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

Abstract

Dengue which was first detected mainly in South East Asia during 1940s is 
now a serious public health concern across the subtropical and temperate 
regions of Americas, Europe and China due to the change in global climate 
and international travel. Hence, 3.9 billion people in 128 countries are 
exposed to the danger of potentially fatal dengue infection. This is a review 
paper of various dengue forecasting methodology to identify suitable models 
for predicting the disease occurrence in San Juan, Puerto Rico and Iquitos, 
Peru. Least Absolute Shrinkage Selector Operator (LASSO) model using 
climatic variables and Google Trends search terms as predictors was proposed 
to forecast dengue cases four weeks in advance. LASSO’s flexibility in 
incorporating a variety of predictors and its ease of interpretation present 
LASSO as a compelling case against the general predictive models. Public 
health regulators could make use of such nowcasting model to facilitate the 
timing of vector control and public health campaigns along with the medical 
resource allocation to cope with potential dengue outbreaks.