Neural Networks for Dengue Prediction: A Systematic Review

Abstract

Objectives: Due to a lack of treatments and universal vaccine, early forecasts of Dengue are an important tool for disease control. Neural networks are powerful predictive models that have made contributions to many areas of public health. In this systematic review, we provide an introduction to the neural networks relevant to Dengue forecasting and review their applications in the literature. The objective is to help inform model design for future work. Methods: Following the PRISMA guidelines, we conduct a systematic search of studies that use neural networks to forecast Dengue in human populations. We summarize the relative performance of neural networks and comparator models, model architectures and hyperparameters, as well as choices of input features. Results: Nineteen papers were included. Most studies implement shallow neural networks using historical Dengue incidence and meteorological input features. Prediction horizons tend to be short. Building on the strengths of neural networks, most studies use granular observations at the city or sub-national level. Performance of neural networks relative to comparators such as Support Vector Machines varies across study contexts. Conclusions: The studies suggest that neural networks can provide good predictions of Dengue and should be included in the set of candidate models. The use of convolutional, recurrent, or deep networks is relatively unexplored but offers promising avenues for further research, as does the use of a broader set of input features such as social media or mobile phone data.

A Deep Learning Approach for Dengue Fever Prediction in Malaysia Using LSTM with Spatial Attention

“…The authors also discuss the strengths and limitations of these techniques. The most common models are support vector machines [7], decision trees [8], random forests [9], and neural networks [10]. In addition, several studies have compared those machine learning models for dengue prediction in different contexts [11][12][13][14].…”