Assessment of Tennessee's county-level vulnerability to hepatitis C virus and HIV outbreaks using socioeconomic, healthcare, and substance use indicators.

BACKGROUND: Human immunodeficiency virus (HIV), hepatitis C virus (HCV), and injection drug use are syndemic in the central Appalachian states. In Tennessee (TN), declines in HIV among persons who inject drugs (PWID) stalled, and HCV infection rates increased significantly from 2013-2017. To better target strategies to address the syndemic, county-level socioeconomic, opioid use, access to healthcare, and health factors were modeled to identify indicators predictive of vulnerability to an HIV/HCV outbreak among PWID in TN. METHODS: Newly reported chronic HCV cases among persons aged 13-39 years in 2016-2017 were used as a proxy for county-level HIV/HCV vulnerability among TN's 95 counties. Seventy-five publicly available county-level measures from 2016-2017 were collected and reduced through multiple dimension reduction techniques. Negative binomial regression identified indicators associated with HCV which were used to calculate county-level vulnerability to a local HIV/HCV outbreak. RESULTS: Thirteen county-level indicators were identified as strongly predictive of HIV/HCV vulnerability with the statistically significant indicators being percentage of the population aged 20-44 years, per capita income, teen birth rate, percentage of clients in TDMHSAS-funded opioid treatment and recovery, syphilis case rate, and percentage of homes with at least one vehicle. Based on the 13 indicators, we identified the distribution of vulnerability to an HIV/HCV outbreak among TN's counties. Eleven high vulnerability counties were identified, with the preponderance located in east and middle TN. CONCLUSION: This analysis identified the county-level factors most associated with vulnerability to an HIV/HCV outbreak among PWID in TN. These results, alongside routine surveillance, will guide targeted prevention and linkage to care efforts for the most vulnerable communities.

Ensemble learning to predict opioid-related overdose using statewide prescription drug monitoring program and hospital discharge data in the state of Tennessee.

OBJECTIVE: To develop and validate algorithms for predicting 30-day fatal and nonfatal opioid-related overdose using statewide data sources including prescription drug monitoring program data, Hospital Discharge Data System data, and Tennessee (TN) vital records. Current overdose prevention efforts in TN rely on descriptive and retrospective analyses without prognostication. MATERIALS AND METHODS: Study data included 3 041 668 TN patients with 71 479 191 controlled substance prescriptions from 2012 to 2017. Statewide data and socioeconomic indicators were used to train, ensemble, and calibrate 10 nonparametric "weak learner" models. Validation was performed using area under the receiver operating curve (AUROC), area under the precision recall curve, risk concentration, and Spiegelhalter z-test statistic. RESULTS: Within 30 days, 2574 fatal overdoses occurred after 4912 prescriptions (0.0069%) and 8455 nonfatal overdoses occurred after 19 460 prescriptions (0.027%). Discrimination and calibration improved after ensembling (AUROC: 0.79-0.83; Spiegelhalter P value: 0-.12). Risk concentration captured 47-52% of cases in the top quantiles of predicted probabilities. DISCUSSION: Partitioning and ensembling enabled all study data to be used given computational limits and helped mediate case imbalance. Predicting risk at the prescription level can aggregate risk to the patient, provider, pharmacy, county, and regional levels. Implementing these models into Tennessee Department of Health systems might enable more granular risk quantification. Prospective validation with more recent data is needed. CONCLUSION: Predicting opioid-related overdose risk at statewide scales remains difficult and models like these, which required a partnership between an academic institution and state health agency to develop, may complement traditional epidemiological methods of risk identification and inform public health decisions.