Epidemiology of Chikungunya Virus in Bahia, Brazil, 2014-2015

Abstract

Chikungunya is an emerging arbovirus that is characterized into four lineages. One of these, the Asian genotype, has spread rapidly in the Americas after its introduction in the Saint Martin island in October 2013. Unexpectedly, a new lineage, the East-Central-South African genotype, was introduced from Angola in the end of May 2014 in Feira de Santana (FSA), the second largest city in Bahia state, Brazil, where over 5,500 cases have now been reported. Number weekly cases of clinically confirmed CHIKV in FSA were analysed alongside with urban district of residence of CHIKV cases reported between June 2014 and October collected from the municipality's surveillance network. The number of cases per week from June 2014 until September 2015 reveals two distinct transmission waves. The first wave ignited in June and transmission ceased by December 2014. However, a second transmission wave started in January and peaked in May 2015, 8 months after the first wave peak, and this time in phase with Dengue virus and Zika virus transmission, which ceased when minimum temperature dropped to approximately 15°C. We find that shorter travelling times from the district where the outbreak first emerged to other urban districts of FSA were strongly associated with incidence in each district in 2014 (R(2)).

Keywords: Chikungunya; Epidemiology and surveillance; Virus; disease outbreak.

Dynamics of Chikungunya in Feira de Santana, Bahia, Brazil, in 2014-2015

Incidence of CHIKV, DENV and ZIKV (number of clinically confirmed cases) in Feira de Santana (FSA) district, Bahia state, Brazil. The red curve shows CHIKV incidence between weeks 13 and 53 in 2014 (an arrow indicates the arrival date of the index case to George Américo, GA, district)). The blue curve shows incidence between weeks 1 and 35 in 2015. For comparison, the numbers of DENV (dark grey) and ZIKV (light grey) cases in 2015 are shown. Curve fitting to incidence time-series data was performed using Poisson-smoothing in R software. Panel (b) shows the correlation (R² and p-value) between the estimated travel time (minutes) from GA to the geographic centre of each other urban district of residence in FSA presenting more than 10 cases in either 2014 or 2015, against the 2015 CHIKV incidence for each district in FSA. Panel (c) shows the equivalent results for 2014. Only urban districts with >10 reported cases in either year were considered. A map of Feira de Santana is shown with the number of cases per district of residence for 2014 (d) and 2015 (e).