Machine Learning for Drug Overdose Surveillance
This work addresses the problem of improving overdose surveillance for public health officials and policymakers, though it is incremental as it applies existing methods to new data in this domain.
The paper tackles the problem of early detection of emerging trends in fatal accidental drug overdoses by applying two machine learning approaches, Gaussian Process Subset Scan and Multidimensional Tensor Scan, to spatio-temporal and case-level data, showing clear advantages over typical anomaly detection methods and discovering previously unidentified patterns such as unusual demographic clusters and impacts of drug legislation.
We describe two recently proposed machine learning approaches for discovering emerging trends in fatal accidental drug overdoses. The Gaussian Process Subset Scan enables early detection of emerging patterns in spatio-temporal data, accounting for both the non-iid nature of the data and the fact that detecting subtle patterns requires integration of information across multiple spatial areas and multiple time steps. We apply this approach to 17 years of county-aggregated data for monthly opioid overdose deaths in the New York City metropolitan area, showing clear advantages in the utility of discovered patterns as compared to typical anomaly detection approaches. To detect and characterize emerging overdose patterns that differentially affect a subpopulation of the data, including geographic, demographic, and behavioral patterns (e.g., which combinations of drugs are involved), we apply the Multidimensional Tensor Scan to 8 years of case-level overdose data from Allegheny County, PA. We discover previously unidentified overdose patterns which reveal unusual demographic clusters, show impacts of drug legislation, and demonstrate potential for early detection and targeted intervention. These approaches to early detection of overdose patterns can inform prevention and response efforts, as well as understanding the effects of policy changes.