Time Series Analysis and Forecasting of the Hand-Foot-Mouth Disease Morbidity in China Using An Advanced Exponential Smoothing State Space TBATS Model

Predicting the epidemiological trend of acute hemorrhagic conjunctivitis in China using Bayesian structural time-series model

This study aims to explore the application value of the Bayesian Time Structure Sequence (BSTS) model in estimating the acute hemorrhagic conjunctivitis (AHC) epidemics. The reported AHC cases spanning from January 2011 to October 2022 in China were collated. Utilizing R software, the BSTS and Autoregressive Integrated Moving Average (ARIMA) models were constructed using the data from January 2011 to December 2021. The prediction effect of both models was compared using the data from January to October 2022, and finally the AHC incidence from November 2022 to December 2023 was predicted. The results indicated that forecast errors under the BSTS model were lower than those under the ARIMA model. The actual AHC incidence in July 2022 from the ARIMA model deviated from the 95% confidence interval (CI) of the predicted value. However, the observed AHC incidence from the BSTS model fell within the 95% CI of the predicted value. Notably, the BSTS model predicted 26,474 new AHC cases in China from November 2022 to December 2023, exhibiting better prediction performance compared to the ARIMA model. This indicates that the BSTS model possesses a high application value for forecasting the epidemic trends of AHC, making it a valuable tool for disease surveillance and prevention strategies.

Spatial-temporal analysis of hepatitis E in Hainan Province, China (2013-2022): insights from four major hospitals

Objective

Exploring the Incidence, Epidemic Trends, and Spatial Distribution Characteristics of Sporadic Hepatitis E in Hainan Province from 2013 to 2022 through four major tertiary hospitals in the Province.

Methods

We collected data on confirmed cases of hepatitis E in Hainan residents admitted to the four major tertiary hospitals in Haikou City from January 2013 to December 2022. We used SPSS software to analyze the correlation between incidence rate and economy, population density and geographical location, and origin software to draw a scatter chart and SAS 9.4 software to conduct a descriptive analysis of the time trend. The distribution was analyzed using ArcMap 10.8 software (spatial autocorrelation analysis, hotspot identification, concentration, and dispersion trend analysis). SAS software was used to build an autoregressive integrated moving average model (ARIMA) to predict the monthly number of cases in 2023 and 2024.

Results

From 2013 to 2022, 1,922 patients with sporadic hepatitis E were treated in the four hospitals of Hainan Province. The highest proportion of patients (n = 555, 28.88%) were aged 50-59 years. The annual incidence of hepatitis E increased from 2013 to 2019, with a slight decrease in 2020 and 2021 and an increase in 2022. The highest number of cases was reported in Haikou, followed by Dongfang and Danzhou. We found that there was a correlation between the economy, population density, latitude, and the number of cases, with the correlation coefficient |r| value fluctuating between 0.403 and 0.421, indicating a linear correlation. At the same time, a scatter plot shows the correlation between population density and incidence from 2013 to 2022, with r2 values fluctuating between 0.5405 and 0.7116, indicating a linear correlation. Global Moran's I, calculated through spatial autocorrelation analysis, showed that each year from 2013 to 2022 all had a Moran's I value >0, indicating positive spatial autocorrelation (p < 0.01). Local Moran's I analysis revealed that from 2013 to 2022, local hotspots were mainly concentrated in the northern part of Hainan Province, with Haikou, Wenchang, Ding'an, and Chengmai being frequent hotspot regions, whereas Baoting, Qiongzhong, and Ledong were frequent cold-spot regions. Concentration and dispersion analysis indicated a clear directional pattern in the average density distribution, moving from northeast to southwest. Time-series forecast modeling showed that the forecast number of newly reported cases per month remained relatively stable in 2023 and 2024, fluctuating between 17 and 19.

