Enhanced surveillance for Rift Valley Fever in livestock during El Niño rains and threat of RVF outbreak, Kenya, 2015-2016

Abstract

Background: In mid-2015, the United States' Pandemic Prediction and Forecasting Science and Technical Working Group of the National Science and Technology Council, Food and Agriculture Organization Emergency Prevention Systems, and Kenya Meteorological Department issued an alert predicting a high possibility of El-Niño rainfall and Rift Valley Fever (RVF) epidemic in Eastern Africa.

Methodology/principal findings: In response to the alert, the Kenya Directorate of Veterinary Services (KDVS) carried out an enhanced syndromic surveillance system between November 2015 and February 2016, targeting 22 RVF high-risk counties in the country as identified previously through risk mapping. The surveillance collected data on RVF-associated syndromes in cattle, sheep, goats, and camels from >1100 farmers through 66 surveillance officers. During the 14-week surveillance period, the KDVS received 10,958 reports from participating farmers and surveillance officers, of which 362 (3.3%) had at least one syndrome. The reported syndromes included 196 (54.1%) deaths in young livestock, 133 (36.7%) abortions, and 33 (9.1%) hemorrhagic diseases, with most occurring in November and December, the period of heaviest rainfall. Of the 69 herds that met the suspect RVF herd definition (abortion in flooded area), 24 (34.8%) were defined as probable (abortions, mortalities in the young ones, and/or hemorrhagic signs) but none were confirmed.

Conclusion/significance: This surveillance activity served as an early warning system that could detect RVF disease in animals before spillover to humans. It was also an excellent pilot for designing and implementing syndromic surveillance in animals in the country, which is now being rolled out using a mobile phone-based data reporting technology as part of the global health security system.

Fig 1. Map of Kenya showing selected Rift Valley Fever (RVF) high-risk counties in grey.

A high-risk county was based on ecological and climatic factors associated with previous RVF outbreaks in Kenya, as defined by Munyua et al. [19]. The high-risk counties were selected for participation in the enhanced surveillance for RVF.

Fig 2. Illustration of RVF surveillance system conducted in Kenya between November 2015 and February 2016.

CDVS = County Director of Veterinary Services, RVF = Rift Valley Fever, SCVO = Sub-County Veterinary Officers.

Fig 3. Weekly number of abortions, bleeding, and death syndrome reports (top graph) and number of total reports (bottom graph) submitted to the Rift Valley Fever Alert Centre in Kenya, November 16, 2015 –February 29, 2016.

The total number of reports includes both syndromic and healthy reports.

Fig 4. Time-series plots of the weekly reporting for each syndrome by whether flooding and/or mosquito swarms were observed by farmers in their area.

Fig 5. Scatterplot and linear prediction of the correlation between the reporting of any syndrome (abortion, bleeding, or death) and observing flooding and mosquito swarms.

These variables showed high correlation, based on Pearson’s correlation coefficient (r > 0.87, p<0.001).

Fig 6. Geographic distribution of the number of Rift Valley Fever suspect and probable herds in Kenya between November 16, 2015 and February 29, 2016.

A suspected RVF herd was defined as a livestock herd reporting abortion in an area experiencing heavy rainfall and flooding. A probable RVF herd was defined as a suspect RVF case that also reported deaths in young livestock and/or hemorrhagic signs.

Fig 7. Mean monthly actual rainfall (light shaded bars and left x-axis) recorded in the participating counties and number of suspect and probable Rift Valley Fever (RVF) herds (dark shaded bars and right x-axis) reported in Kenya, November 2015 –February 2016.