Application of machine learning algorithms for localized syringe services program policy implementation – Florida, 2017

Abstract

Background People who inject drugs (PWID) are at an amplified vulnerability for experiencing a multitude of harms related to their substance use, including viral (e.g. HIV, Hepatitis C) and bacterial infections (e.g. endocarditis). Implementation of evidence-based interventions, such as syringe services programs (SSPs), remains imperative, particularly in locations at an increased risk of HIV outbreaks. This study aims to identify communities in Florida that are high-priority locations for SSP implementation by examining state-level data related to the substance use and overdose crises. Methods State-level surveillance data were aggregated at the ZIP Code Tabulation Area (ZCTA) ( n = 983) for 2017. We used confirmed cases of acute HCV infection as a proxy of injection drug use. Least Absolute Selection and Shrinkage Operator (LASSO) regression was used to develop a machine learning model to identify significant indicators of acute HCV infection and high-priority areas for SSP implementation due to their increased vulnerability to an HIV outbreak. Results The final model retained three variables of importance: (1) the number of drug-associated skin and soft tissue infection hospitalizations, (2) the number of chronic HCV infections in people aged 18–39, and 3) the number of drug-associated endocarditis hospitalizations. High-priority SSP implementation locations were identified in both urban and rural communities outside of current Ending the HIV Epidemic counties. Conclusion SSPs are long researched, safe, and effective evidence-based programs that offer a variety of services that reduce disease transmission and assist with combating the overdose crisis. Opportunities to increase services in needed regions across the state now exist in Florida as supported by the expansion of the Infectious Disease Elimination Act of 2019. This study provides details where potential areas of concern may be and highlights regions where future evidence-based harm reduction programs, such as SSPs, would be useful to reduce opioid overdoses and disease transmission among PWID. Key messages The rate of acute HCV in Florida in 2017 was 1.9 per 100,000, nearly twice the national average. Serious injection related infections among PWID are significant indicators of acute HCV infection. High-priority SSP implementation locations in Florida were identified in both urban and rural communities, including those outside of current Ending the HIV Epidemic counties.

Development and validation of a LASSO-based prediction model for immunosuppressive medication nonadherence in kidney transplant recipients

“…We used the R package glmnet version 4.0.2 (R Foundation for Statistical Computing, Vienna, Austria) to develop a penalized logistic regression LASSO model. The penalty regularization parameter lambda ( λ ) was determined by 10-fold cross validation with the cv.glmnet module [ 34 ]. Based on the optimal parameters, the variables with nonzero coefficients were used to create the final LASSO model.…”

Applying Machine Learning Techniques to Implementation Science

“…One study used a supervised learning model to identify areas where the implementation of HIV prevention programs should be prioritized. Using state surveillance data on substance use, sexually transmitted diseases, and community characteristics (eg, percent living in poverty), ML modeling identified high-priority areas, of which 79% did not have implemented syringe services programs [ 29 ]. Similar modeling approaches could be used to better identify who will adopt what implementation strategies with what supports and tailor resource allocation before an implementation program is launched to improve the adoption and sustainability of EBIs.…”

Natural Language Processing For Identification of Hospitalized People with Substance Use Disorder (Preprint)

“…17 There is only a handful of published studies about applying NLP to the identification of hospitalized PWUD admitted for bloodstream infections; however, this effort was a single-center evaluation focused only on injection drug use. [21][22][23][24] Despite its innovative capacity to identify PWUD, the science of NLP methodology is nascent. The goal of this study is to evaluate the impact of Natural Language Processing on creating a cohort of hospitalized PWUD.…”