Megacities as drivers of national outbreaks: The 2017 chikungunya outbreak in Dhaka, Bangladesh

Abstract

Background: Several large outbreaks of chikungunya have been reported in the Indian Ocean region in the last decade. In 2017, an outbreak occurred in Dhaka, Bangladesh, one of the largest and densest megacities in the world. Population mobility and fluctuations in population density are important drivers of epidemics. Measuring population mobility during outbreaks is challenging but is a particularly important goal in the context of rapidly growing and highly connected cities in low- and middle-income countries, which can act to amplify and spread local epidemics nationally and internationally.

Methods: We first describe the epidemiology of the 2017 chikungunya outbreak in Dhaka and estimate incidence using a mechanistic model of chikungunya transmission parametrized with epidemiological data from a household survey. We combine the modeled dynamics of chikungunya in Dhaka, with mobility estimates derived from mobile phone data for over 4 million subscribers, to understand the role of population mobility on the spatial spread of chikungunya within and outside Dhaka during the 2017 outbreak.

Results: We estimate a much higher incidence of chikungunya in Dhaka than suggested by official case counts. Vector abundance, local demographics, and population mobility were associated with spatial heterogeneities in incidence in Dhaka. The peak of the outbreak in Dhaka coincided with the annual Eid holidays, during which large numbers of people traveled from Dhaka to other parts of the country. We show that travel during Eid likely resulted in the spread of the infection to the rest of the country.

Conclusions: Our results highlight the impact of large-scale population movements, for example during holidays, on the spread of infectious diseases. These dynamics are difficult to capture using traditional approaches, and we compare our results to a standard diffusion model, to highlight the value of real-time data from mobile phones for outbreak analysis, forecasting, and surveillance.

Fig 1

(A) Weekly number of confirmed and estimated cases in the survey data. Orange dashed line shows the number of cases reported to the Institute of Epidemiology, Disease Control and Research (IEDCR) over the course of the outbreak. (B) Estimated cases per household for each survey location. (C) Estimated relative risks (incidence rate ratios) from poisson regression model. 95% Confidence intervals were calculated by applying the delta method [44] to robust standard errors.

Fig 2

(A) Observed and fitted weekly incidence. The blue line shows the observed incidence from the survey. The orange dotted line shows the best-fit model. The shaded region shows the full range of incidence for 100 simulations assuming a poisson error structure. (B) Daily prevalence of symptomatic and asymptomatic infections simulated using the best-fit model parameters. The grey shaded region indicates the time period beyond the survey timeframe.

Fig 3. Population movement patterns in Dhaka.

(A) Number of subscribers in a union versus the population size, for the unions covered by the survey. Map of Dhaka showing two measures of mobility: (B) the number of degrees in the network that had above average weight and (C) the average flow of people in and out of an area as a proportion of the population size. (D) Top panel: The daily proportion of subscribers who traveled from Dhaka to the rest of the country. This data represents the 4.4 million subscribers within the study area. Bottom panel: Daily number of subscribers (log count) traveling from Dhaka to all other districts. Districts are arranged from top to bottom by distance from Dhaka in ascending order.

Fig 4. Spatial heterogeneity in estimated importation time.

Introduction is defined here as the importation of at least ten cases, and measured as days since the start of the outbreak in Dhaka. The map on the left shows the estimated introduction time for each district based on mobility estimates. Lighter colors indicate earlier introduction. The districts that reported suspected cases to IEDCR are highlighted in red. The location of Dhaka city is indicated with the black circle. The difference between estimates using mobile phone data and a diffusion model are highlighted in the map on the right. In general, the diffusion model predicts earlier introduction (green) to nearby locations, and later (purple) or no introduction to more distant locations.

Fig 5. Daily simulated imported cases (log count) from Dhaka to other districts in Bangladesh using (A) mobility estimates versus a (B) diffusion model.

Importations are simulated assuming only the asymptomatic infected are traveling (p_eff = 0.1). Each row represents a district; districts are arranged from top to bottom by distance from Dhaka in ascending order. The districts that reported suspected cases to IEDCR are highlighted in red.