Dataset Information

Comparison of Two Hybrid Models for Forecasting the Incidence of Hemorrhagic Fever with Renal Syndrome in Jiangsu Province, China.

ABSTRACT:

Background

Cases of hemorrhagic fever with renal syndrome (HFRS) are widely distributed in eastern Asia, especially in China, Russia, and Korea. It is proved to be a difficult task to eliminate HFRS completely because of the diverse animal reservoirs and effects of global warming. Reliable forecasting is useful for the prevention and control of HFRS.

Methods

Two hybrid models, one composed of nonlinear autoregressive neural network (NARNN) and autoregressive integrated moving average (ARIMA) the other composed of generalized regression neural network (GRNN) and ARIMA were constructed to predict the incidence of HFRS in the future one year. Performances of the two hybrid models were compared with ARIMA model.

Results

The ARIMA, ARIMA-NARNN ARIMA-GRNN model fitted and predicted the seasonal fluctuation well. Among the three models, the mean square error (MSE), mean absolute error (MAE) and mean absolute percentage error (MAPE) of ARIMA-NARNN hybrid model was the lowest both in modeling stage and forecasting stage. As for the ARIMA-GRNN hybrid model, the MSE, MAE and MAPE of modeling performance and the MSE and MAE of forecasting performance were less than the ARIMA model, but the MAPE of forecasting performance did not improve.

Conclusion

Developing and applying the ARIMA-NARNN hybrid model is an effective method to make us better understand the epidemic characteristics of HFRS and could be helpful to the prevention and control of HFRS.

SUBMITTER: Wu W

PROVIDER: S-EPMC4536138 | biostudies-literature | 2015

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Comparison of Two Hybrid Models for Forecasting the Incidence of Hemorrhagic Fever with Renal Syndrome in Jiangsu Province, China.

Wu Wei W Guo Junqiao J An Shuyi S Guan Peng P Ren Yangwu Y Xia Linzi L Zhou Baosen B

PloS one 20150813 8

<h4>Background</h4>Cases of hemorrhagic fever with renal syndrome (HFRS) are widely distributed in eastern Asia, especially in China, Russia, and Korea. It is proved to be a difficult task to eliminate HFRS completely because of the diverse animal reservoirs and effects of global warming. Reliable forecasting is useful for the prevention and control of HFRS.<h4>Methods</h4>Two hybrid models, one composed of nonlinear autoregressive neural network (NARNN) and autoregressive integrated moving aver ...[more]

PMID: 26270814

Similar Datasets

Project description:BackgroundHemorrhagic fever with renal syndrome (HFRS) is a rodent-borne disease caused by Hantaviruses. It is endemic in all 31 provinces, autonomous regions, and metropolitan areas in mainland China where human cases account for 90% of the total global cases. Shandong Province is among the most serious endemic areas. HFRS cases in Shandong Province were first reported in Yutai County in 1968. Since then, the disease has spread across the province, and as of 2005, all 111 counties were reported to have local human infections. However, causes underlying such rapid spread and wide distribution remain less well understood.Methods and findingsHere we report a spatiotemporal analysis of human HFRS cases in Shandong using data spanning 1973 to 2005. Seasonal incidence maps and velocity vector maps were produced to analyze the spread of HFRS over time in Shandong Province, and a panel data analysis was conducted to explore the association between HFRS incidence and climatic factors. Results show a rapid spread of HFRS from its epicenter in Rizhao, Linyi, Weifang Regions in southern Shandong to north, east, and west parts of the province. Based on seasonal shifts of epidemics, three epidemic phases were identified over the 33-year period. The first phase occurred between 1973 and 1982 during which the foci of HFRS was located in the south Shandong and the epidemic peak occurred in the fall and winter, presenting a seasonal characteristic of Hantaan virus (HTNV) transmission. The second phase between 1983 and 1985 was characterized by northward and westward spread of HFRS foci, and increases in incidence of HFRS in both fall-winter and spring seasons. The human infections in the spring reflected a characteristic pattern of Seoul virus (SEOV) transmission. The third phase between 1986 and 2005 was characterized by the northeast spread of the HFRS foci until it covered all counties, and the HFRS incidence in the fall-winter season decreased while it remained high in the spring. In addition, our findings suggest that precipitation, humidity, and temperature are major environmental variables that are associated with the seasonal variation of HFRS incidence in Shandong Province.ConclusionsThe spread of HFRS in Shandong Province may have been accompanied by seasonal shifts of HTNV-dominated transmission to SEOV-dominated transmission over the past three decades. The variations in HFRS incidence were significantly associated with local precipitation, humidity, and temperature.

