Search

Background: Infectious diseases are a major threat to public health, causing serious medical consumption and casualties. Accurate prediction of infectious diseases incidence is of great significance for public health organizations to prevent the spread of diseases. However, only using historical incidence data for prediction can not get good results. This study analyzes the influence of meteorological factors on the incidence of hepatitis E, which are used to improve the accuracy of incidence prediction. Methods: We extracted the monthly meteorological data, incidence and cases number of hepatitis E from January 2005 to December 2017 in Shandong province, China. We employ GRA method to analyze the correlation between the incidence and meteorological factors. With these meteorological factors, we achieve a variety of methods for incidence of hepatitis E by LSTM and attention-based LSTM. We selected data from July 2015 to December 2017 to validate the models, and the rest was taken as training set. Three metrics were applied to compare the performance of models, including root mean square error(RMSE), mean absolute percentage error(MAPE) and mean absolute error(MAE). Results: Duration of sunshine and rainfall-related factors(total rainfall, maximum daily rainfall) are more relevant to the incidence of hepatitis E than other factors. Without meteorological factors, we obtained 20.74%, 19.50% for incidence in term of MAPE, by LSTM and A-LSTM, respectively. With meteorological factors, we obtained 14.74%, 12.91%, 13.21%, 16.83% for incidence, in term of MAPE, by LSTM-All, MA-LSTM-All, TA-LSTM-All, BiA-LSTM-All, respectively. The prediction accuracy increased by 7.83%. Without meteorological factors, we achieved 20.41%, 19.39% for cases in term of MAPE, by LSTM and A-LSTM, respectively. With meteorological factors, we achieved 14.20%, 12.49%, 12.72%, 15.73% for cases, in term of MAPE, by LSTM-All, MA-LSTM-All, TA-LSTM-All, BiA-LSTM-All, respectively. The prediction accuracy increased by 7.92%. More detailed results are shown in results section of this paper. Conclusions: The experiments show that attention-based LSTM is superior to other comparative models. Multivariate attention and temporal attention can greatly improve the prediction performance of the models. Among them, when all meteorological factors are used, multivariate attention performance is better. This study can provide reference for the prediction of other infectious diseases. [ABSTRACT FROM AUTHOR]

Background: Accurate and reliable predictions of infectious disease can be valuable to public health organizations that plan interventions to decrease or prevent disease transmission. A great variety of models have been developed for this task. However, for different data series, the performance of these models varies. Hepatitis E, as an acute liver disease, has been a major public health problem. Which model is more appropriate for predicting the incidence of hepatitis E? In this paper, three different methods are used and the performance of the three methods is compared. Methods: Autoregressive integrated moving average(ARIMA), support vector machine(SVM) and long short-term memory(LSTM) recurrent neural network were adopted and compared. ARIMA was implemented by python with the help of statsmodels. SVM was accomplished by matlab with libSVM library. LSTM was designed by ourselves with Keras, a deep learning library. To tackle the problem of overfitting caused by limited training samples, we adopted dropout and regularization strategies in our LSTM model. Experimental data were obtained from the monthly incidence and cases number of hepatitis E from January 2005 to December 2017 in Shandong province, China. We selected data from July 2015 to December 2017 to validate the models, and the rest was taken as training set. Three metrics were applied to compare the performance of models, including root mean square error(RMSE), mean absolute percentage error(MAPE) and mean absolute error(MAE). Results: By analyzing data, we took ARIMA(1, 1, 1), ARIMA(3, 1, 2) as monthly incidence prediction model and cases number prediction model, respectively. Cross-validation and grid search were used to optimize parameters of SVM. Penalty coefficient C and kernel function parameter g were set 8, 0.125 for incidence prediction, and 22, 0.01 for cases number prediction. LSTM has 4 nodes. Dropout and L2 regularization parameters were set 0.15, 0.001, respectively. By the metrics of RMSE, we obtained 0.022, 0.0204, 0.01 for incidence prediction, using ARIMA, SVM and LSTM. And we obtained 22.25, 20.0368, 11.75 for cases number prediction, using three models. For MAPE metrics, the results were 23.5%, 21.7%, 15.08%, and 23.6%, 21.44%, 13.6%, for incidence prediction and cases number prediction, respectively. For MAE metrics, the results were 0.018, 0.0167, 0.011 and 18.003, 16.5815, 9.984, for incidence prediction and cases number prediction, respectively. Conclusions: Comparing ARIMA, SVM and LSTM, we found that nonlinear models(SVM, LSTM) outperform linear models(ARIMA). LSTM obtained the best performance in all three metrics of RSME, MAPE, MAE. Hence, LSTM is the most suitable for predicting hepatitis E monthly incidence and cases number. [ABSTRACT FROM AUTHOR]