Predictive modelling of Ross River virus notifications in southeastern Australia

Abstract

Ross River virus (RRV) is a mosquito-borne virus endemic to Australia. The disease, marked by arthritis, myalgia and rash, has a complex epidemiology involving several mosquito species and wildlife reservoirs. Outbreak years coincide with climatic conditions conducive to mosquito population growth. We developed regression models for human RRV notifications in the Mildura Local Government Area, Victoria, Australia with the objective of increasing understanding of the relationships in this complex system, providing trigger points for intervention and developing a forecast model. Surveillance, climatic, environmental and entomological data for the period July 2000-June 2011 were used for model training then forecasts were validated for July 2011-June 2015. Rainfall and vapour pressure were the key factors for forecasting RRV notifications. Validation of models showed they predicted RRV counts with an accuracy of 81%. Two major RRV mosquito vectors (Culex annulirostris and Aedes camptorhynchus) were important in the final estimation model at proximal lags. The findings of this analysis advance understanding of the drivers of RRV in temperate climatic zones and the models will inform public health agencies of periods of increased risk.

Keywords: Arboviruses; modelling; notifiable infectious diseases; surveillance.

Fig. 1.

Study extent of predictive modelling of Ross River virus cases in the Mildura Local Government Area (LGA) (shaded grey), Victoria, Australia, for the period 1 July 2000 to 30 June 2015. The black circle represents the location of the Mildura airport weather station. The Murray River forms the northern border of the Mildura LGA.

Fig. 2.

Monthly time-series, predictions and forecasts of notified Ross River virus cases in the Mildura Local Government Area, Victoria, Australia, for the period 1 July 2000 to 30 June 2015. Data for the Australian financial year 2010/2011 have been rescaled by a factor of 3. Dotted lines represent upper 95% prediction intervals.