Spatiotemporal analysis and forecasting model of hemorrhagic fever with renal syndrome in mainland China

Spatiotemporal risk of human brucellosis under intensification of livestock keeping based on machine learning techniques in Shaanxi, China

As one of the most neglected zoonotic diseases, brucellosis has posed a serious threat to public health worldwide. This study is purposed to apply different machine learning models to improve the prediction accuracy of human brucellosis (HB) in Shaanxi, China from 2008 to 2020, under livestock husbandry intensification from a spatiotemporal perspective. We quantitatively evaluated the performance and suitability of ConvLSTM, RF, and LSTM models in epidemic forecasting, and investigated the spatial heterogeneity of how different factors drive the occurrence and transmission of HB in distinct sub-regions by using Kernel Density Analysis and Shapley Additional Explanations. Our findings demonstrated that ConvLSTM network yielded the best predictive performance with the lowest average RMSE of 13.875 and MAE values of 18.393. RF model generated an underestimated outcome while LSTM model had an overestimated one. In addition, climatic conditions, intensification of livestock keeping and socioeconomic status were identified as the dominant factors that drive the occurrence of HB in Shaanbei Plateau, Guanzhong Plain, and Shaannan Region, respectively. This work provided a comprehensive understanding of the potential risk of HB epidemics in Northwest China driven by both anthropogenic activities and natural environment, which can support further practice in disease control and prevention.

Spatial-temporal patterns and influencing factors for hemorrhagic fever with renal syndrome: A 16-year national surveillance analysis in China

Background

China is confronted with the significant menace posed by hemorrhagic fever with renal syndrome (HFRS). Nevertheless, the long-term spatial-temporal variations, regional prevalence patterns, and fundamental determinants' mechanisms for HFRS remain inadequately elucidated.

Methods

Newly diagnosed cases of HFRS from January 2004 to December 2019 were acquired from the China Public Health Science Data repository. We used Age-period-cohort and Bayesian Spacetime Hierarchy models to identify high-risk populations and regions in mainland China. Additionally, the Geographical Detector model was employed to quantify the determinant powers of significant driver factors to the disease.

Results

A total of 199,799 cases of HFRS were reported in mainland China during 2004-2019. The incidence of HFRS declined from 1.93 per 100,000 in 2004 to 0.69 per 100,000 in 2019. The incidence demonstrated an inverted U-shaped trend with advancing age, peaking in the 50-54 age group, with higher incidences observed among individuals aged 20-74 years. Hyperendemic areas were mainly concentrated in the northeastern regions of China, while some western provinces exhibited a potential upward trend. Geographical detector model identified that the spatial variations of HFRS were significantly associated with the relative humidity (Q = 0.36), forest cover (Q = 0.26), rainfall (Q = 0.18), temperature (Q = 0.16), and the surface water resources (Q = 0.14).

Conclusions

This study offered comprehensive examinations of epidemic patterns, identified high-risk areas quantitatively, and analyzed factors influencing HFRS transmission in China. The findings may contribute to the necessary implementations for the effective prevention and control of HFRS.

Using empirical dynamic modeling to identify the impact of meteorological factors on hemorrhagic fever with renal syndrome in Weifang, Northeastern China, from 2011 to 2020

BACKGROUND

Hemorrhagic Fever with Renal Syndrome (HFRS) continues to pose a significant public health threat to the well-being of the population. Given that the spread of HFRS is susceptible to meteorological factors, we aim to probe into the meteorological drivers of HFRS. Thus, novel techniques that can discern time-delayed non-linear relationships from nonlinear dynamical systems are compulsory.

METHODS

We analyze the epidemiological features of HFRS in Weifang City, 2011-2020, via the employment of the Empirical Dynamic Modeling (EDM) method. Our analysis delves into the intricate web of time-delayed non-linear associations between meteorological factors and HFRS. Additionally, we investigate the repercussions of minor perturbations in meteorological variables on future HFRS incidence.