Conclusion

The overall incidence of hepatitis E in Hainan Province remains relatively stable. The incidence of hepatitis E in Hainan Province increased from 2013 to 2019, with a higher clustering of cases in the northeast region and a gradual spread toward the southwest over time. The ARIMA model predicted a relatively stable number of new cases each month in 2023 and 2024.

Neural-SEIR: A flexible data-driven framework for precise prediction of epidemic disease

Accurately modeling and predicting epidemic diseases is crucial to prevent disease transmission and reduce mortality. Due to various unpredictable factors, including population migration, vaccination, control efforts, and seasonal fluctuations, traditional epidemic models that rely on prior knowledge of virus transmission mechanisms may not be sufficient to forecast complex epidemics like coronavirus disease 2019(COVID-19). The application of traditional epidemiological models such as susceptible-exposed-infectious-recovered (SEIR) may face difficulties in accurately predicting such complex epidemics. Data-driven prediction approaches lack the ability to generalize and exhibit low accuracy on small datasets due to their reliance on large amounts of data without incorporating prior knowledge. To overcome this limitation, we introduce a flexible ensemble data-driven framework (Neural-SEIR) that "neuralizes" the SEIR model by approximating the core parameters through neural networks while preserving the propagation structure of SEIR. Neural-SEIR employs long short-term memory (LSTM) neural network to capture complex correlation features, exponential smoothing (ES) to model seasonal information, and prior knowledge from SEIR. By incorporating SEIR parameters into the neural network structure, Neural-SEIR leverages prior knowledge while updating parameters with real-world data. Our experimental results demonstrate that Neural-SEIR outperforms traditional machine learning and epidemiological models, achieving high prediction accuracy and efficiency in forecasting epidemic diseases.

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.

The research on TBATS and ELM models for prediction of human brucellosis cases in mainland China: a time series study

BACKGROUND

Human brucellosis is a serious public health concern in China. The objective of this study is to develop a suitable model for forecasting human brucellosis cases in mainland China.

METHODS

Data on monthly human brucellosis cases from January 2012 to December 2021 in 31 provinces and municipalities in mainland China were obtained from the National Health Commission of the People's Republic of China website. The TBATS and ELM models were constructed. The MAE, MSE, MAPE, and RMSE were calculated to evaluate the prediction performance of the two models.

RESULTS

The optimal TBATS model was TBATS (1, {0,0}, -, {< 12,4 >}) and the lowest AIC value was 1854.703. In the optimal TBATS model, {0,0} represents the ARIMA (0,0) model, {< 12,4 >} are the parameters of the seasonal periods and the corresponding number of Fourier terms, respectively, and the parameters of the Box-Cox transformation ω are 1. The optimal ELM model hidden layer number was 33 and the R-squared value was 0.89. The ELM model provided lower values of MAE, MSE, MAPE, and RMSE for both the fitting and forecasting performance.

CONCLUSIONS

The results suggest that the forecasting performance of ELM model outperforms the TBATS model in predicting human brucellosis between January 2012 and December 2021 in mainland China. Forecasts of the ELM model can help provide early warnings and more effective prevention and control measures for human brucellosis in mainland China.

Spatiotemporal cluster patterns of hand, foot, and mouth disease at the province level in mainland China, 2011–2018

