Trajectories of Neighborhood-level Overdose Risk Predictions For Prioritization of Harm Reduction Services: Results From the PROVIDENT Study.

Details

• Alternative Title:
  Drug and Alcohol Dependence, 2025, v. 277: Trajectories of Neighborhood-level Overdose Risk Predictions For Prioritization of Harm Reduction Services: Results From the PROVIDENT Study.
• Journal Article:
  Drug and Alcohol Dependence
• Personal Author:
  Skinner, Alexandra ; Goedel, William C. ; Hallowell, Benjamin D. ; Allen, Bennett ; Krieger, Maxwell ; Pratty, Claire ; Ahern, Jennifer ; Cerdá, Magdalena ; Marshall, Brandon D.L.
• Description:
  Neighborhood-level overdose risk may vary over time. In Rhode Island, we developed and validated a machine learning model to identify the 20 percent of census block groups (CBGs) at the highest predicted risk of future overdose death. We updated this model periodically between November 2021 and August 2024 to generate six sets of predictions. This study aims to characterize the trajectory of each CBG's predicted overdose risk over time across these six periods.
  
  In each prediction period, CBGs were designated as "high risk" or not designated as "high risk" based on our model's 20 percent predicted overdose risk threshold. We implemented sequence analysis to describe unique trajectories in each CBG's risk designation over each prediction period. We then calculated optimal matching distances to estimate dissimilarity between each pair of trajectories and applied agglomerative hierarchical clustering to group similar trajectories.
  
  The 809 CBGs included in this study followed 60 unique trajectories in predicted overdose risk designation over the six prediction periods. Clustering of trajectories favored a solution with five trajectory groups. Most CBGs (73.4 %) were rarely or never designated as "high risk", 7.9 % of CBGs were always designated as "high risk", and the remaining 18.7 % were designated as "high risk" in multiple prediction periods, represented by trajectory groups with different patterning over time.
  
  Given the substantial variability in which CBGs were at highest overdose risk over time, dynamic machine learning predictions may inform harm reduction resource allocation by identifying neighborhoods with emerging needs.
• Content Notes:
  Author manuscript
• Subjects:
  • Humans
  • Harm Reduction
  • Drug Overdose
  • Machine Learning
  • Male
  • Female
  • Adult
  • Neighborhood Characteristics
  • Residence Characteristics
• Keywords:
  • Drug overdose
  • Harm reduction
  • Machine learning
  • Predictive analytics
  • Sequence analysis
• Source:
  Drug and Alcohol Dependence, 2025, v. 277
• DOI:
  https://doi.org/10.1016/j.drugalcdep.2025.112927
• ISSN:
  0376-8716 ; 1879-0046
• Pubmed ID:
  41175601
• Pubmed Central ID:
  PMC12651951
• Document Type:
  Text
• Funding:
  K01 CE003586/CE/NCIPC CDC HHSUnited States/ ; K01CE003586/ACL/ACL HHSUnited States/ ; R01 DA046620/DA/NIDA NIH HHSUnited States/
• Genre:
  Journal Article
• Place as Subject:
  Rhode Island
• Pages in Document:
  112927 (11 pdf pages)
• Volume:
  277
• Download URL:
  https://stacks.cdc.gov/view/cdc/260971/cdc_260971_DS1.pdf
• File Type:
  [PDF - 388.59 KB]
• Collection(s):
  CDC Public Access
• Main Document Checksum:
  urn:sha-512:34ff73eb5971f792085323f9d8ccc0ecf1e0bdd3c04cc39708f9da6471672a62e504a7a51aa28f70a41f9896023275f64d1af57eebf08aca2f9c53cff7f75f45