Skip to content
DraconiticResearch
Search Sources API
220,411 studies31 sourcesUpdated 51 min ago
PreprintarXiv licencearXiv

Modeling Drug Overdose Mortality Levels Using Social Vulnerability Indicators in U.S. Counties: A Double Machine Learning Approach for Causal Analysis

  • Qunhui Guo
  • Jiongbai Liu
  • Md Noor E Alam
Open at sourcePDFDOICite

Abstract

Drug poisoning mortality (DPM) remains a leading cause of death among working-age Americans, and its burden falls unevenly across communities. Existing county-level studies of social vulnerability and overdose have largely reported predictive or associational relationships, while the shape of the adjusted exposure-response relationship between overall social vulnerability and mortality remains unclear. We examined the CDC/ATSDR Social Vulnerability Index (SVI) and county drug poisoning mortality across three two-year windows spanning 2016-2021. The associational analysis compared linear regression, Random Forest, and XGBoost models of log mortality using period-specific SVI subfeatures and county covariates. The selected XGBoost models were interpreted with SHAP values. The double machine learning (DML) analysis estimated the exposure-response relationship between SVI and DPM and tested the linearity restriction. Socioeconomic vulnerability contributed positively to predicted mortality, with disability and unemployment among the strongest subfeatures, while racial and ethnic minority composition contributed negatively in all three periods. Summing the four theme contributions reduced the overall-index attribution by 34% to 36%, indicating substantial offsetting. Linearity was rejected in every window (p < 10−26). The adjusted relationship increased through the middle of the SVI distribution and declined in the upper tail. This pattern remained stable both before and after the outbreak of the epidemic. Overall SVI therefore captured meaningful variation in overdose mortality but did not function as a uniformly increasing risk scale across its full range. Component-level interpretation and current overdose surveillance provide important context for interpreting the composite index.

Related

  1. Projected Effects of Naloxone and Buprenorphine Scale-Up on Opioid Overdose Mortality in Six Pennsylvania Counties
    Abdulrahman A. Ahmed, M. Amin Rahimian, Qiushi Chen +1
    arXivPreprintarXiv licenceFull textStatisticsStatistical & nonlinear physicsarXiv
  2. Bayesian ACCESS for Understanding Latent Epidemic Trajectories from Publicly Released Suppressed Data: Application to U.S. Opioid-related Overdose Mortality
    Jiahao Cao, Kehe Zhang, Cici Bauer
    arXivPreprintarXiv licenceFull textStatisticsarXiv
  3. Artificial intelligence-based surrogate modeling of hemodynamic indicators in abdominal aortic aneurysms using computational fluid dynamics
    MyeungHye Suh, Up Huh, Chiseung Lee
    PLOS OnePeer-reviewedCC BYFull textGeneral biologyGeometry & topologyPLOSEurope PMCPMC
  4. On Recoding Ordered Treatments as Binary Indicators*
    Evan K. Rose, Yotam Shem-Tov
    The review of economics and statisticsPeer-reviewedLicence not statedFull text1 citedStatisticsPMC
  5. The binomial distribution maximises entropy among sums of negatively related indicators with fixed mean and support
    Fraser Daly
    arXivPreprintarXiv licenceFull textProbabilityarXiv

Cite

BibTeXRIS
BibTeX
@misc{guo2026modeling,
  title = {{Modeling Drug Overdose Mortality Levels Using Social Vulnerability Indicators in U.S. Counties: A Double Machine Learning Approach for Causal Analysis}},
  author = {Qunhui Guo and Jiongbai Liu and Md Noor E Alam},
  howpublished = {arXiv},
  year = {2026},
  month = nov,
  doi = {10.48550/arxiv.2611.14537},
  eprint = {2611.14537},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.14537},
}
RIS
TY  - UNPB
TI  - Modeling Drug Overdose Mortality Levels Using Social Vulnerability Indicators in U.S. Counties: A Double Machine Learning Approach for Causal Analysis
AU  - Qunhui Guo
AU  - Jiongbai Liu
AU  - Md Noor E Alam
PY  - 2026
DA  - 2026/11/01
PB  - arXiv
DO  - 10.48550/arxiv.2611.14537
UR  - https://arxiv.org/abs/2611.14537
AB  - Drug poisoning mortality (DPM) remains a leading cause of death among working-age Americans, and its burden falls unevenly across communities. Existing county-level studies of social vulnerability and overdose have largely reported predictive or associational relationships, while the shape of the adjusted exposure-response relationship between overall social vulnerability and mortality remains unclear. We examined the CDC/ATSDR Social Vulnerability Index (SVI) and county drug poisoning mortality across three two-year windows spanning 2016-2021. The associational analysis compared linear regression, Random Forest, and XGBoost models of log mortality using period-specific SVI subfeatures and county covariates. The selected XGBoost models were interpreted with SHAP values. The double machine learning (DML) analysis estimated the exposure-response relationship between SVI and DPM and tested the linearity restriction. Socioeconomic vulnerability contributed positively to predicted mortality, with disability and unemployment among the strongest subfeatures, while racial and ethnic minority composition contributed negatively in all three periods. Summing the four theme contributions reduced the overall-index attribution by 34% to 36%, indicating substantial offsetting. Linearity was rejected in every window (p < 10^−26). The adjusted relationship increased through the middle of the SVI distribution and declined in the upper tail. This pattern remained stable both before and after the outbreak of the epidemic. Overall SVI therefore captured meaningful variation in overdose mortality but did not function as a uniformly increasing risk scale across its full range. Component-level interpretation and current overdose surveillance provide important context for interpreting the composite index.
ER  -