Forecast of Dengue Cases in 20 Chinese Cities Based on the Deep Learning Method

Abstract

Dengue fever (DF) is one of the most rapidly spreading diseases in the world, and accurate forecasts of dengue in a timely manner might help local government implement effective control measures. To obtain the accurate forecasting of DF cases, it is crucial to model the long-term dependency in time series data, which is difficult for a typical machine learning method. This study aimed to develop a timely accurate forecasting model of dengue based on long short-term memory (LSTM) recurrent neural networks while only considering monthly dengue cases and climate factors. The performance of LSTM models was compared with the other previously published models when predicting DF cases one month into the future. Our results showed that the LSTM model reduced the average the root mean squared error (RMSE) of the predictions by 12.99% to 24.91% and reduced the average RMSE of the predictions in the outbreak period by 15.09% to 26.82% as compared with other candidate models. The LSTM model achieved superior performance in predicting dengue cases as compared with other previously published forecasting models. Moreover, transfer learning (TL) can improve the generalization ability of the model in areas with fewer dengue incidences. The findings provide a more precise forecasting dengue model and could be used for other dengue-like infectious diseases.

Association between meteorological factors and the prevalence dynamics of Japanese encephalitis

“…“Deep Learning”, a branch of artificial intelligence, allows autonomously learning how viruses spread using raw observation data. Compared with the traditional statistical models, the deep learning method have many advantages, the most prominent of which is that deep learning models can automatically learn the information contained in the data without manually setting parameters such as thresholds value [ 22 , 38 ]. The neural network model is established by setting the structural parameters.…”

“…In addition, the LSTM recursive neural network can use memory and gate units to truncate the gradient without damaging it and can bridge a large number of discrete-time steps to achieve the time series rule in a longer period of learning. Therefore, many different models have been developed by using LSTM, such as speech recognition model, forecasting model of air quality, forecasting models of infectious disease [ 21 , 22 , 38 – 40 ].…”

Enhancing fine-grained intra-urban dengue forecasting by integrating spatial interactions of human movements between urban regions

“…Consequently, an accurate early warning of dengue epidemic is important for timely and targeted vector control and prevention. To achieve this, various models have been proposed for dengue forecasting, including autoregressive models [7][8][9][10], generalized linear models [11][12][13], Poisson regression models [14][15][16], Bayesian hierarchical models [17,18], machine learning models such as artificial neural network (ANN) and support vector machine (SVM) [19][20], and deep learning models such as long short-term memory (LSTM) [21][22]. For instance, a time series Poisson multivariate regression model, that allows warning 16 weeks in advance of dengue epidemics, was developed in Singapore [16].…”

Untitled

“…"Deep Learning", a branch of artificial intelligence, allows autonomously learning how viruses spread using raw observation data. Compared with the traditional statistical models, the deep learning method have many advantages, the most prominent of which is that deep learning models can automatically learn the information contained in the data without manually setting parameters such as thresholds value [22,38]. The neural network model is established by setting the structural parameters.…”