Prediction of high incidence of dengue in the Philippines.

Background Accurate prediction of dengue incidence levels weeks in advance of an outbreak may reduce the morbidity and mortality associated with this neglected disease. Therefore, models were developed to predict high and low dengue incidence in order to provide timely forewarnings in the Philippines. Methods Model inputs were chosen based on studies indicating variables that may impact dengue incidence. The method first uses Fuzzy Association Rule Mining techniques to extract association rules from these historical epidemiological, environmental, and socio-economic data, as well as climate data indicating future weather patterns. Selection criteria were used to choose a subset of these rules for a classifier, thereby generating a Prediction Model. The models predicted high or low incidence of dengue in a Philippines province four weeks in advance. The threshold between high and low was determined relative to historical incidence data. Principal Findings Model accuracy is described by Positive Predictive Value (PPV), Negative Predictive Value (NPV), Sensitivity, and Specificity computed on test data not previously used to develop the model. Selecting a model using the F-0.5 measure, which gives PPV more importance than Sensitivity, gave these results: PPV = 0.780, NPV = 0.938, Sensitivity = 0.547, Specificity = 0.978. Using the F-3 measure, which gives Sensitivity more importance than PPV, the selected model had PPV = 0.778, NPV = 0.948, Sensitivity = 0.627, Specificity = 0.974. The decision as to which model has greater utility depends on how the predictions will be used in a particular situation. Conclusions This method builds prediction models for future dengue incidence in the Philippines and is capable of being modified for use in different situations; for diseases other than dengue; and for regions beyond the Philippines. The Philippines dengue prediction models predicted high or low incidence of dengue four weeks in advance of an outbreak with high accuracy, as measured by PPV, NPV, Sensitivity, and Specificity. Author Summary A largely automated methodology is described for creating models that use past and recent data to predict dengue incidence levels several weeks in advance for a specific time period and a geographic region that can be sub-national. The input data include historical and recent dengue incidence, socioeconomic factors, and remotely sensed variables related to weather, climate, and the environment. Among the climate variables are those known to indicate future weather patterns that may or may not be seasonal. The final prediction models adhere to these principles: 1) the data used must be available at the time the prediction is made (avoiding pitfalls made by studies that use recent data that, in actual practice, would not be available until after the date the prediction was made); and 2) the models are tested on data not used in their development (thereby avoiding overly optimistic measures of accuracy of the prediction). Local public health preferences for low numbers of false positives and negatives are taken into account. These models appear to be robust even when applied to nearby geographic regions that were not used in model development. The method may be applied to other vector borne and environmentally affected diseases.