epidemic is likely to spread or diffuse through the country, and interdiction efforts require demand-analysis such as that provided in this study to allocate scarce resources for supply-side and demand-side interdiction: prevention, treatment, and enforcement.