Abstract
Hand-foot-mouth disease (HFMD) is a common infectious disease in children and is particularly severe in Guangxi, China. Meteorological conditions are known to play a pivotal role in the HFMD. Previous studies have reported numerous models to predict the incidence of HFMD. In this study, we proposed a new method for the HFMD prediction using GeoDetector and a Long Short-Term Memory neural network (LSTM). The daily meteorological factors and HFMD records in Guangxi during 2014–2015 were adopted. First, potential risk factors for the occurrence of HFMD were identified based on the GeoDetector. Then, region-specific prediction models were developed in 14 administrative regions of Guangxi, China using an optimized three-layer LSTM model. Prediction results (the R-square ranges from 0.39 to 0.71) showed that the model proposed in this study had a good performance in HFMD predictions. This model could provide support for the prevention and control of HFMD. Moreover, this model could also be extended to the time series prediction of other infectious diseases.
Highlights
Hand-foot-mouth disease (HFMD) is a common viral infectious disease in children under 5 years old, which is commonly caused by the enteric pathogen coxsackievirus A16 (CoxA16) and enterovirus 71 (EV 71)[1,2]
The 14 meteorological factors were divided into four categories, including (1) Humidity: minimum relative humidity (MIH), mean relative humidity (MEH), and precipitation (PR); (2) temperature: mean temperature (MET), maximum temperature (MAT), and minimum temperature (MIT); (3) pressure: mean pressure (MEP), maximum pressure (MAP), and minimum pressure (MIP); (4) wind speed: mean wind speed (MEW), maximum wind speed(MW), the direction of maximum wind speed (DMW), extreme wind speed (EW), and the direction of extreme wind speed (DEW)
It can be seen that the primary impacting factor is the temperature of MIT (q = 0.23) and MET (q = 0.20), followed by PR (q = 0.10) and wind speed (DEW, q = 0.04; MW, q = 0.02; EW, q = 0.01; MEW, q = 0.01)
Summary
Hand-foot-mouth disease (HFMD) is a common viral infectious disease in children under 5 years old, which is commonly caused by the enteric pathogen coxsackievirus A16 (CoxA16) and enterovirus 71 (EV 71)[1,2]. The linear regression model was established by analyzing the correlations between the incidence of HFMD and the influential factors[17]. The time series model uses the relationship in the sequential lag time series to predict the incidence of HFMD, such as the seasonal auto-regressive integrated moving average model (ARIMA)[19,20] These models did not consider the relationship between HFMD and potential impacting factors. Gradient boosting tree (GBT) and random forest (RF) were found to be capable of identifying both mild and severe HFMD, which is helpful for early surveillance and control in HFMD24,25 Deep learning methods such as Back Propagation Neural Networks (BPNN) were adopted to predict the incidence of HFMD26. The dominant impacting factors were input into LSTM model to predict the weekly cases of HFMD in 14 subregions of Guangxi, China
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