RESULTS

A total of 2515 HFRS cases were reported in Weifang from 2011 to 2020. The number of cases per week was 4.81, and the average weekly incidence was 0.52 per 1,000,000. The propagation of HFRS is significantly impacted by the mean weekly temperature, relative humidity, cumulative rainfall, and wind speed, and the ρCCM converges to 0.55,0.48,0.38 and 0.39, respectively. The graphical representation of the relationship between temperature (lagged by 2 weeks) and the incidence of HFRS exhibits an inverted U-shaped curve, whereby the incidence of HFRS culminates as the temperature reaches 10 °C. Moreover, temperature, relative humidity, cumulative rainfall, and wind speed exhibit a positive correlation with HFRS incidence, with a time lag of 4-6 months.

CONCLUSIONS

Our discoveries suggest that meteorological factors can drive the transmission of HFRS both at a macroscopic and microscopic scale. Prospective alterations in meteorological conditions, for instance, elevations in temperature, relative humidity, and precipitation will instigate an upsurge in the incidence of HFRS after 4-6 months, and thus, timely public health measures should be taken to mitigate these changes.

Spatiotemporal trends of hemorrhagic fever with renal syndrome (HFRS) in China under climate variation

Hemorrhagic fever with renal syndrome (HFRS) is a zoonotic disease caused by the rodent-transmitted orthohantaviruses (HVs), with China possessing the most cases globally. The virus hosts in China are Apodemus agrarius and Rattus norvegicus, and the disease spread is strongly influenced by global climate dynamics. To assess and predict the spatiotemporal trends of HFRS from 2005 to 2098, we collected historical HFRS data in mainland China (2005-2020), historical and projected climate and population data (2005-2098), and spatial variables including biotic, environmental, topographical, and socioeconomic. Spatiotemporal predictions and mapping were conducted under 27 scenarios incorporating multiple integrated representative concentration pathway models and population scenarios. We identify the type of magistral HVs host species as the best spatial division, including four region categories. Seven extreme climate indices associated with temperature and precipitation have been pinpointed as key factors affecting the trends of HFRS. Our predictions indicate that annual HFRS cases will increase significantly in 62 of 356 cities in mainland China. Rattus regions are predicted to be the most active, surpassing Apodemus and Mixed regions. Eighty cities are identified as at severe risk level for HFRS, each with over 50 reported cases annually, including 22 new cities primarily located in East China and Rattus regions after 2020, while 6 others develop new risk. Our results suggest that the risk of HFRS will remain high through the end of this century, with Rattus norvegicus being the most active host, and that extreme climate indices are significant risk factors. Our findings can inform evidence-based policymaking regarding future risk of HFRS.

Epidemiology of Hemorrhagic Fever with Renal Syndrome and Host Surveillance in Zhejiang Province, China, 1990-2021

Hemorrhagic fever with renal syndrome (HFRS) is caused by hantaviruses (HVs) and is endemic in Zhejiang Province, China. In this study, we aimed to explore the changing epidemiology of HFRS cases and the dynamics of hantavirus hosts in Zhejiang Province. Joinpoint regression was used to analyze long-term trends in the incidence of HFRS. The comparison of animal density at different stages was conducted using the Mann-Whitney Test. A comparison of HV carriage rates between stages and species was performed using the chi-square test. The incidence of HFRS shows a continuous downward trend. Cases are widely distributed in all counties of Zhejiang Province except Shengsi County. There was a high incidence belt from west to east, with low incidence in the south and north. The HFRS epidemic showed two seasonal peaks in Zhejiang Province, which were winter and summer. It showed a marked increase in the age of the incidence population. A total of 23,073 minibeasts from 21 species were captured. Positive results were detected in the lung tissues of 14 rodent species and 1 shrew species. A total of 80% of the positive results were from striped field mice and brown rats. No difference in HV carriage rates between striped field mice and brown rats was observed (χ2 = 0.258, p = 0.611).

Epidemiological characteristics and prediction model construction of hemorrhagic fever with renal syndrome in Quzhou City, China, 2005-2022

Background

Hemorrhagic fever with renal syndrome (HFRS) is one of the 10 major infectious diseases that jeopardize human health and is distributed in more than 30 countries around the world. China is the country with the highest number of reported HFRS cases worldwide, accounting for 90% of global cases. The incidence level of HFRS in Quzhou is at the forefront of Zhejiang Province, and there is no specific treatment for it yet. Therefore, it is crucial to grasp the epidemiological characteristics of HFRS in Quzhou and establish a prediction model for HFRS to lay the foundation for early warning of HFRS.

