Why the study?
Due to a lack of effective therapeutic drugs for HFMD, accurate prediction of the number of patients is important for disease prevention and control.
Does a Dilated Recurrent Neural Network (DRNN) model improve the prediction of the future number of HFMD patients compared to widely-used methods?
Does a Dilated Recurrent Neural Network (DRNN) model improve the prediction of the future number of HFMD patients compared to widely-used methods?
A Dilated Recurrent Neural Network model improves the prediction of hand, foot and mouth disease cases compared to traditional time series methods.
Hand, foot and mouth disease (HFMD) is an acute febrile and exudative infectious disease caused by enterovirus, which children are susceptible to. It spreads among children mainly through the digestive tract, respiratory tract and close contact, etc. Currently, since, lack of effective therapeutic drugs, symptomatic treatment is widely adopted. Therefore, accurate prediction of the number of HFMD patients is very important for the prevention and control of HFMD. In this paper, a predicting model, which is based on the Dilated Recurrent Neural Network (DRNN), is proposed to predict the future number of HFMD patients for different prediction horizons. Experimental results, based upon recorded time series data about the number of hand, foot and mouth disease cases in Xiamen, demonstrate that our model improves the forecast well compared to a set of widely-used methods for time series prediction.
No takes yet. Share an insight, caveat, or question.
Luo et al. (2019) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: