Identifying counties at risk of high overdose mortality burden during the emerging fentanyl epidemic in the USA: a predictive statistical modelling study

BACKGROUND: The emergence of fentanyl around 2013 represented a new, deadly stage of the opioid epidemic in the USA. We aimed to develop a statistical regression approach to identify counties at the highest risk of high overdose mortality in the subsequent years by predicting annual county-level overdose death rates across the contiguous USA and to validate our approach against observed overdose mortality data collected between 2013 and 2018. METHODS: We fit mixed-effects negative binomial regression models to predict overdose death rates in the subsequent year for 2013-18 for all contiguous state counties in the USA (ie, excluding Alaska and Hawaii). We used publicly available county-level data related to health-care access, drug markets, socio-demographics, and the geographical spread of opioid overdose as model predictors. The crude number of county-level overdose deaths was extracted from restricted US Centers for Disease Control and Prevention mortality records. To predict county-level overdose rates for the year 201X: (1) a model was trained on county-level predictor data for the years 2010-201(X-2) paired with county-level overdose deaths for the year 2011-201(X-1); (2) county-level predictor data for the year 201(X-1) was fed into the model to predict the 201X county-level crude number of overdose deaths; and (3) the latter were converted to a population-adjusted rate. For comparison, we generated a benchmark set of predictions by applying the observed slope of change in overdose death rates in the previous year to 201(X-1) rates. To assess the predictive performance of the model, we compared predicted values (of both the model and benchmark) to observed values by (1) calculating the mean average error, root mean squared error, and Spearman's correlation coefficient and (2) assessing the proportion of counties in the top decile (10%) of overdose death rates that were correctly predicted as such. Finally, in a post-hoc analysis, we sought to identify variables with greatest predictive utility. FINDINGS: Between 2013 and 2018, among the 3106 US counties included, our modelling approach outperformed the benchmark strategy across all metrics. The observed average county-level overdose death rate rose from 11·8 per 100 000 people in 2013 to 15·4 in 2017 before falling to 14·6 in 2018. Our negative binomal modelling approach similarly identified an increasing trend, predicting an average 11·8 deaths per 100 000 in 2013, up to 15·1 in 2017, and increasing further to 16·4 in 2018. The benchmark model over-predicted average death rates each year, ranging from 13·0 per 100 000 in 2013 to 18·3 in 2018. Our modelling approach successfully ranked counties by overdose death rate identifying between 42% and 57% of counties in the top decile of overdose mortality (compared with 29% and 43% using the benchmark) each year and identified 194 of the 808 counties with emergent overdose outbreaks (ie, newly entered the top decile) across the study period, versus 31 using the benchmark. In the post-hoc analysis, we identified geospatial proximity of overdose in nearby counties, opioid prescription rate, presence of an urgent care facility, and several economic indicators as the variables with the greatest predictive utility. INTERPRETATION: Our model shows that a regression approach can effectively predict county-level overdose death rates and serve as a risk assessment tool to identify future high mortality counties throughout an emerging drug use epidemic. FUNDING: National Institute on Drug Abuse