Monitoring linked epidemics: the case of tuberculosis and HIV

Abstract

Background: The tight epidemiological coupling between HIV and its associated opportunistic infections leads to challenges and opportunities for disease surveillance.

Methodology/principal findings: We review efforts of WHO and collaborating agencies to track and fight the TB/HIV co-epidemic, and discuss modeling--via mathematical, statistical, and computational approaches--as a means to identify disease indicators designed to integrate data from linked diseases in order to characterize how co-epidemics change in time and space. We present R(TB/HIV), an index comparing changes in TB incidence relative to HIV prevalence, and use it to identify those sub-Saharan African countries with outlier TB/HIV dynamics. R(TB/HIV) can also be used to predict epidemiological trends, investigate the coherency of reported trends, and cross-check the anticipated impact of public health interventions. Identifying the cause(s) responsible for anomalous R(TB/HIV) values can reveal information crucial to the management of public health.

Conclusions/significance: We frame our suggestions for integrating and analyzing co-epidemic data within the context of global disease monitoring. Used routinely, joint disease indicators such as R(TB/HIV) could greatly enhance the monitoring and evaluation of public health programs.

Figure 1. Timeline used to generate values depicted in Figure 2.

The HIV time frame starts at t ₁ = 0, corresponding to 1997. In order to track the impact of HIV on TB, we delay the TB time frame by r = 3 years. Accordingly, we analyze TB data starting at t ₁+r = 3 years, i.e. 3 years after 1997, which corresponds to the year 2000. We have TB data until the year 2006, such that the length of our TB time frame spans 2000–2006, for a total of n = 7 years of TB data. Under our formulation this corresponds to t ₁+r+n = 10. Because optimally we compare trends for the same number of years for the two diseases, we also use 7 years of HIV data, t ₁+n = 7 years, i.e. from 1997–2003. Dashed lines indicate HIV, dotted lines indicate TB.

Figure 2. for Africa for the time point t ₁ corresponding to the year 1997.

Here n = 7 and r = 3. This index quantifies the change in TB incidence per 100,000 over the period 2000–2006 relative to the change in percent HIV prevalence over the period 1997–2003.

Figure 3. Schematic illustrating the population-level response of the HIV and TB epidemics to a novel HIV control measure.

The relative growth rates of percent HIV prevalence (solid line) and TB incidence (dashed line) epidemics before and after the novel intervention (which for example could be the delivery of a new antiretroviral) are captured by in three different time intervals i = 1, 2 and 3. These intervals start before the novel intervention (with t ₁ representing the first year for which we have data), when the novel intervention is first implemented (at year t ₂), and for the period starting at the point when TB incidence first decreases in scenario A (at year t ₃). Years t ₂ and t ₃ are represented by vertical lines. Because this diagram is a simple schematic we will not define exact values for the parameters t_i, n and r. While in both scenarios HIV prevalence decreases, in (A) TB incidence decreases after a certain time lag such that (omitting subscripts and common argument values) , while in (B) TB incidence continues to increase and , indicating that TB control is not reaping the benefits anticipated from the new HIV control measure.