Abstract
Dengue has been as an endemic with year‐round presence in Singapore. In the recent years 2013, 2014, and 2016, there were several severe dengue outbreaks, posing serious threat to the public health. To proactively control and mitigate the disease spread, early warnings of dengue outbreaks, at which there are rapid and large‐scale spread of dengue incidences, are extremely helpful. In this study, a two‐step framework is proposed to predict dengue outbreaks and it is evaluated based on the dengue incidences in Singapore during 2012 to 2017. First, a generalized additive model (GAM) is trained based on the weekly dengue incidence data during 2006 to 2011. The proposed GAM is a one‐week‐ahead forecasting model, and it inherently accounts for the possible correlation among the historical incidence data, making the residuals approximately normally distributed. Then, an exponentially weighted moving average (EWMA) control chart is proposed to sequentially monitor the weekly residuals during 2012 to 2017. Our investigation shows that the proposed two‐step framework is able to give persistent signals at the early stage of the outbreaks in 2013, 2014, and 2016, which provides early alerts of outbreaks and wins time for the early interventions and the preparation of necessary public health resources. In addition, extensive simulations show that the proposed method is comparable to other potential outbreak detection methods and it is robust to the underlying data‐generating mechanisms.
Highlights
Dengue is an arthropod-borne viral disease transmitted by the Aedes aegypti and Aedes albopictus mosquitos
As seen from the ACF and partial ACF plots of the residuals in Figure 4, there is no significant autocorrelation among the residuals. All these results demonstrate that the proposed generalized additive model (GAM) can serve as an appropriate model for the dengue count data, and residuals so obtained can be treated as appropriate inputs for a conventional exponentially weighted moving average (EWMA) control chart
Based on the estimation results in phase I, the upper control limit for this EWMA chart can be obtained by the R package “spc.” On the other hand, the EWMA control chart based on the proposed Gaussian error GAM in Section 3 could still be applied to deal with this Poisson distributed dataset
Summary
Dengue is an arthropod-borne viral disease transmitted by the Aedes aegypti and Aedes albopictus mosquitos. In a typical disease surveillance dataset, the conventional assumptions for the use of a control chart, for example, normality, independence and stationary, are often violated.10 To deal with these problems, a two-step framework for sequential detection of disease outbreak is proposed in this study. Data are incorporated to train the GAM only if the weekly peak incidence in that year is below the annual threshold determined by the Ministry of Health (MOH) of Singapore at the beginning of each year This procedure approximately selects the normal (or in-control) dengue data so that the trained GAM could be used for outbreak detection. By taking advantage of the proposed GAM, we use the conventional EWMA chart to monitor the residuals, that is, the (log-transformed) difference between the predicted weekly incidence and the observed one This procedure is much easier for practitioners to follow and implement.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
