The role of vaccine coverage within social networks in cholera vaccine efficacy

Abstract

Background: Traditional vaccine trial methods have an underlying assumption that the effect of a vaccine is the same throughout the trial area. There are, however, many spatial and behavioral factors that alter the rates of contact among infectious and susceptible individuals and result in different efficacies across a population. We reanalyzed data from a field trial in Bangladesh to ascertain whether there is evidence of indirect protection from cholera vaccines when vaccination rates are high in an individual's social network.

Methods: We analyzed the first year of surveillance data from a placebo-controlled trial of B subunit-killed whole-cell and killed whole-cell-only oral cholera vaccines in children and adult women in Bangladesh. We calculated whether there was an inverse trend for the relation between the level of vaccine coverage in an individual's social network and the incidence of cholera in individual vaccine recipients or placebo recipients after controlling for potential confounding variables.

Results: Using bari-level social network ties, we found incidence rates of cholera among placebo recipients were inversely related to levels of vaccine coverage (5.28 cases per 1000 in the lowest quintile vs 3.27 cases per 1000 in the highest quintile; p = 0.037 for trend). Receipt of vaccine by an individual and the level of vaccine coverage of the individual's social network were independently related to a reduced risk of cholera.

Conclusions: Findings indicate that progressively higher levels of vaccine coverage in bari-level social networks can lead to increasing levels of indirect protection of non-vaccinated individuals and could also lead to progressively higher levels of total protection of vaccine recipients.

Figure 1. Matrix network example of bari-level kinship social connections.

GREY circles indicate baris while RED lines indicate a kinship-based social connection between the two linked baris.

Figure 2. Graph network example of bari-level kinship social connections.

A “0” indicates no social connection between two baris while a “1” indicates a kinship-based social connection exists.

Figure 3. Risk of cholera and protective efficacy of killed oral cholera vaccines, by level of vaccine coverage in household-level social networks.

** p<0.01 for the difference in risk between vaccinees and placebo recipients. Note: Quintile values are as follows: <27.2%, 27.2-40.0%, 40.1-50.0%, 50.1-62.5%, >62.5%. GREY bars show vaccine protective efficacy by quintile of vaccine coverage within social networks developed using household-level kinship connections. The number shown above each bar is the calculated protective efficacy. The RED line indicates the risk of cholera for placebo recipients while the BLUE line indicates the risk of cholera for vaccine recipients by quintile of vaccine coverage within social networks. The numbers contained in the table below the graph indicate the calculated cholera risk for each group. An asterisk (**) indicate that the cholera risk per 1,000 was significantly different between the placebo and vaccine groups (e.g., the confidence intervals for the two calculated rates did not overlap). Quintiles show the proportion of a person's social network that was vaccinated (e.g., for quintile 1, <27.2% of people in an individual's social network were administered the cholera vaccine).

Figure 4. Risk of cholera and protective efficacy of killed oral cholera vaccines, by level of vaccine coverage in bari-level social networks.

**p<0.01 for the difference in risk between vaccinees and placebo recipients; * p<0.05 for the difference in risk between vaccinees and placebo recipients. Note: Quintile values are as follows: <28.7, 28.7-37.9%, 38.0-44.9%, 45.0-51.8%, >51.8%. GREY bars show vaccine protective efficacy by quintile of vaccine coverage within social networks developed using bari-level kinship connections. The number shown above each bar is the calculated protective efficacy. The RED line indicates the risk of cholera for placebo recipients while the BLUE line indicates the risk of cholera for vaccine recipients by quintile of vaccine coverage within social networks. The numbers contained in the table below the graph indicate the calculated cholera risk for each group. An asterisk (**) indicate that the cholera risk per 1,000 was significantly different between the placebo and vaccine groups (e.g., the confidence intervals for the two calculated rates did not overlap). Quintiles show the proportion of a person's social network that was vaccinated (e.g., for quintile 1, <28.7% of people in an individual's social network were administered the cholera vaccine).