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: The avian influenza A H7N9 virus has caused infections in human beings in China since 2013. A large epidemic in 2016-17 prompted concerns that the epidemiology of the virus might have changed, increasing the threat of a pandemic. We aimed to describe the epidemiological characteristics, clinical severity, and time-to-event distributions of patients infected with A H7N9 in the 2016-17 epidemic compared with previous epidemics.Methods: In this epidemiological study, we obtained information about all laboratory-confirmed human cases of A H7N9 virus infection reported in mainland China as of Feb 23, 2017, from an integrated electronic database managed by the China Center for Disease Control and Prevention (CDC) and provincial CDCs. Every identified human case of A H7N9 virus infection was required to be reported to China CDC within 24 h via a national surveillance system for notifiable infectious diseases. We described the epidemiological characteristics across epidemics, and estimated the risk of death, mechanical ventilation, and admission to the intensive care unit for patients admitted to hospital for routine clinical practice rather than for isolation purpose. We estimated the incubation periods, and time delays from illness onset to hospital admission, illness onset to initiation of antiviral treatment, and hospital admission to death or discharge using survival analysis techniques.Findings: Between Feb 19, 2013, and Feb 23, 2017, 1220 laboratory-confirmed human infections with A H7N9 virus were reported in mainland China, with 134 cases reported in the spring of 2013, 306 in 2013-14, 219 in 2014-15, 114 in 2015-16, and 447 in 2016-17. The 2016-17 A H7N9 epidemic began earlier, spread to more districts and counties in affected provinces, and had more confirmed cases than previous epidemics. The proportion of cases in middle-aged adults increased steadily from 41% (55 of 134) to 57% (254 of 447) from the first epidemic to the 2016-17 epidemic. Proportions of cases in semi-urban and rural residents in the 2015-16 and 2016-17 epidemics (63% [72 of 114] and 61% [274 of 447], respectively) were higher than those in the first three epidemics (39% [52 of 134], 55% [169 of 306], and 56% [122 of 219], respectively). The clinical severity of individuals admitted to hospital in the 2016-17 epidemic was similar to that in the previous epidemics.Interpretation: Age distribution and case sources have changed gradually across epidemics since 2013, while clinical severity has not changed substantially. Continued vigilance and sustained intensive control efforts are needed to minimise the risk of human infection with A H7N9 virus.Funding: The National Science Fund for Distinguished Young Scholars. [ABSTRACT FROM AUTHOR]