Search

Background: In China, dengue remains an important public health issue with expanded areas and increased incidence recently. Accurate and timely forecasts of dengue incidence in China are still lacking. We aimed to use the state-of-the-art machine learning algorithms to develop an accurate predictive model of dengue. Methodology/Principal findings: Weekly dengue cases, Baidu search queries and climate factors (mean temperature, relative humidity and rainfall) during 2011–2014 in Guangdong were gathered. A dengue search index was constructed for developing the predictive models in combination with climate factors. The observed year and week were also included in the models to control for the long-term trend and seasonality. Several machine learning algorithms, including the support vector regression (SVR) algorithm, step-down linear regression model, gradient boosted regression tree algorithm (GBM), negative binomial regression model (NBM), least absolute shrinkage and selection operator (LASSO) linear regression model and generalized additive model (GAM), were used as candidate models to predict dengue incidence. Performance and goodness of fit of the models were assessed using the root-mean-square error (RMSE) and R-squared measures. The residuals of the models were examined using the autocorrelation and partial autocorrelation function analyses to check the validity of the models. The models were further validated using dengue surveillance data from five other provinces. The epidemics during the last 12 weeks and the peak of the 2014 large outbreak were accurately forecasted by the SVR model selected by a cross-validation technique. Moreover, the SVR model had the consistently smallest prediction error rates for tracking the dynamics of dengue and forecasting the outbreaks in other areas in China. Conclusion and significance: The proposed SVR model achieved a superior performance in comparison with other forecasting techniques assessed in this study. The findings can help the government and community respond early to dengue epidemics. [ABSTRACT FROM AUTHOR]

Background: An explosive outbreak of dengue fever occurred in Guangdong Province, China in 2014. A community-based integrated intervention was applied to control this outbreak in the capital city Guangzhou, where dengue epidemic was mainly caused by imported cases. Methodology/Principal Findings: We used a time series generalized additive model based on meteorological factors to assess the effectiveness of this intervention. The results showed that there was significant reduction in mosquito density following the intervention, and there was a 70.47% (95% confidence interval: 66.07%, 74.88%) reduction in the reported dengue cases compared with the predicted cases after 12 days since the beginning of the intervention, we estimated that a total of 23,302 dengue cases were prevented. Conclusions: This study suggests that an integrated dengue intervention program has significant effects to control a dengue outbreak in areas where dengue epidemic was mainly caused by imported dengue cases. [ABSTRACT FROM AUTHOR]

Background Dengue fever is an important infectious disease in Guangzhou, China; previous studies on the effects of weather factors on the incidence of dengue fever did not consider the linearity of the associations. Methods This study evaluated the effects of daily mean temperature, relative humidity and rainfall on the incidence of dengue fever. A generalized additive model with splines smoothing function was performed to examine the effects of daily mean, minimum and maximum temperatures, relative humidity and rainfall on incidence of dengue fever during 2006–2014. Results Our analysis detected a non-linear effect of mean, minimum and maximum temperatures and relative humidity on dengue fever with the thresholds at 28 °C, 23 °C and 32 °C for daily mean, minimum and maximum temperatures, 76% for relative humidity, respectively. Below the thresholds, there was a significant positive effect, the excess risk in dengue fever for each 1 °C in the mean temperature at lag7–14 days was 10.21%, (95% CI: 6.62% to 13.92%), 7.10% (95% CI: 4.99%, 9.26%) for 1 °C increase in daily minimum temperature in lag 11 days, and 2.27% (95% CI: 0.84%, 3.72%) for 1 °C increase in daily maximum temperature in lag 10 days; and each 1% increase in relative humidity of lag7–14 days was associated with 1.95% (95% CI: 1.21% to 2.69%) in risk of dengue fever. Conclusions Future prevention and control measures and epidemiology studies on dengue fever should consider these weather factors based on their exposure-response relationship. [ABSTRACT FROM AUTHOR]