Ensemble method for dengue prediction

Abstract

BackgroundIn the 2015 NOAA Dengue Challenge, participants made three dengue target predictions for two locations (Iquitos, Peru, and San Juan, Puerto Rico) during four dengue seasons: 1) peak height (i.e., maximum weekly number of cases during a transmission season; 2) peak week (i.e., week in which the maximum weekly number of cases occurred); and 3) total number of cases reported during a transmission season. A dengue transmission season is the 12-month period commencing with the location-specific, historical week with the lowest number of cases. At the beginning of the Dengue Challenge, participants were provided with the same input data for developing the models, with the prediction testing data provided at a later date.MethodsOur approach used ensemble models created by combining three disparate types of component models: 1) two-dimensional Method of Analogues models incorporating both dengue and climate data; 2) additive seasonal Holt-Winters models with and without wavelet smoothing; and 3) simple historical models. Of the individual component models created, those with the best performance on the prior four years of data were incorporated into the ensemble models. There were separate ensembles for predicting each of the three targets at each of the two locations.Principal findingsOur ensemble models scored higher for peak height and total dengue case counts reported in a transmission season for Iquitos than all other models submitted to the Dengue Challenge. However, the ensemble models did not do nearly as well when predicting the peak week.ConclusionsThe Dengue Challenge organizers scored the dengue predictions of the Challenge participant groups. Our ensemble approach was the best in predicting the total number of dengue cases reported for transmission season and peak height for Iquitos, Peru.

Multivariable prediction model for predicting deaths in severe dengue cases

“…Modelling studies in outbreak prediction utilised several predictive analytics which includes ensemble methods, time series regression, and support vector machine. [10][11][12][13][14][15][16] Modelling studies involving earlier clinical aspects of management of dengue -identifying and stratifying dengue -used decision trees, logistic regression, and structural equation models. [17][18][19][20][21] However, only three studies have modelled prediction of death.…”

“…Most predictive modelling studies have been conducted for the prediction of dengue outbreak. [10][11][12][13][14][15][16] Several studies have looked at two clinical aspects of dengue management: predicting the identification of dengue in unselected cases of febrile illnesses, 17,18 and predicting the severity of the disease. 17,19,20,21 Early recognition of dengue infection and severity stratification would improve clinical management amnd lead to a better outcome.…”

Review on Nowcasting using Least Absolute Shrinkage Selector Operator (LASSO) to Predict Dengue Occurrence in San Juan and Iquitos as Part of Disease Surveillance System

“…The authors were able to deduce from the significant coefficients from MLR and WMLR models that vegetation and precipitation had negative impact while humidity and maximum temperature had positive influence on dengue occurrence. Buczak et al [31] was another winning team from the 2015 challenge. Their ensemble algorithm weighted the top 300 performing models from among the following by comparing their forecast errors in the past four years: (1) 1248 distinct additive seasonal Holt-Winters (HW) models which were created by tuning various parameters (with / without wavelet smoothing, periods of seasonality, ending weeks, optimization using RMSE or mean absolute percentage error (MAPE)).…”

Predicting hyperlipidemia using enhanced ensemble classifier

“…In the ensemble approach, various classification techniques are combined in order to improve the accuracy of the entire model. Various researches have been conducted for developing efficient systems using ensemble approach [20], [21], [22], [23]. In this project, we have used SVM, Naïve Bayes, KNN and Decision Tree for developing the ensemble classifier.…”