Dynamic contact networks of residents of an urban jail in the era of SARS-CoV-2

Abstract

Background: In custodial settings such as jails and prisons, infectious disease transmission is heightened by factors such as overcrowding and limited healthcare access. Specific features of social contact networks within these settings have not been sufficiently characterized, especially in the context of a large-scale respiratory infectious disease outbreak. The study aims to quantify contact network dynamics within the Fulton County Jail in Atlanta, Georgia.

Methods: Jail roster data were utilized to construct social contact networks. Rosters included resident details, cell locations, and demographic information. This analysis involved 6702 male residents over 140,901 person days. Network statistics, including degree, mixing, and dissolution (movement within and out of the jail) rates, were assessed. We compared outcomes for two distinct periods (January 2022 and April 2022) to understand potential responses in network structures during and after the SARS-CoV-2 Omicron variant peak.

Results: We found high cross-sectional network degree at both cell and block levels. While mean degree increased with age, older residents exhibited lower degree during the Omicron peak. Block-level networks demonstrated higher mean degrees than cell-level networks. Cumulative degree distributions increased from January to April, indicating heightened contacts after the outbreak. Assortative age mixing was strong, especially for younger residents. Dynamic network statistics illustrated increased degrees over time, emphasizing the potential for disease spread.

Conclusions: Despite some reduction in network characteristics during the Omicron peak, the contact networks within the Fulton County Jail presented ideal conditions for infectious disease transmission. Age-specific mixing patterns suggested unintentional age segregation, potentially limiting disease spread to older residents. This study underscores the necessity for ongoing monitoring of contact networks in carceral settings and provides valuable insights for epidemic modeling and intervention strategies, including quarantine, depopulation, and vaccination, laying a foundation for understanding disease dynamics in such environments.Top of Form.

Keywords: Incarceration; Jails; Network science; Prisons; SARS-CoV-2; Social networks.

Fig. 1

PRISMA diagram of Fulton County Jail roster data used in analysis, by overall unique persons (n) and person days (p-d). From two starting datasets spanning October 2021 to May 2022, the combined dataset included 8525 unique jail residents, contributing 160,157 days. After exclusion of missing and non-standard locations and limited records to men, there were 6702 unique persons. For Omicron wave comparisons, we further stratified the rosters into January and April subsets.

Fig. 2

Schematic of Fulton County Jail (FCJ) representation in analysis. The FCJ main building are structured into two towers (North and South), each of which contain 7 floors. Each floor contains up to 6 blocks, and each (standard) block contains up to 19 cells. Transmission-relevant social contacts occur among residents sharing a cell, but can also occur among residents in the same block during free time spent outside the cell. We visualize the block-level and cell-level networks accordingly. This figure depicts a cross-sectional representation of the contact networks, although network dynamics (residents changing cells and blocks) were also evaluated in our analysis.

Fig. 3

Social network degree distribution for cell-level and block-level networks during January and April roster dates. Boxes display the average and spread of the momentary active degree at each date within the January dates versus the April dates.

Fig. 4

Cumulative degree distributions (proportion of residents with X or higher value of network degree), stratified by cell-level versus block-level degree definitions and January versus April 2022 date spans. The cumulative degree curves were higher at both cell-levels and block-levels for April compared to January.

Fig. 5

Mean dynamic network degree, counting the average number of unique contacts over the 11-day spans in January and April 2022 date ranges. Cumulative network degree starts at the cross-sectional value for cell-level and block-level degree on day 1, then monotonically increase as residents acquire new contacts due to movement within the jail.

Fig. 6

Age mixing in cell-level and block-level networks in the January and April roster date spans. Matrices are standardized to the total contacts in each age group, summing vertically to 1. There was stronger within-group age mixing in the cell-level compared to the block-level networks, and in both network types in January compared to April.