Assessing the population at risk of Zika virus in Asia - is the emergency really over?

Abstract

On November 18, 2016, the WHO ended its designation of the Zika virus (ZIKV) epidemic as a Public Health Emergency of International Concern (PHEIC). At the same time, ZIKV transmission continues in Asia, with the number of Asian countries reporting Zika cases increasing over the last 2 years. Applying a method that combines epidemiological theory with data on epidemic size and drivers of transmission, we characterised the population at risk of ZIKV infection from Aedes aegypti mosquitoes in 15 countries in Asia. Projections made under the assumption of no pre-existing immunity suggest that up to 785 (range: 730-992) million people in Asia would be at risk of ZIKV infection under that scenario. Assuming that 20% of ZIKV infections are symptomatic, this implies an upper limit of 146-198 million for the population at risk of a clinical episode of Zika. Due to limited information about pre-existing immunity to ZIKV in the region, we were unable to make specific numerical projections under a more realistic assumption about pre-existing immunity. Even so, combining numerical projections under an assumption of no pre-existing immunity together with theoretical insights about the extent to which pre-existing immunity may lower epidemic size, our results suggest that the population at risk of ZIKV infection in Asia could be even larger than in the Americas. As a result, we conclude that the WHO's removal of the PHEIC designation should not be interpreted as an indication that the threat posed by ZIKV has subsided.

Keywords: arboviruses; dengue; epidemiology; medical entomology; public health.

Figure 1

Comparison of model projections of infection attack rate (IAR) (blue and red) and empirical estimates of IAR (black) for each of 17 sites. Coloured violin plots show the distribution of 1,000 Monte Carlo samples of model projections of IAR at the 13 sites used to calibrate the model (blue) and at the four sites used to independently validate the model (red). Black lines show the 95% posterior predictive intervals of empirical estimates of IAR of either CHIKV or ZIKV at those sites, and the points shows the respective medians.

Figure 2

Model-based projections of ZIKV epidemic potential in Asia. (A) Median projections of first-wave ZIKV infection attack rates at 5 km x 5 km resolution across Bangladesh, Brunei, Cambodia, India, Indonesia, Laos, Malaysia, Myanmar, Pakistan, Philippines, Singapore, Sri Lanka, Timor-Leste, Thailand, and Vietnam, using the approach by Perkins et al. These projected infection attack rates were combined with spatial demographic data to project (D) expected numbers of infections for men and women of all ages and then (B, C) summed nationally. These location-specific projections are shown in greater detail for (E) western Java, (F) southern Vietnam, (G) Bangladesh, and (H) Singapore and Kuala Lumpur. Tables indicate median values and the total range of values from 1,000 Monte Carlo samples that reflect uncertainty in model parameters.

Figure 3

The effect of pre-existing immunity on infection attack rates (IAR). The nonlinear relationship between the basic reproduction number R ₀ and the infection attack rate IAR implies that the same level of pre-existing immunity 1-s could have different impacts on future epidemics of ZIKV in Asia, depending on location-specific values of R ₀ or, in other words, the overall potential for transmission in a given area. Consider a population with 50% pre-existing immunity. The reproduction number R = (1-s) R ₀=R ₀/2. For locations with high R ₀, this reduces IAR to IAR_i by a relatively small fraction (eg, 19%). For locations with low R ₀, this reduces IAR to IAR_i by a relatively large fraction (eg, 92%). In both scenarios, IAR_i is the projected infection attack rate among individuals susceptible at the onset of the epidemic in question.