Prediction of hand, foot, and mouth disease epidemics in Japan using a long short-term memory approach

Detection of enteroviruses related to hand foot and mouth disease in wastewater of Asian communities

Hand, foot, and mouth disease (HFMD) is contagious and predominantly affects children below the age of five. HFMD-associated serotypes of Enterovirus A (EVA) family include EVA71, Coxsackievirus A type 6 (CVA6), 10 (CVA10), and 16 (CVA16). Although prevalent in numerous Asian countries, studies on HFMD-causing agents in wastewater are scarce. This study aimed to conduct wastewater surveillance in various Asian communities to detect and quantify serotypes of EVA associated with HFMD. In total, 77 wastewater samples were collected from Indonesia, the Philippines, Thailand, and Vietnam from March 2022 to February 2023. The detection ratio for CVA6 RNA in samples from Vietnam was 40 % (8/20). The detection ratio for CVA6 and EVA71 RNA each was 25 % (5/20) for the Indonesian samples, indicating the need for clinical surveillance of CVA6, as clinical reports have been limited. For the Philippines, 12 % (2/17) of the samples were positive for CVA6 and EVA71 RNA each, with only one quantifiable sample each. Samples from Thailand had a lower detection ratio (1/20) for CVA6 RNA, and the concentration was unquantifiable. Conversely, CVA10 and CVA16 RNAs were not detected in any of the samples. The minimum and maximum concentrations of CVA6 RNA were 2.7 and 3.9 log10 copies/L and those for EVA71 RNA were 2.5 and 4.9 log10 copies/L, respectively. This study underscores the importance of wastewater surveillance in understanding the epidemiology of HFMD-associated EVA serotypes in Asian communities. Long-term wastewater surveillance is recommended to monitor changes in dominant serotypes, understand seasonality, and develop effective prevention and control strategies for HFMD.

Monitoring hand foot and mouth disease using long-term wastewater surveillance in Japan: Quantitative PCR assay development and application

Hand, foot, and mouth disease (HFMD) is a highly contagious disease that primarily affects children under five years of age. It is mainly caused by serotypes of Enterovirus A (EVA): EVA71, Coxsackievirus A types 6 (CVA6), 10 (CVA10), and 16 (CVA16). Despite being highly prevalent in Japan and other countries in the Asia-Pacific region, few studies have investigated HFMD pathogens in wastewater. The present study aimed to develop a highly sensitive and broadly reactive quantitative polymerase chain reaction (qPCR) assay of dominant serotype CVA6, to revise previously developed CVA6, CVA10, and CVA16 assays, and to test these assays in wastewater samples from Yamanashi Prefecture, Japan. The new-CVA6 qPCR assay was developed with maximal nucleotide percent identity among CVA6 isolates from Japan. The new-CVA6 and revised assays were highly sensitive and had the ability to quantify respective positive controls at levels as low as 1 copy/μL. Among the 53 grab influent samples collected between March 2022 and March 2023, EVA71, CVA10, and CVA16 RNA were not detected in any samples, whereas the new-CVA6 assay could detect CVA6 RNA in 38 % (20/53) of samples. CVA6 RNA was detected at a significantly higher concentration in the summer season (3.3 ± 0.8 log10 copies/L; 79 % (11/14)) than in autumn (2.7 ± 0.6 log10 copies/L; 69 % (9/13)). The seasonal trend of CVA6 RNA detection in wastewater aligned with the trend of HFMD case reports in the catchment of the wastewater treatment plant. This is the first study to report the detection and seasonal trends of the EVA serotypes associated with HFMD in wastewater samples in Japan. It provides evidence that wastewater-based epidemiology is applicable even for diseases that are prevalent only in specific population groups.

Evaluation of models for multi-step forecasting of hand, foot and mouth disease using multi-input multi-output: A case study of Chengdu, China

BACKGROUND

Hand, foot and mouth disease (HFMD) is a public health concern that threatens the health of children. Accurately forecasting of HFMD cases multiple days ahead and early detection of peaks in the number of cases followed by timely response are essential for HFMD prevention and control. However, many studies mainly predict future one-day incidence, which reduces the flexibility of prevention and control.

METHODS

We collected the daily number of HFMD cases among children aged 0-14 years in Chengdu from 2011 to 2017, as well as meteorological and air pollutant data for the same period. The LSTM, Seq2Seq, Seq2Seq-Luong and Seq2Seq-Shih models were used to perform multi-step prediction of HFMD through multi-input multi-output. We evaluated the models in terms of overall prediction performance, the time delay and intensity of detection peaks.

RESULTS

From 2011 to 2017, HFMD in Chengdu showed seasonal trends that were consistent with temperature, air pressure, rainfall, relative humidity, and PM10. The Seq2Seq-Shih model achieved the best performance, with RMSE, sMAPE and PCC values of 13.943~22.192, 17.880~27.937, and 0.887~0.705 for the 2-day to 15-day predictions, respectively. Meanwhile, the Seq2Seq-Shih model is able to detect peaks in the next 15 days with a smaller time delay.

CONCLUSIONS

The deep learning Seq2Seq-Shih model achieves the best performance in overall and peak prediction, and is applicable to HFMD multi-step prediction based on environmental factors.

Research on hand, foot and mouth disease incidence forecasting using hybrid model in mainland China

BACKGROUND

This study aimed to construct a more accurate model to forecast the incidence of hand, foot, and mouth disease (HFMD) in mainland China from January 2008 to December 2019 and to provide a reference for the surveillance and early warning of HFMD.

METHODS

We collected data on the incidence of HFMD in mainland China between January 2008 and December 2019. The SARIMA, SARIMA-BPNN, and SARIMA-PSO-BPNN hybrid models were used to predict the incidence of HFMD. The prediction performance was compared using the mean absolute error(MAE), mean squared error(MSE), root mean square error (RMSE), mean absolute percentage error (MAPE), and correlation analysis.

RESULTS

The incidence of HFMD in mainland China from January 2008 to December 2019 showed fluctuating downward trends with clear seasonality and periodicity. The optimal SARIMA model was SARIMA(1,0,1)(2,1,2)_[12], with Akaike information criterion (AIC) and Bayesian Schwarz information criterion (BIC) values of this model were 638.72, 661.02, respectively. The optimal SARIMA-BPNN hybrid model was a 3-layer BPNN neural network with nodes of 1, 10, and 1 in the input, hidden, and output layers, and the R-squared, MAE, and RMSE values were 0.78, 3.30, and 4.15, respectively. For the optimal SARIMA-PSO-BPNN hybrid model, the number of particles is 10, the acceleration coefficients c1 and c2 are both 1, the inertia weight is 1, the probability of change is 0.95, and the values of R-squared, MAE, and RMSE are 0.86, 2.89, and 3.57, respectively.

CONCLUSIONS

Compared with the SARIMA and SARIMA-BPNN hybrid models, the SARIMA-PSO-BPNN model can effectively forecast the change in observed HFMD incidence, which can serve as a reference for the prevention and control of HFMD.