Methods

Descriptive epidemiological methods were used to analyze the epidemic characteristics of HFRS, the incidence map was drawn by ArcGIS software, the Seasonal AutoRegressive Integrated Moving Average (SARIMA) and Prophet model were established by R software. Then, root mean square error (RMSE) and mean absolute error (MAE) were used to evaluate the fitting and prediction performances of the model.

Results

A total of 843 HFRS cases were reported in Quzhou City from 2005 to 2022, with the highest annual incidence rate in 2007 (3.93/100,000) and the lowest in 2022 (1.05/100,000) (P trend<0.001). The incidence is distributed in a seasonal double-peak distribution, with the first peak from October to January and the second peak from May to July. The incidence rate in males (2.87/100,000) was significantly higher than in females (1.32/100,000). Farmers had the highest number of cases, accounting for 79.95% of the total number of cases. The incidence is high in the northwest of Quzhou City, with cases concentrated on cultivated land and artificial land. The RMSE and MAE values of the Prophet model are smaller than those of the SARIMA (1,0,1) (2,1,0)12 model.

Conclusion

From 2005 to 2022, the incidence of HFRS in Quzhou City showed an overall downward trend, but the epidemic in high-incidence areas was still serious. In the future, the dynamics of HFRS outbreaks and host animal surveillance should be continuously strengthened in combination with the Prophet model. During the peak season, HFRS vaccination and health education are promoted with farmers as the key groups.

Case Report: Hemorrhagic Fever with Renal Syndrome Complicated by Bilateral Subdural Hematoma

Hemorrhagic fever with renal syndrome (HFRS) is an acute, natural focal disease worldwide. Bilateral subdural hematoma (BSH) is a rare occurrence in patients with HFRS. A 51-year-old man was admitted with fever, headache, lower back pain, and reduced urine volume. The patient was diagnosed with HFRS accompanied by BSH, as evidenced by IgM and IgG antibodies for hantavirus that were positive, and abnormal blood test results and computed tomographic head scan. He recovered and was discharged after symptomatic treatment. Hemorrhagic fever with renal syndrome might present rare clinical manifestations with BSH. The early identification of this condition is crucial to an improved prognosis.

Time series analyses based on the joint lagged effect analysis of pollution and meteorological factors of hemorrhagic fever with renal syndrome and the construction of prediction model

BACKGROUND

Hemorrhagic fever with renal syndrome (HFRS) is a rodent-related zoonotic disease induced by hantavirus. Previous studies have identified the influence of meteorological factors on the onset of HFRS, but few studies have focused on the stratified analysis of the lagged effects and interactions of pollution and meteorological factors on HFRS.

METHODS

We collected meteorological, contaminant and epidemiological data on cases of HFRS in Shenyang from 2005-2019. A seasonal autoregressive integrated moving average (SARIMA) model was used to predict the incidence of HFRS and compared with Holt-Winters three-parameter exponential smoothing model. A distributed lag nonlinear model (DLNM) with a maximum lag period of 16 weeks was applied to assess the lag, stratification and extreme effects of pollution and meteorological factors on HFRS cases, followed by a generalized additive model (GAM) to explore the interaction of SO2 and two other meteorological factors on HFRS cases.

RESULTS

The SARIMA monthly model has better fit and forecasting power than its own quarterly model and the Holt-Winters model, with an optimal model of (1,1,0) (2,1,0)12. Overall, environmental factors including humidity, wind speed and SO2 were correlated with the onset of HFRS and there was a non-linear exposure-lag-response association. Extremely high SO2 increased the risk of HFRS incidence, with the maximum RR values: 2.583 (95%CI:1.145,5.827). Extremely low windy and low SO2 played a significant protective role on HFRS infection, with the minimum RR values: 0.487 (95%CI:0.260,0.912) and 0.577 (95%CI:0.370,0.898), respectively. Interaction indicated that the risk of HFRS infection reached its highest when increasing daily SO2 and decreasing humidity.

CONCLUSIONS

The SARIMA model may help to enhance the forecast of monthly HFRS incidence based on a long-range dataset. Our study had shown that environmental factors such as humidity and SO2 have a delayed effect on the occurrence of HFRS and that the effect of humidity can be influenced by SO2 and wind speed. Public health professionals should take greater care in controlling HFRS in low humidity, low windy conditions and 2-3 days after SO2 levels above 200 μg/m3.

The Spatiotemporal Pattern and Its Determinants of Hemorrhagic Fever With Renal Syndrome in Northeastern China: Spatiotemporal Analysis

BACKGROUND

Hemorrhagic fever with renal syndrome (HFRS) is a significant zoonotic disease mainly transmitted by rodents. However, the determinants of its spatiotemporal patterns in Northeast China remain unclear.

OBJECTIVE

This study aimed to investigate the spatiotemporal dynamics and epidemiological characteristics of HFRS and detect the meteorological effect of the HFRS epidemic in Northeastern China.

METHODS

The HFRS cases of Northeastern China were collected from the Chinese Center for Disease Control and Prevention, and meteorological data were collected from the National Basic Geographic Information Center. Times series analyses, wavelet analysis, Geodetector model, and SARIMA model were performed to identify the epidemiological characteristics, periodical fluctuation, and meteorological effect of HFRS in Northeastern China.

RESULTS

A total of 52,655 HFRS cases were reported in Northeastern China from 2006 to 2020, and most patients with HFRS (n=36,558, 69.43%) were aged between 30-59 years. HFRS occurred most frequently in June and November and had a significant 4- to 6-month periodicity. The explanatory power of the meteorological factors to HFRS varies from 0.15 ≤ q ≤ 0.01. In Heilongjiang province, mean temperature with a 4-month lag, mean ground temperature with a 4-month lag, and mean pressure with a 5-month lag had the most explanatory power on HFRS. In Liaoning province, mean temperature with a 1-month lag, mean ground temperature with a 1-month lag, and mean wind speed with a 4-month lag were found to have an effect on HFRS, but in Jilin province, the most important meteorological factors for HFRS were precipitation with a 6-month lag and maximum evaporation with a 5-month lag. The interaction analysis of meteorological factors mostly showed nonlinear enhancement. The SARIMA model predicted that 8,343 cases of HFRS are expected to occur in Northeastern China.

CONCLUSIONS

HFRS showed significant inequality in epidemic and meteorological effects in Northeastern China, and eastern prefecture-level cities presented a high risk of epidemic. This study quantifies the hysteresis effects of different meteorological factors and prompts us to focus on the influence of ground temperature and precipitation on HFRS transmission in future studies, which could assist local health authorities in developing HFRS-climate surveillance, prevention, and control strategies targeting high-risk populations in China.

Spatio-temporal distribution and influencing factors of norovirus outbreaks in Beijing, China from 2016 to 2020

BACKGROUND

Noroviruses are a leading cause of acute gastroenteritis (AGE) worldwide. The geographical characteristics of norovirus outbreaks in Beijing and their influencing factors remain unknown. This study aimed to explore the spatial distributions, geographical characteristics, and influencing factors of norovirus outbreaks in Beijing, China.

METHODS

Epidemiological data and specimens were collected through the AGE outbreak surveillance system in all 16 districts of Beijing. Data on spatial distribution, geographical characteristics, and influencing factors of norovirus outbreaks were analyzed using descriptive statistics methods. We measured spatial, geographical clustering of high- or low-value deviance from random distribution using Z-scores and P-values as statistical significance measures with Global Moran's I statistics and Getis-Ord Gi in ArcGIS. Linear regression and correlation methods were used to explore influencing factors.

RESULTS

Between September 2016 and August 2020, 1,193 norovirus outbreaks were laboratory-confirmed. The number of outbreaks varied seasonally, typically peaking in spring (March to May) or winter (October to December). Outbreaks primarily occurred around central districts at the town level, and spatial autocorrelation was evident in both the entire study period and in individual years. Hotspots of norovirus outbreaks in Beijing were primarily found in contiguous areas between three central districts (Chaoyang, Haidian, Fengtai) and four suburban districts (Changping, Daxing, Fangshan, Tongzhou). The average population numbers, mean number of all schools, and mean number of kindergartens and primary schools for towns in central districts and hotspot areas were higher than those in suburban districts and non-hotspot areas respectively. Additionally, population numbers and densities of kindergartens and primary schools were influencing factors at the town level.

CONCLUSIONS

Hotspots of norovirus outbreaks in Beijing were in contiguous areas between central and suburban districts with high populations, and high kindergarten and primary school densities were the likely driving forces. Outbreak surveillance needs to focus on contiguous areas between central and suburban districts with increased monitoring, medical resources, and health education.

Construction of a Hantaan Virus Phage Antibody Library and Screening for Potential Neutralizing Activity

China is one of the main epidemic areas for hemorrhagic fever with renal syndrome (HFRS). Currently, there is no human antibody specific to Hantaan virus (HTNV) for the emergency prevention and treatment of HFRS. To prepare human antibodies with neutralizing activity, we established an anti-HTNV phage antibody library using phage display technology by transforming peripheral blood mononuclear cells (PBMCs) of patients with HFRS into B lymphoblastoid cell lines (BLCLs) and extracting cDNA from BLCLs that secreted neutralizing antibodies. Based on the phage antibody library, we screened HTNV-specific Fab antibodies with neutralizing activities. Our study provides a potential way forward for the emergency prevention of HTNV and specific treatment of HFRS.

Dual seasonal pattern for hemorrhagic fever with renal syndrome and its potential determinants in China

Hemorrhagic fever with renal syndrome (HFRS) continued to affect human health across Eurasia, which complicated by climate change has posed a challenge for the disease prevention measures. Nation-wide surveillance data of HFRS cases were collected during 2008-2020.The seasonality and epidemiological features were presented by combining the HFRS incidence and the endemic types data. Factors potentially involved in affecting incidence and shaping disease seasonality were investigated by generalized additive mixed model, distributed lag nonlinear model and multivariate meta-analysis. A total of 76 cities that reported totally 111,054 cases were analyzed. Three endemic types were determined, among them the Type I cities (Hantaan virus-dominant) were related to higher incidence level, showing one spike every year in Autumn-Winter season; Type II (Seoul virus-dominant) cities were related to lower incidence, showing one spike in Spring, while Type III (Hantaan/Seoul-mixed type) showed dual peaks with incidence lying between. Persistently heavy rainfall had significantly negative influence on HFRS incidence in Hantaan virus-dominant endemic area, while a significantly opposite effect was identified when continuously heavy rainfall induced floods, where temperature and relative humidity affected HFRS incidence via an approximately parabolic or linear manner, however few or no such effects was shown in Seoul virus-dominant endemic areas, which was more vulnerable to temperature variation. Dual seasonal pattern of HFRS was depended on the dominant genotypes of hantavirus, and impact of climate on HFRS was greater in Hantaan virus-dominant endemic areas, than in Seoul virus-dominant areas.

Spatial-temporal dynamics and time series prediction of HFRS in mainland China: A long-term retrospective study

Hemorrhagic fever with renal syndrome (HFRS) is highly endemic in mainland China. The current study aims to characterize the spatial-temporal dynamics of HFRS in mainland China during a long-term period (1950-2018). A total of 1 665 431 cases of HFRS were reported with an average annual incidence of 54.22 cases/100 000 individuals during 1950-2018. The joint regression model was used to define the global trend of the HFRS cases with an increasing-decreasing-slightly increasing-decreasing-slightly increasing trend during the 68 years. Then spatial correlation analysis and wavelet cluster analysis were used to identify four types of clusters of HFRS cases located in central and northeastern China. Lastly, the prophet model outperforms auto-regressive integrated moving average model in the HFRS modeling. Our findings will help reduce the knowledge gap on the transmission dynamics and distribution patterns of the HFRS in mainland China and facilitate to take effective preventive and control measures for the high-risk epidemic area.

Expert Consensus on the Prevention and Treatment of Hemorrhagic Fever with Renal Syndrome

Abstract

Hemorrhagic fever with renal syndrome (HFRS) is an acute zoonosis with a global distribution. China is one of the countries with a high incidence of HFRS, which has long endangered the lives and health of the Chinese people. The Infectious Disease Branch of the Chinese Preventive Medicine Association and the Infectious Diseases Branch of the Chinese Medical Association organized national multidisciplinary experts, based on domestic and international research results combined with experts’ practical experiences, to reach this consensus after thorough discussion. This consensus contains 17 recommendations aimed at prevention and identification of important clinical issues to further standardize the prevention, diagnosis, and treatment of HFRS.

