Spatial variation in socio-economic vulnerability to Influenza-like Infection for the US population

Shrabani S Tripathy, Joseph V Puthussery, Taveen S Kapoor, John R Cirrito and Rajan K Chakrabarty

PLOS Computational Biology, 2026, vol. 22, issue 1, 1-18

Abstract: This study aims to quantify environmental health impacts and assess risk by understanding the disproportionate burden of infectious diseases, specifically Influenza-like Illness (ILI), across regions with varying socio-economic characteristics. We introduce a novel vulnerability-based approach to better understand the complex relationship between socio-economic factors and ILI burden. We developed a machine-learning-driven framework to assess and map state-level socio-economic vulnerability to ILI in the United States. A vulnerability index was created by integrating 39 diverse socio-economic and health indicators from the latest CENSUS. A Random Forest Regression model then weighed these indicators to quantify each state’s vulnerability for the ILI values in 2022. To assess multicollinearity, Variance Inflation Factor (VIF) was calculated, and parameters were filtered to reduce the VIF. Key determinants of vulnerability include migration patterns, insurance coverage, and proportions of female and elderly populations. The resulting state-level vulnerability map reveals significant regional disparities. District of Columbia was identified as the most vulnerable state, followed by Massachusetts, Hawaii, New Mexico, and Rhode Island, all with normalized vulnerability indices exceeding 0.35. Our findings highlight significant regional variations in ILI vulnerability, emphasizing the need for targeted public health interventions tailored to state-specific socio-economic conditions. This scalable and adaptable methodology extends beyond influenza, offering a valuable approach for assessing vulnerability to a wide range of infectious diseases, strengthening epidemic preparedness and response.Author summary: Socio-economic conditions significantly influence a location’s susceptibility to influenza-like illness (ILI). Identifying infection hotspots based on these factors and quantifying relative susceptibility is crucial for policymakers. A vulnerability index serves as an effective tool for this purpose. Our study employs a Random Forest-based technique to not only provide relative vulnerability values but also to identify the dominant socio-economic features contributing to high vulnerability in specific areas.

Date: 2026
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1013839 (text/html)
https://journals.plos.org/ploscompbiol/article/fil ... 13839&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pcbi00:1013839

DOI: 10.1371/journal.pcbi.1013839

Access Statistics for this article

More articles in PLOS Computational Biology from Public Library of Science
Bibliographic data for series maintained by ploscompbiol ().