The leading neighborhood-level predictors of drug overdose: A mixed machine learning and spatial approach.

Background: Drug overdose is a leading cause of unintentional death in the United States and has contributed significantly to a decline in life expectancy during recent years. To combat this health issue, this study aims to identify the leading neighborhood-level predictors of drug overdose and develop a model to predict areas at the highest risk of drug overdose using geographic information systems and machine learning (ML) techniques.

Method: Neighborhood-level (block group) predictors were grouped into three domains: socio-demographic factors, drug use variables, and protective resources.

Facility Attractiveness and Social Vulnerability Impacts on Spatial Accessibility to Opioid Treatment Programs in South Carolina.

Opioid dependence and opioid-related mortality have been increasing in recent years in the United States. Available and accessible treatments may result in a reduction of opioid-related mortality. This work describes the geographic variation of spatial accessibility to opioid treatment programs (OTPs) and identifies areas with poor access to care in South Carolina.

Mercury in South Carolina fishes, USA.

The South Carolina Department of Health and Environmental Control has collected, processed, and analyzed fish tissue total mercury (Hg) since 1976. For this study, skin-on-filet data from 1993 to 2007 were examined to determine biotic, spatial and temporal trends in tissue Hg levels for SC fishes. Because of the relatively high number of tissue Hg values below the analytical detection limits interval censored regression and censored least absolute deviations were used to construct several models to characterize trends.