Although three monovalent EV-A71 vaccines have been launched in mainland China since 2016, hand, foot, and mouth disease (HFMD) still causes a considerable disease burden in China. Vaccines’ use may change the epidemiological characters of HFMD. Spatial autocorrelation analysis and space-time scan statistics analysis were used to explore the spatiotemporal distribution pattern of this disease at the provincial level in mainland China. The effects of meteorological factors, socio-economic factors, and health resources on HFMD incidence were analyzed using Geodetector. Interrupted time series (ITS) was used to analyze the impact of the EV-A71 vaccine on the incidence of HFMD. This study found that the median annual incidence of HFMD was 153.78 per 100,000 (ranging from 120.79 to 205.06) in mainland China from 2011 to 2018. Two peaks of infections were observed per year. Children 5 years and under were the main morbid population. The spatial distribution of HFMD was presented a significant clustering pattern in each year (P<0.001). The distribution of HFMD cases was clustered in time and space. The range of cluster time was between April and October. The most likely cluster appeared in the southern coastal provinces (Guangxi, Guangdong, Hainan) from 2011 to 2017 and in the eastern coastal provinces (Shanghai, Jiangsu, Zhejiang) in 2018. The spatial heterogeneity of HFMD incidence could be attributed to meteorological factors, socioeconomic factors, and health resource. After introducing the EV-A71 vaccine, the instantaneous level of HFMD incidence decreased at the national level, and HFMD incidence trended downward in the southern coastal provinces and increased in the eastern coastal provinces. The prevention and control policies of HFMD should be adapted to local conditions in different provinces. It is necessary to advance the EV-A71 vaccination plan, expand the vaccine coverage and develop multivalent HFMD vaccines as soon as possible.

Time-Series Analysis for the Number of Foot and Mouth Disease Outbreak Episodes in Cattle Farms in Thailand Using Data from 2010-2020

Thailand is one of the countries where foot and mouth disease outbreaks have resulted in considerable economic losses. Forecasting is an important warning technique that can allow authorities to establish an FMD surveillance and control program. This study aimed to model and forecast the monthly number of FMD outbreak episodes (n-FMD episodes) in Thailand using the time-series methods, including seasonal autoregressive integrated moving average (SARIMA), error trend seasonality (ETS), neural network autoregression (NNAR), and Trigonometric Exponential smoothing state−space model with Box−Cox transformation, ARMA errors, Trend and Seasonal components (TBATS), and hybrid methods. These methods were applied to monthly n-FMD episodes (n = 1209) from January 2010 to December 2020. Results showed that the n-FMD episodes had a stable trend from 2010 to 2020, but they appeared to increase from 2014 to 2020. The outbreak episodes followed a seasonal pattern, with a predominant peak occurring from September to November annually. The single-technique methods yielded the best-fitting time-series models, including SARIMA(1,0,1)(0,1,1)12, NNAR(3,1,2)12,ETS(A,N,A), and TBATS(1,{0,0},0.8,{<12,5>}. Moreover, SARIMA-NNAR and NNAR-TBATS were the hybrid models that performed the best on the validation datasets. The models that incorporate seasonality and a non-linear trend performed better than others. The forecasts highlighted the rising trend of n-FMD episodes in Thailand, which shares borders with several FMD endemic countries in which cross-border trading of cattle is found common. Thus, control strategies and effective measures to prevent FMD outbreaks should be strengthened not only in Thailand but also in neighboring countries.

A Novel Approach to Modeling and Forecasting Cancer Incidence and Mortality Rates through Web Queries and Automated Forecasting Algorithms: Evidence from Romania

Simple Summary

Cancer remains a global burden, currently causing nearly one in six deaths worldwide. Accurate projections of cancer incidence and mortality are needed for effective and efficient policymaking, accurate resource allocation, and to assess the impact of newly introduced policies and measures. However, the COVID-19 pandemic disrupted public health systems and caused a significant number of cancers to remain undiagnosed, thus affecting the quality of official statistics and their usefulness for health studies. This paper addresses this issue by proposing novel cancer incidence/cancer mortality models based on population web-search habits and historical links with official health variables. The models are empirically estimated using data from one of the most vulnerable European Union (EU) members, Romania, a country that consistently reports lower survival rates than the EU average, and are further used to forecast cancer incidence and mortality rates in the country. Research findings have important policy implications, and the novel framework, owing to its generalizability, can be applied to the same task in other countries. Overall, the results indicate a continuation of the increasing trends in cancer incidence and mortality in Romania and thus underline the urgency to change the status quo in the Romanian public-health system.