Adenosine Deaminase is a Potential Molecular Marker for Diagnosis and Prognosis of Haemorrhagic Fever with Renal Syndrome

Objective

Haemorrhagic fever with renal syndrome (HFRS) is a serious zoonotic disease which seriously endangers physical health and mainly occurs in China. To date, there is still a lack of early and novel biomarkers to detect the severity of disease and prognosis of HFRS. This study was aimed to examine the value of the serum Adenosine deaminase (ADA) concentrations in the patients with HFRS.

Methods

The clinical and laboratory data of 124 adult patients with HFRS and 131 patients with similar clinical symptoms to HFRS were analyzed. A receiver operating characteristic (ROC) curve was used to analyze the diagnostic value of ADA in HFRS.

Results

The ADA levels in the serum of HFRS patients were significantly higher than those in control patients (P < 0.001), and ADA has a strong positive correlation with HFRS (r = 0.785, P < 0.001). The optimal cut-off value of ADA for diagnosis of HFRS was 18 U/L and the area under the curve (AUC) was 0.953 (95% CI: 0.925, 0.981). The sensitivity was 84.8%, the specificity was 93.1%, the positive predictive value was 92.2%, the negative predictive value was 86.5% and the Youden index was 77.9%. Serum ADA levels in patients with HFRS tended to decrease at discharge compared with those at admission.

Conclusion

ADA could be a potential molecular marker for diagnosis and prognosis of HFRS patients.

Comparison of ARIMA and LSTM for prediction of hemorrhagic fever at different time scales in China

Objectives

This study intends to build and compare two kinds of forecasting models at different time scales for hemorrhagic fever incidence in China.

Methods

Autoregressive Integrated Moving Average (ARIMA) and Long Short-Term Memory Neural Network (LSTM) were adopted to fit monthly, weekly and daily incidence of hemorrhagic fever in China from 2013 to 2018. The two models, combined and uncombined with rolling forecasts, were used to predict the incidence in 2019 to examine their stability and applicability.

Results

ARIMA (2, 1, 1) (0, 1, 1)₁₂, ARIMA (1, 1, 3) (1, 1, 1)₅₂ and ARIMA (5, 0, 1) were selected as the best fitting ARIMA model for monthly, weekly and daily incidence series, respectively. The LSTM model with 64 neurons and Stochastic Gradient Descent (SGDM) for monthly incidence, 8 neurons and Adaptive Moment Estimation (Adam) for weekly incidence, and 64 neurons and Root Mean Square Prop (RMSprop) for daily incidence were selected as the best fitting LSTM models. The values of root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE) of the models combined with rolling forecasts in 2019 were lower than those of the direct forecasting models for both ARIMA and LSTM. It was shown from the forecasting performance in 2019 that ARIMA was better than LSTM for monthly and weekly forecasting while the LSTM was better than ARIMA for daily forecasting in rolling forecasting models.

Conclusions

Both ARIMA and LSTM could be used to build a prediction model for the incidence of hemorrhagic fever. Different models might be more suitable for the incidence prediction at different time scales. The findings can provide a good reference for future selection of prediction models and establishments of early warning systems for hemorrhagic fever.

Time series analysis of hemorrhagic fever with renal syndrome in mainland China by using an XGBoost forecasting model

BACKGROUND

Hemorrhagic 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.

METHODS

We 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.

RESULTS

There 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.

CONCLUSIONS

The 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.

Improving the precision of modeling the incidence of hemorrhagic fever with renal syndrome in mainland China with an ensemble machine learning approach

OBJECTIVE

Hemorrhagic fever with renal syndrome (HFRS), one of the main public health concerns in mainland China, is a group of clinically similar diseases caused by hantaviruses. Statistical approaches have always been leveraged to forecast the future incidence rates of certain infectious diseases to effectively control their prevalence and outbreak potential. Compared to the use of one base model, model stacking can often produce better forecasting results. In this study, we fitted the monthly reported cases of HFRS in mainland China with a model stacking approach and compared its forecasting performance with those of five base models.

METHOD

We fitted the monthly reported cases of HFRS ranging from January 2004 to June 2019 in mainland China with an autoregressive integrated moving average (ARIMA) model; the Holt-Winter (HW) method, seasonal decomposition of the time series by LOESS (STL); a neural network autoregressive (NNAR) model; and an exponential smoothing state space model with a Box-Cox transformation; ARMA errors; and trend and seasonal components (TBATS), and we combined the forecasting results with the inverse rank approach. The forecasting performance was estimated based on several accuracy criteria for model prediction, including the mean absolute percentage error (MAPE), root-mean-squared error (RMSE) and mean absolute error (MAE).

RESULT

There was a slight downward trend and obvious seasonal periodicity inherent in the time series data for HFRS in mainland China. The model stacking method was selected as the best approach with the best performance in terms of both fitting (RMSE 128.19, MAE 85.63, MAPE 8.18) and prediction (RMSE 151.86, MAE 118.28, MAPE 13.16).

CONCLUSION

The results showed that model stacking by using the optimal mean forecasting weight of the five abovementioned models achieved the best performance in terms of predicting HFRS one year into the future. This study has corroborated the conclusion that model stacking is an easy way to enhance prediction accuracy when modeling HFRS.

Analysis of Hemorrhagic Fever With Renal Syndrome Using Wavelet Tools in Mainland China, 2004-2019

Introduction : Hemorrhagic fever with renal syndrome (HFRS) is a life-threatening public health problem in China, accounting for ~90% of HFRS cases reported globally. Accurate analysis and prediction of the HFRS epidemic could help to establish effective preventive measures.

Materials and Methods : In this study, the geographical information system (GIS) explored the spatiotemporal features of HFRS, the wavelet power spectrum (WPS) unfolded the cyclical fluctuation of HFRS, and the wavelet neural network (WNN) model predicted the trends of HFRS outbreaks in mainland China.

Results : A total of 209,209 HFRS cases were reported in mainland China from 2004 to 2019, with the annual incidence ranged from 0 to 13.05 per 100,0000 persons at the province level. The WPS proved that the periodicity of HFRS could be half a year, 1 year, and roughly 7-year at different time intervals. The WNN structure of 12-6-1 was set up as the fittest forecasting model for the HFRS epidemic.

Conclusions : This study provided several potential support tools for the control and risk-management of HFRS in China.

SARFIMA model prediction for infectious diseases: application to hemorrhagic fever with renal syndrome and comparing with SARIMA

Background

The early warning model of infectious diseases plays a key role in prevention and control. This study aims to using seasonal autoregressive fractionally integrated moving average (SARFIMA) model to predict the incidence of hemorrhagic fever with renal syndrome (HFRS) and comparing with seasonal autoregressive integrated moving average (SARIMA) model to evaluate its prediction effect.

Methods

Data on notified HFRS cases in Weifang city, Shandong Province were collected from the official website and Shandong Center for Disease Control and Prevention between January 1, 2005 and December 31, 2018. The SARFIMA model considering both the short memory and long memory was performed to fit and predict the HFRS series. Besides, we compared accuracy of fit and prediction between SARFIMA and SARIMA which was used widely in infectious diseases.

Results

Model assessments indicated that the SARFIMA model has better goodness of fit (SARFIMA (1, 0.11, 2)(1, 0, 1)₁₂: Akaike information criterion (AIC):-631.31; SARIMA (1, 0, 2)(1, 1, 1)₁₂: AIC: − 227.32) and better predictive ability than the SARIMA model (SARFIMA: root mean square error (RMSE):0.058; SARIMA: RMSE: 0.090).

Conclusions

The SARFIMA model produces superior forecast performance than the SARIMA model for HFRS. Hence, the SARFIMA model may help to improve the forecast of monthly HFRS incidence based on a long-range dataset.

Molecular and epidemiological characteristics of human Puumala and Dobrava-Belgrade hantavirus infections, Germany, 2001 to 2017

Introduction

Two hantavirus species, Puumala (PUUV) and Dobrava-Belgrade (DOBV) virus (genotype Kurkino), are endemic in Germany. Recent PUUV outbreaks raised questions concerning increasing frequency of outbreaks and expansion of PUUV endemic areas.

Aims

To describe the epidemiology of human PUUV and DOBV infections in Germany.

