Jesse L Yedinak1, Yu Li1, Maxwell S Krieger1, Katharine Howe2, Colleen Daley Ndoye3, Hyunjoon Lee4, Anna M Civitarese2, Theodore Marak2, Elana Nelson1, Elizabeth A Samuels5, Philip A Chan6, Thomas Bertrand2, Brandon D L Marshall7. 1. Department of Epidemiology, Brown University School of Public Health, Providence, RI, USA. 2. Center for HIV, Hepatitis, STD, and TB Epidemiology, Rhode Island Department of Health, Providence, RI, USA. 3. Project Weber/Renew: Harm Reduction & Recovery Services Provider, Providence, RI, USA. 4. Psychiatric and Neurodevelopmental Genetics Unit, Center for Genomic Medicine, Massachusetts General Hospital, Boston, MA, USA. 5. Department of Emergency Medicine, Alpert Medical School of Brown University, Providence, RI, USA; Overdose Prevention Program, Rhode Island Department of Health, Providence, RI, USA. 6. Department of Behavioral and Social Sciences, Brown University School of Public Health, Providence, RI, USA; Department of Medicine, Alpert Medical School of Brown University, Providence, RI, USA; Center for HIV, Hepatitis, STD, and TB Epidemiology, Rhode Island Department of Health, Providence, RI, USA. 7. Department of Epidemiology, Brown University School of Public Health, Providence, RI, USA. Electronic address: brandon_marshall@brown.edu.
Abstract
BACKGROUND: Multiple areas in the United States of America (USA) are experiencing high rates of overdose and outbreaks of bloodborne infections, including HIV and hepatitis C virus (HCV), due to non-sterile injection drug use. We aimed to identify neighbourhoods at increased vulnerability for overdose and infectious disease outbreaks in Rhode Island, USA. The primary aim was to pilot machine learning methods to identify which neighbourhood-level factors were important for creating "vulnerability assessment scores" across the state. The secondary aim was to engage stakeholders to pilot an interactive mapping tool and visualize the results. METHODS: From September 2018 to November 2019, we conducted a neighbourhood-level vulnerability assessment and stakeholder engagement process named The VILLAGE Project (Vulnerability Investigation of underlying Local risk And Geographic Events). We developed a predictive analytics model using machine learning methods (LASSO, Elastic Net, and RIDGE) to identify areas with increased vulnerability to an outbreak of overdose, HIV and HCV, using census tract-level counts of overdose deaths as a proxy for injection drug use patterns and related health outcomes. Stakeholders reviewed mapping tools for face validity and community distribution. RESULTS: Machine learning prediction models were suitable for estimating relative neighbourhood-level vulnerability to an outbreak. Variables of importance in the model included housing cost burden, prior overdose deaths, housing density, and education level. Eighty-nine census tracts (37%) with no prior overdose fatalities were identified as being vulnerable to such an outbreak, and nine of those were identified as having a vulnerability assessment score in the top 25%. Results were disseminated as a vulnerability stratification map and an online interactive mapping tool. CONCLUSION: Machine learning methods are well suited to predict neighborhoods at higher vulnerability to an outbreak. These methods show promise as a tool to assess structural vulnerabilities and work to prevent outbreaks at the local level.
BACKGROUND: Multiple areas in the United States of America (USA) are experiencing high rates of overdose and outbreaks of bloodborne infections, including HIV and hepatitis C virus (HCV), due to non-sterile injection drug use. We aimed to identify neighbourhoods at increased vulnerability for overdose and infectious disease outbreaks in Rhode Island, USA. The primary aim was to pilot machine learning methods to identify which neighbourhood-level factors were important for creating "vulnerability assessment scores" across the state. The secondary aim was to engage stakeholders to pilot an interactive mapping tool and visualize the results. METHODS: From September 2018 to November 2019, we conducted a neighbourhood-level vulnerability assessment and stakeholder engagement process named The VILLAGE Project (Vulnerability Investigation of underlying Local risk And Geographic Events). We developed a predictive analytics model using machine learning methods (LASSO, Elastic Net, and RIDGE) to identify areas with increased vulnerability to an outbreak of overdose, HIV and HCV, using census tract-level counts of overdose deaths as a proxy for injection drug use patterns and related health outcomes. Stakeholders reviewed mapping tools for face validity and community distribution. RESULTS: Machine learning prediction models were suitable for estimating relative neighbourhood-level vulnerability to an outbreak. Variables of importance in the model included housing cost burden, prior overdose deaths, housing density, and education level. Eighty-nine census tracts (37%) with no prior overdose fatalities were identified as being vulnerable to such an outbreak, and nine of those were identified as having a vulnerability assessment score in the top 25%. Results were disseminated as a vulnerability stratification map and an online interactive mapping tool. CONCLUSION: Machine learning methods are well suited to predict neighborhoods at higher vulnerability to an outbreak. These methods show promise as a tool to assess structural vulnerabilities and work to prevent outbreaks at the local level.
Authors: William C Goedel; Maximilian R F King; Mark N Lurie; Sandro Galea; Jeffrey P Townsend; Alison P Galvani; Samuel R Friedman; Brandon D L Marshall Journal: Clin Infect Dis Date: 2020-03-03 Impact factor: 9.079
Authors: Maxwell S Krieger; Jesse L Yedinak; Jane A Buxton; Mark Lysyshyn; Edward Bernstein; Josiah D Rich; Traci C Green; Scott E Hadland; Brandon D L Marshall Journal: Harm Reduct J Date: 2018-02-08
Authors: Joëlla W Adams; Mark N Lurie; Maximilian R F King; Kathleen A Brady; Sandro Galea; Samuel R Friedman; Maria R Khan; Brandon D L Marshall Journal: BMC Public Health Date: 2018-12-18 Impact factor: 3.295
Authors: Brandon D L Marshall; Nicole Alexander-Scott; Jesse L Yedinak; Benjamin D Hallowell; William C Goedel; Bennett Allen; Robert C Schell; Yu Li; Maxwell S Krieger; Claire Pratty; Jennifer Ahern; Daniel B Neill; Magdalena Cerdá Journal: Addiction Date: 2021-11-29 Impact factor: 6.526
Authors: David Hupin; Philip Sarajlic; Ashwin Venkateshvaran; Cecilia Fridén; Birgitta Nordgren; Christina H Opava; Ingrid E Lundberg; Magnus Bäck Journal: Front Med (Lausanne) Date: 2021-12-15