Spatiotemporal variability in dengue transmission intensity in Jakarta, Indonesia

Abstract

Background: Approximately 70% of the global burden of dengue disease occurs on the Asian continent, where many large urban centres provide optimal environments for sustained endemic transmission and periodic epidemic cycles. Jakarta, the capital of Indonesia, is a densely populated megacity with hyperendemic dengue transmission. Characterization of the spatiotemporal distribution of dengue transmission intensity is of key importance for optimal implementation of novel control and prevention programmes, including vaccination. In this paper we use mathematical models to provide the first detailed description of spatial and temporal variability in dengue transmission intensity in Jakarta.

Methodology/principal findings: We applied catalytic models in a Bayesian framework to age-stratified dengue case notification data to estimate dengue force of infection and reporting probabilities in 42 subdistricts of Jakarta. The model was fitted to yearly and average annual data covering a 10-year period between 2008 and 2017. We estimated a long-term average annual transmission intensity of 0.130 (95%CrI: 0.129-0.131) per year in Jakarta province, ranging from 0.090 (95%CrI: 0.077-0.103) to 0.164 (95%CrI: 0.153-0.174) across subdistricts. Annual average transmission intensity in Jakarta province during the 10-year period ranged from 0.012 (95%CrI: 0.011-0.013) in 2017 to 0.124 (95%CrI: 0.121-0.128) in 2016.

Conclusions/significance: While the absolute number of dengue case notifications cannot be relied upon as a measure of endemicity, the age-distribution of reported dengue cases provides valuable insights into the underlying nature of transmission. Our estimates from yearly and average annual case notification data represent the first detailed estimates of dengue transmission intensity in Jakarta's subdistricts. These will be important to consider when assessing the population-level impact and cost-effectiveness of potential control and prevention programmes in Jakarta province, such as the controlled release of Wolbachia-carrying mosquitoes and vaccination.

Fig 1. Cumulative age-specific incidence of hospitalized dengue haemorrhagic fever (DHF) cases by region and subdistrict for the 10-year period between 2008 and 2017 in Jakarta province.

Grey lines show subdistrict age-distributions and black dashed lines show the average age-distribution of hospitalized DHF cases for the region. Dengue case notification data were obtained from the Jakarta Ministry of Health Epidemiological surveillance system (17). Subdistrict incidence rates and population age structures are reported in Tables B and C in the S1 Text.

Fig 2. Total force of infection (4λ) estimates obtained from the fit of model 2 variant PS (assuming reported hospitalised DHF cases are caused by primary or secondary infections) to annual DHF cases reported between 2008 and 2017.

Blue points show the median and the bars the 95% credible interval of the estimates obtained for the whole province of Jakarta. Green points represent the yearly median estimates obtained at the subdistrict level. Annual subdistrict parameter estimates are available in S2 File.

Fig 3. Spatial variation in average annual total dengue force of infection (4λ) estimates in Jakarta obtained from the fit of model 1 variant PS (assuming reported hospitalised DHF cases are caused by primary or secondary infections) to average annual hospitalised DHF data reported in 2008–2017.

(A) Map of median force of infection estimates per subdistrict; (B) median and 95% credible interval of the estimates reported in panel A. Blue dashed line and shading shows the median and 95% credible interval province-level average annual force of infection in 2008–2017. FOI: force of infection. Boundaries were obtained from Wikimedia Commons under a CC-BY 3.0 NL license and converted to shapefile format using QGIS (25,26).

Fig 4. Expected seroprevalence levels in Jakarta province.

(A) Expected proportion (median and 95% credible interval) of the population seropositive to dengue by age using the total force of infection (4λ) estimate obtained from the fit of model 1 variant PS (assuming all hospitalised DHF cases are caused by primary or secondary infections) to average annual hospitalised DHF data reported in the period 2008–2017 in Jakarta province (blue dashed line); Sawah Besar, the subdistrict with the lowest force of infection estimate (green); and Pasar Rebo, the subdistrict with the highest force of infection estimate (purple). The corresponding average force of infection estimate is given at the end of each line. (B) The proportion of subdistricts (N = 42) in Jakarta province that reach at least 50%, 70% and 90% seroprevalence by age, obtained from subdistrict force of infection estimates using model 1 variant PS fitted to the average annual incidence of hospitalised DHF cases reported in the period 2008–2017.