Abstract

Cancer remains a leading cause of worldwide mortality and is a growing, multifaceted global burden. As a result, cancer prevention and cancer mortality reduction are counted among the most pressing public health issues of the twenty-first century. In turn, accurate projections of cancer incidence and mortality rates are paramount for robust policymaking, aimed at creating efficient and inclusive public health systems and also for establishing a baseline to assess the impact of newly introduced public health measures. Within the European Union (EU), Romania consistently reports higher mortality from all types of cancer than the EU average, caused by an inefficient and underfinanced public health system and lower economic development that in turn have created the phenomenon of “oncotourism”. This paper aims to develop novel cancer incidence/cancer mortality models based on historical links between incidence and mortality occurrence as reflected in official statistics and population web-search habits. Subsequently, it employs estimates of the web query index to produce forecasts of cancer incidence and mortality rates in Romania. Various statistical and machine-learning models—the autoregressive integrated moving average model (ARIMA), the Exponential Smoothing State Space Model with Box-Cox Transformation, ARMA Errors, Trend, and Seasonal Components (TBATS), and a feed-forward neural network nonlinear autoregression model, or NNAR—are estimated through automated algorithms to assess in-sample fit and out-of-sample forecasting accuracy for web-query volume data. Forecasts are produced with the overperforming model in the out-of-sample context (i.e., NNAR) and fed into the novel incidence/mortality models. Results indicate a continuation of the increasing trends in cancer incidence and mortality in Romania by 2026, with projected levels for the age-standardized total cancer incidence of 313.8 and the age-standardized mortality rate of 233.8 representing an increase of 2%, and, respectively, 3% relative to the 2019 levels. Research findings thus indicate that, under the no-change hypothesis, cancer will remain a significant burden in Romania and highlight the need and urgency to improve the status quo in the Romanian public health system.

Estimating the Long-Term Epidemiological Trends and Seasonality of Hemorrhagic Fever with Renal Syndrome in China

OBJECTIVE

We aim to examine the adequacy of an innovation state-space modeling framework (called TBATS) in forecasting the long-term epidemic seasonality and trends of hemorrhagic fever with renal syndrome (HFRS).

METHODS

The HFRS morbidity data from January 1995 to December 2020 were taken, and subsequently, the data were split into six different training and testing segments (including 12, 24, 36, 60, 84, and 108 holdout monthly data) to investigate its predictive ability of the TBATS method, and its forecasting performance was compared with the seasonal autoregressive integrated moving average (SARIMA).

RESULTS

The TBATS (0.27, {0,0}, -, {<12,4>}) and SARIMA (0,1,(1,3))(0,1,1)12 were selected as the best TBATS and SARIMA methods, respectively, for the 12-step ahead prediction. The mean absolute deviation, root mean square error, mean absolute percentage error, mean error rate, and root mean square percentage error were 91.799, 14.772, 123.653, 0.129, and 0.193, respectively, for the preferred TBATS method and were 144.734, 25.049, 161.671, 0.203, and 0.296, respectively, for the preferred SARIMA method. Likewise, for the 24-, 36-, 60-, 84-, and 108-step ahead predictions, the preferred TBATS methods produced smaller forecasting errors over the best SARIMA methods. Further validations also suggested that the TBATS model outperformed the Error-Trend-Seasonal framework, with little exception. HFRS had dual seasonal behaviors, peaking in May-June and November-December. Overall a notable decrease in the HFRS morbidity was seen during the study period (average annual percentage change=-6.767, 95% confidence intervals: -10.592 to -2.778), and yet different stages had different variation trends. Besides, the TBATS model predicted a plateau in the HFRS morbidity in the next ten years.

CONCLUSION

The TBATS approach outperforms the SARIMA approach in estimating the long-term epidemic seasonality and trends of HFRS, which is capable of being deemed as a promising alternative to help stakeholders to inform future preventive policy or practical solutions to tackle the evolving scenarios.