TY - JOUR
T1 - Machine Learning for Drug Overdose Surveillance
AU - Neill, Daniel B.
AU - Herlands, William
N1 - Funding Information:
This work was supported by the National Science Foundation [Grant Number GRFP DGE-1252522, IIS-0953330] and NCSU Laboratory for Analytical Sciences.
Publisher Copyright:
© 2017 Taylor & Francis Group, LLC.
PY - 2018/1/2
Y1 - 2018/1/2
N2 - We describe two recently proposed machine learning approaches for discovering emerging trends in fatal accidental drug overdoses. The Gaussian Process Subset Scan (Herlands, McFowland, Wilson, & Neill, 2017) enables early detection of emerging patterns in spatio-temporal data, accounting for both the complex, correlated 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 (Neill, 2017) to 8 years of case-level overdose data from Allegheny County, Pennsylvania. 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.
AB - We describe two recently proposed machine learning approaches for discovering emerging trends in fatal accidental drug overdoses. The Gaussian Process Subset Scan (Herlands, McFowland, Wilson, & Neill, 2017) enables early detection of emerging patterns in spatio-temporal data, accounting for both the complex, correlated 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 (Neill, 2017) to 8 years of case-level overdose data from Allegheny County, Pennsylvania. 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.
KW - Disease surveillance
KW - machine learning
KW - opioids
KW - subset scan
UR - http://www.scopus.com/inward/record.url?scp=85041099006&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85041099006&partnerID=8YFLogxK
U2 - 10.1080/15228835.2017.1416511
DO - 10.1080/15228835.2017.1416511
M3 - Article
AN - SCOPUS:85041099006
VL - 36
SP - 8
EP - 14
JO - Journal of Technology in Human Services
JF - Journal of Technology in Human Services
SN - 1522-8835
IS - 1
ER -