High Zika Virus Seroprevalence in Salvador, Northeastern Brazil Limits the Potential for Further Outbreaks

Abstract

During 2015 to 2016, Brazil reported more Zika virus (ZIKV) cases than any other country, yet population exposure remains unknown. Serological studies of ZIKV are hampered by cross-reactive immune responses against heterologous viruses. We conducted serosurveys for ZIKV, dengue virus (DENV), and Chikungunya virus (CHIKV) in 633 individuals prospectively sampled during 2015 to 2016, including microcephaly and non-microcephaly pregnancies, HIV-infected patients, tuberculosis patients, and university staff in Salvador in northeastern Brazil using enzyme-linked immunosorbent assays (ELISAs) and plaque reduction neutralization tests. Sera sampled retrospectively during 2013 to 2015 from 277 HIV-infected patients were used to assess the spread of ZIKV over time. Individuals were georeferenced, and sociodemographic indicators were compared between ZIKV-positive and -negative areas and areas with and without microcephaly cases. Epidemiological key parameters were modeled in a Bayesian framework. ZIKV seroprevalence increased rapidly during 2015 to 2016, reaching 63.3% by 2016 (95% confidence interval [CI], 59.4 to 66.8%), comparable to the seroprevalence of DENV (75.7%; CI, 69.4 to 81.1%) and higher than that of CHIKV (7.4%; CI, 5.6 to 9.8%). Of 19 microcephaly pregnancies, 94.7% showed ZIKV IgG antibodies, compared to 69.3% of 257 non-microcephaly pregnancies (P = 0.017). Analyses of sociodemographic data revealed a higher ZIKV burden in low socioeconomic status (SES) areas. High seroprevalence, combined with case data dynamics allowed estimates of the basic reproduction number R₀ of 2.1 (CI, 1.8 to 2.5) at the onset of the outbreak and an effective reproductive number R_eff of <1 in subsequent years. Our data corroborate ZIKV-associated congenital disease and an association of low SES and ZIKV infection and suggest that population immunity caused cessation of the outbreak. Similar studies from other areas will be required to determine the fate of the American ZIKV outbreak.IMPORTANCE The ongoing American Zika virus (ZIKV) outbreak involves millions of cases and has a major impact on maternal and child health. Knowledge of infection rates is crucial to project future epidemic patterns and determine the absolute risk of microcephaly upon maternal ZIKV infection during pregnancy. For unknown reasons, the vast majority of ZIKV-associated microcephaly cases are concentrated in northeastern Brazil. We analyzed different subpopulations from Salvador, a Brazilian metropolis representing one of the most affected areas during the American ZIKV outbreak. We demonstrate rapid spread of ZIKV in Salvador, Brazil, and infection rates exceeding 60%. We provide evidence for the link between ZIKV and microcephaly, report that ZIKV predominantly affects geographic areas with low socioeconomic status, and show that population immunity likely caused cessation of the outbreak. Our results enable stakeholders to identify target populations for vaccination and for trials on vaccine efficacy and allow refocusing of research efforts and intervention strategies.

Keywords: Zika virus; microcephaly; risk factors; serology; socioeconomic status.

FIG 1

Ranking of Brazilian states according to the United Nations Development Programme. Longevity (gray), income (orange) and education (red) indexes, and the human development index (blue) as the geometric mean of the three aformentioned indexes. Data retrieved from Atlas Brazil, 2013 (http://www.atlasbrasil.org.br/2013/). The northeastern state Bahia is shown in bold and red.

FIG 2

Serosurveys and distribution of specimens per age category. (A) Main research question, time span of sampling, and specimens per subpopulation. (B) Distribution of specimens per age category. Only specimens sampled for all subpopulations in 2015 to 2016 were included due to low Zika virus prevalence in the preceding years. The numbers (n) of study participants for which age information was available are given below the age categories. Age data for Salvador were retrieved from the 2010 census (https://cidades.ibge.gov.br/brasil/ba/salvador/panorama).

FIG 3

ZIKV seroprevalence and reported cases. (A) ZIKV, CHIKV, and DENV seroprevalence in parturients. Non-microcephaly pregnancies (PRG) (n = 257 for ZIKV IgG and CHIKV IgG and n = 69 for DENV IgG); microcephaly pregnancies (MC) (n = 19 for ZIKV IgG and CHIKV IgG and n = 0 for DENV IgG). (B) ZIKV, CHIKV, and DENV seroprevalence in HIV-positive patients from 2013 (n = 96 for ZIKV IgG and CHIKV IgG and n = 52 for DENV IgG), 2014 (n = 89 for ZIKV IgG and CHIKV IgG and n = 57 for DENV IgG), 2015 (n = 92 for ZIKV IgG and CHIKV IgG and n = 46 for DENV IgG), and 2016 (n = 263 for ZIKV IgG and CHIKV IgG and n = 110 for DENV IgG). (C) ZIKV, CHIKV, and DENV seroprevalence in tuberculosis patients (TBC) (n = 55 for ZIKV IgG and CHIKV IgG and n = 8 for DENV IgG) and university employees (UNI) (n = 39 for ZIKV IgG and CHIKV IgG and n = 20 for DENV IgG). (D) ZIKV, CHIKV, and DENV seroprevalence in all 633 samples from 2016. The bars in panels A to D depict 95% confidence intervals. (E) Seroprevalence per age group for ZIKV IgG, CHIKV, and DENV in 633 samples from 2016. (F) Reported Brazilian cases of acute exanthematic disease in Salvador and Bahia until epidemiological week 22 in 2017. The months are indicated by capital first letter.

FIG 4

Transmission model and projected trajectory of the Zika epidemic in Salvador, Brazil. (A) Model fit to ZIKV incidence in Salvador. The red circles show the reported ZIKV cases. The black line shows the median model estimate. The shaded regions depict the interquartile range and 95% CI. (B) ZIKV seroprevalence over time in the study population (n = 633). The black line shows the median model estimate. The shaded regions depict the interquartile range (IQR) and 95% CI. The red circle shows the observed proportion of seropositive individuals. (C) Estimated seasonal variation in ZIKV transmission. (D) Estimated change in effective reproduction number over time.

FIG 5

Association of socioeconomic status and ZIKV exposure. (A) Maps showing Brazil, the state of Bahia, metropolitan Salvador, and sample distribution onto human development units (HDUs). (B) Sociodemographic indicators differing significantly between ZIKV-positive and ZIKV-negative HDUs. Boxplots show medians, interquartile range (box length), outliers (circles), and extreme values (squares). Values that are significantly different are indicated by bars and asterisks as follows: *, P ≤ 0.05; **, P < 0.01. (C) Distribution of samples used for nested case-control study. ZIKV-positive and -negative cases and microcephaly pregnancies (stars; n = 11) are shown. One additional case was outside the area shown in the map. Seven other cases were insufficiently georeferenced. Due to geographic proximity of home adresses of some controls, not all 72 controls are visible.