Methods

We conducted an observational retrospective study analysing national hantavirus surveillance data notified to the national public health institute and hantavirus nucleotide sequences from patients collected at the national consultation laboratory between 2001 and 2017. Matching molecular sequences with surveillance data, we conducted epidemiological, phylogenetic and phylogeographic analyses.

Results

In total, 12,148 cases of symptomatic hantavirus infection were notified 2001–17 (mean annual incidence: 0.87/100,000; range: 0.09–3.51). PUUV infections showed a highly variable space-time disease incidence pattern, causing large outbreaks every 2–3 years with peaks in early summer and up to 3,000 annually reported cases. Sex-specific differences in disease presentation were observed. Of 202 PUUV nucleotide sequences obtained from cases, 189 (93.6%) fall into well-supported phylogenetic clusters corresponding to different endemic areas in Germany. DOBV infections caused few, mostly sporadic cases in autumn and winter in the north and east of Germany.

Conclusions

The frequency of PUUV outbreaks increased between 2001 and 2017 but our data does not support the suggested expansion of endemic areas. The epidemiology of PUUV and DOBV-Kurkino infections differs in several aspects. Moreover, the latter are relatively rare and combining efforts and data of several countries to identify risk factors and develop specific recommendations for prevention could be worthwhile.

Time series analysis of temporal trends in hemorrhagic fever with renal syndrome morbidity rate in China from 2005 to 2019

Hemorrhagic fever with renal syndrome (HFRS) is seriously endemic in China with 70%~90% of the notified cases worldwide and showing an epidemic tendency of upturn in recent years. Early detection for its future epidemic trends plays a pivotal role in combating this threat. In this scenario, our study investigates the suitability for application in analyzing and forecasting the epidemic tendencies based on the monthly HFRS morbidity data from 2005 through 2019 using the nonlinear model-based self-exciting threshold autoregressive (SETAR) and logistic smooth transition autoregressive (LSTAR) methods. The experimental results manifested that the SETAR and LSTAR approaches presented smaller values among the performance measures in both two forecasting subsamples, when compared with the most extensively used seasonal autoregressive integrated moving average (SARIMA) method, and the former slightly outperformed the latter. Descriptive statistics showed an epidemic tendency of downturn with average annual percent change (AAPC) of −5.640% in overall HFRS, however, an upward trend with an AAPC = 1.213% was observed since 2016 and according to the forecasts using the SETAR, it would seemingly experience an outbreak of HFRS in China in December 2019. Remarkably, there were dual-peak patterns in HFRS incidence with a strong one occurring in November until January of the following year, additionally, a weak one in May and June annually. Therefore, the SETAR and LSTAR approaches may be a potential useful tool in analyzing the temporal behaviors of HFRS in China.

The year 2020, a milestone in breaking the vicious cycle of poverty and illness in China

Marking the end of the five-year programme initiated by the Chinese Government to lift more than 70 million people out of poverty, the year 2020 is a milestone. Poverty alleviation has moved strongly forward in China and the major health indicators are now better than the average of all middle- and high-income countries. However, the dual burden of infectious and chronic diseases remains a challenge with respect to achieving the health target in the United Nations 2030 Agenda for sustainable development goals (SDGs). In 2015, about 44% of the poor population in China were impoverished by illness but already in 2018, multi-sectoral actions delivered by the Health-related Poverty Alleviation programme had reduced the number almost by half. In the past three years 15 million poor people (98% of the poor population) with infectious and chronic diseases had been treated and taken care of thanks to financial support through multiple health insurance schemes and other governmental subsidies. This article discusses the lessons learnt with regard to health-related poverty alleviation in China with special reference to those still remaining impoverished by illness. Consolidation of the achievements reached and provision of basic needs to those still disadvantaged and in poor health will require a major improvement of accessibility to, and affordability of, health services. The next step towards enhanced productivity and better living conditions will involve upgrading of the capacity of health professionals in the poor regions, promotion of coherent efforts in health-related poverty alleviation and rural revitalization measures. As an additional measure, data monitoring and research on health poverty alleviation should be strengthened as they are essential to generate the evidence and knowledge needed to support the move in the direction envisioned by the SDGs, and the new Healthy China 2030 programme.