Transmission dynamics of SARS-CoV-2 in a strictly-Orthodox Jewish community in the UK

Abstract

Some social settings such as households and workplaces, have been identified as high risk for SARS-CoV-2 transmission. Identifying and quantifying the importance of these settings is critical for designing interventions. A tightly-knit religious community in the UK experienced a very large COVID-19 epidemic in 2020, reaching 64.3% seroprevalence within 10 months, and we surveyed this community both for serological status and individual-level attendance at particular settings. Using these data, and a network model of people and places represented as a stochastic graph rewriting system, we estimated the relative contribution of transmission in households, schools and religious institutions to the epidemic, and the relative risk of infection in each of these settings. All congregate settings were important for transmission, with some such as primary schools and places of worship having a higher share of transmission than others. We found that the model needed a higher general-community transmission rate for women (3.3-fold), and lower susceptibility to infection in children to recreate the observed serological data. The precise share of transmission in each place was related to assumptions about the internal structure of those places. Identification of key settings of transmission can allow public health interventions to be targeted at these locations.

Figure 1

The data and formulation of the people and places network. (A) Illustrative representation of a bipartite people and places network. Circles represent people and squares represent places. All people are connected to a household (H). Some people are connected to primary (P) or secondary (S) schools, places of worship (G) or ritual baths (M). The orange dotted, and red solid edges represent embeddings of a transmission rule (Eq. 6) capturing the situation immediately before a transmission event that will result in the individual p14 becoming infected. (B) The distribution of the fraction of individuals in each setting who were male. Households were mixed, but the attendees of both primary and secondary schools were strongly bimodal: either predominantly male or predominantly female. Attendance at places of worship and ritual baths was predominantly reported by males. Overall, the community was balanced to within a few percent. (C) The distribution of average ages in the various settings (for the community in general, this is simply the age distribution of individuals). Note that attendance at primary school is disjoint with attendance at secondary schools, and attendance at schools was mostly disjoint with places of worship or ritual baths.

Figure 2

Transmission activity and positive test distributions. (A) Share of transmission attributable to different settings or location types according to the simulation. (B) Relative risk of transmission in different settings. This is the amount of transmission that occurred in a given setting relative to the total amount of transmission that is possible in that setting. There is a clear separation between the general community, households, and all other kinds of place. (C) Probability distributions of positive test results for households of size 1–10 after censoring. The observed distributions are in dark blue and simulations in light blue. (D) Probability of positive test result by age and sex after censoring. Square, triangle and circle marks indicate the values measured by serosurvey, error bars belong to the simulated values. Note that the model is not explicitly fitted to these data.

Figure 3

Fraction of within-household transmission events for households of size 1–10. Mean and percentile contours are shown for the fraction of transmission events within households. The maximal contours represent the 95% confidence interval computed as the region contained between $P_{2.5\%}$ (coincident with the horizontal axis) and $P_{97.5\%}$.

Figure 4

Comparison of epidemic sizes with altered network structure. These figures show estimates of epidemic sizes under conditions where primary schools and places of worship have separately been split such that no institution is larger than the percentile size indicated on the horizontal axis. (A) Shows the peak size of the epidemic and (B) shows the final size, indicated with bars and the left-hand axis scale. The solid lines and the right-hand axis scale show the percentile institution size.