Project description:BackgroundHemorrhagic fever with renal syndrome (HFRS) is still attracting public attention because of its outbreak in various cities in China. Predicting future outbreaks or epidemics disease based on past incidence data can help health departments take targeted measures to prevent diseases in advance. In this study, we propose a multistep prediction strategy based on extreme gradient boosting (XGBoost) for HFRS as an extension of the one-step prediction model. Moreover, the fitting and prediction accuracy of the XGBoost model will be compared with the autoregressive integrated moving average (ARIMA) model by different evaluation indicators.MethodsWe collected HFRS incidence data from 2004 to 2018 of mainland China. The data from 2004 to 2017 were divided into training sets to establish the seasonal ARIMA model and XGBoost model, while the 2018 data were used to test the prediction performance. In the multistep XGBoost forecasting model, one-hot encoding was used to handle seasonal features. Furthermore, a series of evaluation indices were performed to evaluate the accuracy of the multistep forecast XGBoost model.ResultsThere were 200,237 HFRS cases in China from 2004 to 2018. A long-term downward trend and bimodal seasonality were identified in the original time series. According to the minimum corrected akaike information criterion (CAIC) value, the optimal ARIMA (3, 1, 0) × (1, 1, 0)12 model is selected. The index ME, RMSE, MAE, MPE, MAPE, and MASE indices of the XGBoost model were higher than those of the ARIMA model in the fitting part, whereas the RMSE of the XGBoost model was lower. The prediction performance evaluation indicators (MAE, MPE, MAPE, RMSE and MASE) of the one-step prediction and multistep prediction XGBoost model were all notably lower than those of the ARIMA model.ConclusionsThe multistep XGBoost prediction model showed a much better prediction accuracy and model stability than the multistep ARIMA prediction model. The XGBoost model performed better in predicting complicated and nonlinear data like HFRS. Additionally, Multistep prediction models are more practical than one-step prediction models in forecasting infectious diseases.

Project description:BACKGROUND: Since the end of the 1990s, the incidence of hemorrhagic fever with renal syndrome (HFRS) has been increasing dramatically in Changchun, northeastern China. However, it is unknown which, and how, underlying risk factors have been involved in the reemergence of the disease. METHODS: Data on HFRS cases at the county scale were collected from 1998 to 2012. Data on livestock husbandry including the numbers of large animals (cattle, horses, donkeys and mules), sheep, and deer, and on climatic and land cover variables were also collected. Epidemiological features, including the spatial, temporal and human patterns of disease were characterized. The potential factors related to spatial heterogeneity and temporal trends were analyzed using standard and time-series Poisson regression analysis, respectively. RESULTS: Annual incidence varied among the 10 counties. Shuangyang County in southeastern Changchun had the highest number of cases (1,525 cases; 35.9% of all cases), but its population only accounted for 5.6% of the total population. Based on seasonal pattern in HFRS incidence, two epidemic phases were identified. One was a single epidemic peak at the end of each year from 1988 to 1997 and the other consisted of dual epidemic peaks at both the end and the beginning of each year from 1998 to the end of the study period. HFRS incidence was higher in males compared to females, and most of the HFRS cases occurred in peasant populations. The results of the Poisson regression analysis indicated that the spatial distribution and the increasing incidence of HFRS were significantly associated with livestock husbandry and climate factors, particularly with deer cultivation. CONCLUSIONS: Our results indicate that the re-emergence of HFRS in Changchun has been accompanied by changing seasonal patterns over the past 25 years. Integrated measures focusing on areas related to local livestock husbandry could be helpful for the prevention and control of HFRS.

Dataset Information

Comparison of Two Hybrid Models for Forecasting the Incidence of Hemorrhagic Fever with Renal Syndrome in Jiangsu Province, China.

Background

Methods

Results

Conclusion

Publications

Comparison of Two Hybrid Models for Forecasting the Incidence of Hemorrhagic Fever with Renal Syndrome in Jiangsu Province, China.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets