Application of a hybrid model in predicting the incidence of tuberculosis in a Chinese population

Long- and short-run asymmetric impacts of climate variation on tuberculosis based on a time series study

Distinguishing between long-term and short-term effects allows for the identification of different response mechanisms. This study investigated the long- and short-run asymmetric impacts of climate variation on tuberculosis (TB) and constructed forecasting models using the autoregressive distributed lag (ARDL) and nonlinear ARDL (NARDL). TB showed a downward trend, peaking in March-May per year. A 1 h increment or decrement in aggregate sunshine hours resulted in an increase of 32 TB cases. A 1 m/s increment and decrement in average wind velocity contributed to a decrement of 3600 and 5021 TB cases, respectively (Wald long-run asymmetry test [WLR] = 13.275, P < 0.001). A 1% increment and decrement in average relative humidity contributed to an increase of 115 and 153 TB cases, respectively. A 1 hPa increment and decrement in average air pressure contributed to a decrease of 318 and 91 TB cases, respectively (WLR = 7.966, P = 0.005). ∆temperature(-), ∆(sunshine hours)( -), ∆(wind velocity)(+) and ∆(wind velocity)(-) at different lags had a meaningful short-run effect on TB. The NARDL outperformed the ARDL in forecasting. Climate variation has significant long- and short-run asymmetric impacts on TB. By incorporating both dimensions of effects into the NARDL, the accuracy of the forecasts and policy recommendations for TB can be enhanced.

Epidemiological changes of scarlet fever before, during and after the COVID-19 pandemic in Chongqing, China: a 19-year surveillance and prediction study

BACKGROUND

This study aimed to investigate the epidemiological changes in scarlet fever before, during and after the COVID-19 pandemic (2005-2023) and predict the incidence of the disease in 2024 and 2025 in Chongqing Municipality, Southwest China.

METHODS

Descriptive analysis was used to summarize the characteristics of the scarlet fever epidemic. Spatial autocorrelation analysis was utilized to explore the distribution pattern of the disease, and the seasonal autoregressive integrated moving average (SARIMA) model was constructed to predict its incidence in 2024 and 2025.

RESULTS

Between 2005 and 2023, 9,593 scarlet fever cases were reported in Chongqing, which resulted in an annual average incidence of 1.6694 per 100,000 people. Children aged 3-7 were the primary victims of this disease, with the highest average incidence found among children aged 6 (5.0002 per 100,000 people). Kindergarten children were the dominant infected population, accounting for as much as 54.32% of cases, followed by students (34.09%). The incidence for the male was 1.51 times greater than that for the female. The monthly distribution of the incidence showed a bimodal pattern, with one peak occurring between April and June and another in November or December. The spatial autocorrelation analysis revealed that scarlet fever cases were markedly clustered; the areas with higher incidence were mainly concentrated in Chongqing's urban areas and its adjacent districts, and gradually spreading to remote areas after 2020. The incidence of scarlet fever increased by 106.54% and 39.33% in the post-upsurge period (2015-2019) and the dynamic zero-COVID period (2020-2022), respectively, compared to the pre-upsurge period (2005-2014) (P < 0.001). During the dynamic zero-COVID period, the incidence of scarlet fever decreased by 68.61%, 25.66%, and 10.59% (P < 0.001) in 2020, 2021, and 2022, respectively, compared to the predicted incidence. In 2023, after the dynamic zero-COVID period, the reported cases decreased to 1.5168 per 100,000 people unexpectedly instead of increasing. The cases of scarlet fever are predicted to increase in 2024 (675 cases) and 2025 (705 cases).

CONCLUSIONS

Children aged 3-7 years are the most affected population, particularly males, and kindergartens and primary schools serving as transmission hotspots. It is predicted that the high incidence of scarlet fever in Chongqing will persist in 2024 and 2025, and the outer districts (counties) beyond urban zone would bear the brunt of the impact. Therefore, imminent public health planning and resource allocation should be focused within those areas.

Forecasting tuberculosis incidence: a review of time series and machine learning models for prediction and eradication strategies

Despite efforts by the World Health Organization (WHO), tuberculosis (TB) remains a leading cause of fatalities globally. This study reviews time series and machine learning models for TB incidence prediction, identifies popular algorithms, and highlights the need for further research to improve accuracy and global scope. SCOPUS, PUBMED, IEEE, Web of Science, and PRISMA were used for search and article selection from 2012 to 2023. The results revealed that ARIMA, SARIMA, ETS, GRNN, BPNN, NARNN, NNAR, and RNN are popular time series and ML algorithms adopted for TB incidence rate predictions. The inaccurate TB incidence prediction and limited global scope of prior studies suggest a need for further research. This review serves as a roadmap for the WHO to focus on regions that require more attention for TB prevention and the need for more sophisticated models for TB incidence predictions.

Application of ARIMA, and hybrid ARIMA Models in predicting and forecasting tuberculosis incidences among children in Homa Bay and Turkana Counties, Kenya

Tuberculosis (TB) infections among children (below 15 years) is a growing concern, particularly in resource-limited settings. However, the TB burden among children is relatively unknown in Kenya where two-thirds of estimated TB cases are undiagnosed annually. Very few studies have used Autoregressive Integrated Moving Average (ARIMA), and hybrid ARIMA models to model infectious diseases globally. We applied ARIMA, and hybrid ARIMA models to predict and forecast TB incidences among children in Homa Bay and Turkana Counties in Kenya. The ARIMA, and hybrid models were used to predict and forecast monthly TB cases reported in the Treatment Information from Basic Unit (TIBU) system by health facilities in Homa Bay and Turkana Counties between 2012 and 2021. The best parsimonious ARIMA model that minimizes errors was selected based on a rolling window cross-validation procedure. The hybrid ARIMA-ANN model produced better predictive and forecast accuracy compared to the Seasonal ARIMA (0,0,1,1,0,1,12) model. Furthermore, using the Diebold-Mariano (DM) test, the predictive accuracy of ARIMA-ANN versus ARIMA (0,0,1,1,0,1,12) model were significantly different, p<0.001, respectively. The forecasts showed a TB incidence of 175 TB cases per 100,000 (161 to 188 TB incidences per 100,000 population) children in Homa Bay and Turkana Counties in 2022. The hybrid (ARIMA-ANN) model produces better predictive and forecast accuracy compared to the single ARIMA model. The findings show evidence that the incidence of TB among children below 15 years in Homa Bay and Turkana Counties is significantly under-reported and is potentially higher than the national average.

Estimating the tuberculosis incidence using a SARIMAX-NNARX hybrid model by integrating meteorological factors in Qinghai Province, China

Tuberculosis (TB) is recognized as being a major public health concern owing to its increase in Qinghai, China. In this study, we aimed to estimate the long-term effects of meteorological variables on TB incidence and construct an advanced hybrid model with seasonal autoregressive integrated moving average (SARIMA) and a neural network nonlinear autoregression (SARIMAX-NNARX) by integrating meteorological factors and evaluating the model fitting and prediction effect. During 2005-2017, TB experienced an upward trend with obvious periodic and seasonal characteristics, peaking in spring and winter. The results showed that TB incidence was positively correlated with average relative humidity (ARH) with a 2-month lag (β = 1.889, p = 0.003), but negatively correlated with average atmospheric pressure (AAP) with a 1-month lag (β =  - 1.633, p = 0.012), average temperature (AT) with a 2-month lag (β =  - 0.093, p = 0.027), and average wind speed (AWS) with a 0-month lag (β =  - 13.221, p = 0.033), respectively. The SARIMA (3,1,0)(1,1,1)_12, SARIMAX(3,1,0)(1,1,1)₁₂, and SARIMAX(3,1,0)(1,1,1)₁₂-NNARX(15,3) were considered preferred models based on the evaluation criteria. Of them, the SARIMAX-NNARX technique had smaller error values than the SARIMA and SARIMAX models in both fitting and forecasting aspects. The sensitivity analysis also revealed the robustness of the mixture forecasting model. Therefore, the SARIMAX-NNARX model by integrating meteorological variables can be used as an accurate method for forecasting the epidemic trends which would be great importance for TB prevention and control in the coming periods in Qinghai.

Epidemiological trend in scarlet fever incidence in China during the COVID-19 pandemic: A time series analysis

Objective

Over the past decade, scarlet fever has caused a relatively high economic burden in various regions of China. Non-pharmaceutical interventions (NPIs) are necessary because of the absence of vaccines and specific drugs. This study aimed to characterize the demographics of patients with scarlet fever, describe its spatiotemporal distribution, and explore the impact of NPIs on the disease in the era of coronavirus disease 2019 (COVID-19) in China.

Methods

Using monthly scarlet fever data from January 2011 to December 2019, seasonal autoregressive integrated moving average (SARIMA), advanced innovation state-space modeling framework that combines Box-Cox transformations, Fourier series with time-varying coefficients, and autoregressive moving average error correction method (TBATS) models were developed to select the best model for comparing between the expected and actual incidence of scarlet fever in 2020. Interrupted time series analysis (ITSA) was used to explore whether NPIs have an effect on scarlet fever incidence, while the intervention effects of specific NPIs were explored using correlation analysis and ridge regression methods.

Results

From 2011 to 2017, the total number of scarlet fever cases was 400,691, with children aged 0-9 years being the main group affected. There were two annual incidence peaks (May to June and November to December). According to the best prediction model TBATS (0.002, {0, 0}, 0.801, {<12, 5>}), the number of scarlet fever cases was 72,148 and dual seasonality was no longer prominent. ITSA showed a significant effect of NPIs of a reduction in the number of scarlet fever episodes (β2 = -61526, P < 0.005), and the effect of canceling public events (c3) was the most significant (P = 0.0447).

Conclusions

The incidence of scarlet fever during COVID-19 was lower than expected, and the total incidence decreased by 80.74% in 2020. The results of this study indicate that strict NPIs may be of potential benefit in preventing scarlet fever occurrence, especially that related to public event cancellation. However, it is still important that vaccines and drugs are available in the future.

A data-driven eXtreme gradient boosting machine learning model to predict COVID-19 transmission with meteorological drivers

COVID-19 pandemic has become a global major public health concern. Examining the meteorological risk factors and accurately predicting the incidence of the COVID-19 pandemic is an extremely important challenge. Therefore, in this study, we analyzed the relationship between meteorological factors and COVID-19 transmission in SAARC countries. We also compared the predictive accuracy of Autoregressive Integrated Moving Average (ARIMAX) and eXtreme Gradient Boosting (XGBoost) methods for precise modelling of COVID-19 incidence. We compiled a daily dataset including confirmed COVID-19 case counts, minimum and maximum temperature (°C), relative humidity (%), surface pressure (kPa), precipitation (mm/day) and maximum wind speed (m/s) from the onset of the disease to January 29, 2022, in each country. The data were divided into training and test sets. The training data were used to fit ARIMAX model for examining significant meteorological risk factors. All significant factors were then used as covariates in ARIMAX and XGBoost models to predict the COVID-19 confirmed cases. We found that maximum temperature had a positive impact on the COVID-19 transmission in Afghanistan (β = 11.91, 95% CI: 4.77, 19.05) and India (β = 0.18, 95% CI: 0.01, 0.35). Surface pressure had a positive influence in Pakistan (β = 25.77, 95% CI: 7.85, 43.69) and Sri Lanka (β = 411.63, 95% CI: 49.04, 774.23). We also found that the XGBoost model can help improve prediction of COVID-19 cases in SAARC countries over the ARIMAX model. The study findings will help the scientific communities and policymakers to establish a more accurate early warning system to control the spread of the pandemic.

Application of the ARIMA Model in Forecasting the Incidence of Tuberculosis in Anhui During COVID-19 Pandemic from 2021 to 2022

Objective

Forecasting the seasonality and trend of pulmonary tuberculosis is important for the rational allocation of health resources. In this study, we predict the incidence of pulmonary tuberculosis by establishing the autoregressive integrated moving average (ARIMA) model and providing support for pulmonary tuberculosis prevention and control during COVID-19 pandemic.

Methods

Registered tuberculosis(TB) cases from January 2013 to December 2020 in Anhui province were analysed using traditional descriptive epidemiological methods. Then we used the monthly incidence rate of TB from January 2013 through June 2020 to construct ARIMA model, and used the incidence rate from July 2020 to December 2020 to evaluate the forecasting accuracy. Ljung Box test, Akaike's information criterion(AICc), Bayesian information criterion(BIC) and Realtive error were used to evaluate the model fitting and forecasting effect, Finally, the optimal model was used to forecast the expected monthly incidence of tuberculosis for 2021 and 2022 to learn about the incidence trend.

Results

A total of 255,656 TB cases were registered. The reported rate of tuberculosis was highest in 2013 and lowest in 2020. The peak incidence was in March, Tongling (71.97/100,000), Chizhou (59.93/100,000), and Huainan (58.36/100,000) had the highest number of cases. The ratio of male to female incidence was 2.59:1, with the largest proportion of people being between 66 and 75 years old. The main occupation of patients was farmer. ARIMA (0, 1, 1) (0, 1, 1)₁₂ model was the optimal model to forecast the incidence trend of TB.

Conclusion

Tongling, Chizhou, and Huainan should strengthen measures for TB. In particular, the government should pay more attention on elderly people to prevent tuberculosis infections. The rate of TB patient registration and reporting has decreased under the pandemic of COVID-19. The ARIMA model can be a useful tool for predicting future TB cases.

Accuracy comparison of ARIMA and XGBoost forecasting models in predicting the incidence of COVID-19 in Bangladesh

Accurate predictive time series modelling is important in public health planning and response during the emergence of a novel pandemic. Therefore, the aims of the study are three-fold: (a) to model the overall trend of COVID-19 confirmed cases and deaths in Bangladesh; (b) to generate a short-term forecast of 8 weeks of COVID-19 cases and deaths; (c) to compare the predictive accuracy of the Autoregressive Integrated Moving Average (ARIMA) and eXtreme Gradient Boosting (XGBoost) for precise modelling of non-linear features and seasonal trends of the time series. The data were collected from the onset of the epidemic in Bangladesh from the Directorate General of Health Service (DGHS) and Institute of Epidemiology, Disease Control and Research (IEDCR). The daily confirmed cases and deaths of COVID-19 of 633 days in Bangladesh were divided into several training and test sets. The ARIMA and XGBoost models were established using those training data, and the test sets were used to evaluate each model's ability to forecast and finally averaged all the predictive performances to choose the best model. The predictive accuracy of the models was assessed using the mean absolute error (MAE), mean percentage error (MPE), root mean square error (RMSE) and mean absolute percentage error (MAPE). The findings reveal the existence of a nonlinear trend and weekly seasonality in the dataset. The average error measures of the ARIMA model for both COVID-19 confirmed cases and deaths were lower than XGBoost model. Hence, in our study, the ARIMA model performed better than the XGBoost model in predicting COVID-19 confirmed cases and deaths in Bangladesh. The suggested prediction model might play a critical role in estimating the spread of a novel pandemic in Bangladesh and similar countries.

Deep learning time series prediction models in surveillance data of hepatitis incidence in China

Background

Precise incidence prediction of Hepatitis infectious disease is critical for early prevention and better government strategic planning. In this paper, we presented different prediction models using deep learning methods based on the monthly incidence of Hepatitis through a national public health surveillance system in China mainland.

Methods

We assessed and compared the performance of three deep learning methods, namely, Long Short-Term Memory (LSTM) prediction model, Recurrent Neural Network (RNN) prediction model, and Back Propagation Neural Network (BPNN) prediction model. The data collected from 2005 to 2018 were used for the training and prediction model, while the data are split via 5-Fold cross-validation. The performance was evaluated based on three metrics: mean square error (MSE), mean absolute error (MAE), and mean absolute percentage error (MAPE).

Results

Among the year 2005–2018, 20,924,951 cases and 11,892 deaths were supervised in the system. Hepatitis B (HB) is the most disease-causing incidence and death, and the proportion is greater than 70 percent, while the percentage of the incidence and deaths is decreased much in 2018 compared with 2005. Based on the measured errors and the visualization of the three neural networks, there is no one model predicting the incidence cases that can be completely superior to other models. When predicting the number of incidence cases for HB, the performance ranking of the three models from high to low is LSTM, BPNN, RNN, while it is LSTM, RNN, BPNN for Hepatitis C (HC). while the MAE, MSE and MAPE of the LSTM model for HB, HC are 3.84*10⁻⁰⁶, 3.08*10⁻¹¹, 4.981, 8.84*10⁻⁰⁶, 1.98*10⁻¹²,5.8519, respectively.

Conclusions

The deep learning time series predictive models show their significance to forecast the Hepatitis incidence and have the potential to assist the decision-makers in making efficient decisions for the early detection of the disease incidents, which would significantly promote Hepatitis disease control and management.

The research of ARIMA, GM(1,1), and LSTM models for prediction of TB cases in China

Background and objective

Tuberculosis (Tuberculosis, TB) is a public health problem in China, which not only endangers the population’s health but also affects economic and social development. It requires an accurate prediction analysis to help to make policymakers with early warning and provide effective precautionary measures. In this study, ARIMA, GM(1,1), and LSTM models were constructed and compared, respectively. The results showed that the LSTM was the optimal model, which can be achieved satisfactory performance for TB cases predictions in mainland China.

Methods

The data of tuberculosis cases in mainland China were extracted from the National Health Commission of the People’s Republic of China website. According to the TB data characteristics and the sample requirements, we created the ARIMA, GM(1,1), and LSTM models, which can make predictions for the prevalence trend of TB. The mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE) were applied to evaluate the effects of model fitting predicting accuracy.

Results

There were 3,021,995 tuberculosis cases in mainland China from January 2018 to December 2020. And the overall TB cases in mainland China take on a downtrend trend. We established ARIMA, GM(1,1), and LSTM models, respectively. The optimal ARIMA model is the ARIMA (0,1,0) × (0,1,0)12. The equation for GM(1,1) model was X(k+1) = -10057053.55e^(-0.01k) + 10153178.55 the Mean square deviation ratio C value was 0.49, and the Small probability of error P was 0.94. LSTM model consists of an input layer, a hidden layer and an output layer, the parameters of epochs, learning rating are 60, 0.01, respectively. The MAE, RMSE, and MAPE values of LSTM model were smaller than that of GM(1,1) and ARIMA models.

Conclusions

Our findings showed that the LSTM model was the optimal model, which has a higher accuracy performance than that of ARIMA and GM (1,1) models. Its prediction results can act as a predictive tool for TB prevention measures in mainland China.

Estimating the Effects of the COVID-19 Outbreak on the Reductions in Tuberculosis Cases and the Epidemiological Trends in China: A Causal Impact Analysis

Objective

COVID-19 may have a demonstrable influence on disease patterns. However, it remained unknown how tuberculosis (TB) epidemics are impacted by the COVID-19 outbreak. The purposes of this study are to evaluate the impacts of the COVID-19 outbreak on the decreases in the TB case notifications and to forecast the epidemiological trends in China.

Methods

The monthly TB incidents from January 2005 to December 2020 were taken. Then, we investigated the causal impacts of the COVID-19 pandemic on the TB case reductions using intervention analysis under the Bayesian structural time series (BSTS) method. Next, we split the observed values into different training and testing horizons to validate the forecasting performance of the BSTS method.

Results

The TB incidence was falling during 2005–2020, with an average annual percentage change of −3.186 (95% confidence interval [CI] −4.083 to −2.281), and showed a peak in March–April and a trough in January–February per year. The BSTS method assessed a monthly average reduction of 14% (95% CI 3.8% to 24%) in the TB case notifications from January–December 2020 owing to COVID-19 (probability of causal effect=99.684%, P=0.003), and this method generated a highly accurate forecast for all the testing horizons considering the small forecasting error rates and estimated a continued downward trend from 2021 to 2035 (annual percentage change =−2.869, 95% CI −3.056 to −2.681).

Conclusion

COVID-19 can cause medium- and longer-term consequences for the TB epidemics and the BSTS model has the potential to forecast the epidemiological trends of the TB incidence, which can be recommended as an automated application for public health policymaking in China. Considering the slow downward trend in the TB incidence, additional measures are required to accelerate the progress of the End TB Strategy.

Estimating the COVID-19 prevalence and mortality using a novel data-driven hybrid model based on ensemble empirical mode decomposition

In this study, we proposed a new data-driven hybrid technique by integrating an ensemble empirical mode decomposition (EEMD), an autoregressive integrated moving average (ARIMA), with a nonlinear autoregressive artificial neural network (NARANN), called the EEMD-ARIMA-NARANN model, to perform time series modeling and forecasting based on the COVID-19 prevalence and mortality data from 28 February 2020 to 27 June 2020 in South Africa and Nigeria. By comparing the accuracy level of forecasting measurements with the basic ARIMA and NARANN models, it was shown that this novel data-driven hybrid model did a better job of capturing the dynamic changing trends of the target data than the others used in this work. Our proposed mixture technique can be deemed as a helpful policy-supportive tool to plan and provide medical supplies effectively. The overall confirmed cases and deaths were estimated to reach around 176,570 [95% uncertainty level (UL) 173,607 to 178,476] and 3454 (95% UL 3384 to 3487), respectively, in South Africa, along with 32,136 (95% UL 31,568 to 32,641) and 788 (95% UL 775 to 804) in Nigeria on 12 July 2020 using this data-driven EEMD-ARIMA-NARANN hybrid technique. The contributions of this study include three aspects. First, the proposed hybrid model can better capture the dynamic dependency characteristics compared with the individual models. Second, this new data-driven hybrid model is constructed in a more reasonable way relative to the traditional mixture model. Third, this proposed model may be generalized to estimate the epidemic patterns of COVID-19 in other regions.

Time series analysis of foodborne diseases during 2012–2018 in Shenzhen, China

The present study aimed to use the autoregressive integrated moving average (ARIMA) model to forecast foodborne disease incidence in Shenzhen city and help guide efforts to prevent foodborne disease. The data of foodborne diseases in Shenzhen comes from the infectious diarrhea surveillance network, community foodborne disease surveillance network, and student foodborne disease surveillance network. The incidence data from January 2012 to December 2017 was used for the model-constructing, while the data from January 2018 to December 2018 was used for the model-validating. The mean absolute percentage error (MAPE) was used to assess the performance of the model. The monthly foodborne disease incidence from January 2012 to December 2017 in Shenzhen was between 954 and 32,863 with an incidence rate between 4.77 and 164.32/100,000 inhabitants. The ARIMA (1,1,0) was an adequate model for the change in monthly foodborne disease incidence series, yielding a MAPE of 5.34%. The mathematical formula of the ARIMA (1,1,0) model was (1 − B) × log(incidencet) = 0.04338 + εt/(1 + 0.51106B). The predicted foodborne disease incidences in the next three years were 635,751, 1,069,993, 1,800,838, respectively. Monthly foodborne disease incidence in Shenzhen were shown to follow the ARIMA (1,1,0) model. This model can be considered adequate for predicting future foodborne disease incidence in Shenzhen and can aid in the decision-making processes.

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.

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

Objective

The high morbidity, complex seasonality, and recurring risk of hand-foot-and-mouth disease (HFMD) exert a major burden in China. Forecasting its epidemic trends is greatly instrumental in informing vaccine and targeted interventions. This study sets out to investigate the usefulness of an advanced exponential smoothing state space framework by combining Box-Cox transformations, Fourier representations with time-varying coefficients and autoregressive moving average (ARMA) error correction (TBATS) method to assess the temporal trends of HFMD in China.

Methods

Data from January 2009 to December 2019 were drawn, and then they were split into two segments comprising the in-sample training data and out-of-sample testing data to develop and validate the TBATS model, and its fitting and forecasting abilities were compared with the most frequently used seasonal autoregressive integrated moving average (SARIMA) method.

Results

Following the modelling procedures of the SARIMA and TBATS methods, the SARIMA (1,0,1)(0,1,1)₁₂ and TBATS (0.024, {1,1}, 0.855, {<12,4>}) specifications were recognized as being the optimal models, respectively, for the 12-step ahead forecasting, along with the SARIMA (1,0,1)(0,1,1)₁₂ and TBATS (0.062, {1,3}, 0.86, {<12,4>}) models as being the optimal models, respectively, for the 24-step ahead forecasting. Among them, the optimal TBATS models produced lower error rates in both 12-step and 24-step ahead forecasting aspects compared to the preferred SARIMA models. Descriptive analysis of the data showed a significantly high level and a marked dual seasonal pattern in the HFMD morbidity.

Conclusion

The TBATS model has the capacity to outperform the most frequently used SARIMA model in forecasting the HFMD incidence in China, and it can be recommended as a flexible and useful tool in the decision-making process of HFMD prevention and control in China.

Forecasting the Tuberculosis Incidence Using a Novel Ensemble Empirical Mode Decomposition-Based Data-Driven Hybrid Model in Tibet, China

Objective

The purpose of this study is to develop a novel data-driven hybrid model by fusing ensemble empirical mode decomposition (EEMD), seasonal autoregressive integrated moving average (SARIMA), with nonlinear autoregressive artificial neural network (NARNN), called EEMD-ARIMA-NARNN model, to assess and forecast the epidemic patterns of TB in Tibet.

Methods

The TB incidence from January 2006 to December 2017 was obtained, and then the time series was partitioned into training subsamples (from January 2006 to December 2016) and testing subsamples (from January to December 2017). Among them, the training set was used to develop the EEMD-SARIMA-NARNN combined model, whereas the testing set was used to validate the forecasting performance of the model. Whilst the forecasting accuracy level of this novel method was compared with the basic SARIMA model, basic NARNN model, error-trend-seasonal (ETS) model, and traditional SARIMA-NARNN mixture model.

Results

By comparing the accuracy level of the forecasting measurements including root-mean-square error, mean absolute deviation, mean error rate, mean absolute percentage error, and root-mean-square percentage error, it was shown that the EEMD-SARIMA-NARNN combined method produced lower error rates than the others. The descriptive statistics suggested that TB was a seasonal disease, peaking in late winter and early spring and a trough in autumn and early winter, and the TB epidemic indicated a drastic increase by a factor of 1.7 from 2006 to 2017 in Tibet, with average annual percentage change of 5.8 (95% confidence intervals: 3.5–8.1).

Conclusion

This novel data-driven hybrid method can better consider both linear and nonlinear components in the TB incidence than the others used in this study, which is of great help to estimate and forecast the future epidemic trends of TB in Tibet. Besides, under present trends, strict precautionary measures are required to reduce the spread of TB in Tibet.

Use of meteorological parameters for forecasting scarlet fever morbidity in Tianjin, Northern China

The scarlet fever incidence has increased drastically in recent years in China. However, the long-term relationship between climate variation and scarlet fever remains contradictory, and an early detection system is lacking. In this study, we aim to explore the potential long-term effects of variations in monthly climatic parameters on scarlet fever and to develop an early scarlet-fever detection tool. Data comprising monthly scarlet fever cases and monthly average climatic variables from 2004 to 2017 were retrieved from the Notifiable Infectious Disease Surveillance System and National Meteorological Science Center, respectively. We used a negative binomial multivariable regression to assess the long-term impacts of weather parameters on scarlet fever and then built a novel forecasting technique by integrating an autoregressive distributed lag (ARDL) method with a nonlinear autoregressive neural network (NARNN) based on the significant meteorological drivers. Scarlet fever was a seasonal disease that predominantly peaked in spring and winter. The regression results indicated that a 1 °C increment in the monthly average temperature and a 1-h increment in the monthly aggregate sunshine hours were associated with 17.578% (95% CI 7.674 to 28.393%) and 0.529% (95% CI 0.035 to 1.025%) increases in scarlet fever cases, respectively; a 1-hPa increase in the average atmospheric pressure at a 1-month lag was associated with 12.996% (95% CI 9.972 to 15.919%) decrements in scarlet fever cases. Based on the model evaluation criteria, the best-performing basic and combined approaches were ARDL(1,0,0,1) and ARDL(1,0,0,1)-NARNN(5, 22), respectively, and this hybrid approach comprised smaller performance measures in both the training and testing stages than those of the basic model. Climate variability has a significant long-term influence on scarlet fever. The ARDL-NARNN technique with the incorporation of meteorological drivers can be used to forecast the future epidemic trends of scarlet fever. These findings may be of great help for the prevention and control of scarlet fever.

Predictive study of tuberculosis incidence by time series method and Elman neural network in Kashgar, China

OBJECTIVES

Kashgar, located in Xinjiang, China has a high incidence of tuberculosis (TB) making prevention and control extremely difficult. In addition, there have been very few prediction studies on TB incidence here. We; therefore, considered it a high priority to do prediction analysis of TB incidence in Kashgar, and so provide a scientific reference for eventual prevention and control.

DESIGN

Time series study.

SETTING KASHGAR, CHINA

Kashgar, China.

METHODS

We used a single Box-Jenkins method and a Box-Jenkins and Elman neural network (ElmanNN) hybrid method to do prediction analysis of TB incidence in Kashgar. Root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE) were used to measure the prediction accuracy.

RESULTS

After careful analysis, the single autoregression (AR) (1, 2, 8) model and the AR (1, 2, 8)-ElmanNN (AR-Elman) hybrid model were established, and the optimal neurons value of the AR-Elman hybrid model is 6. In the fitting dataset, the RMSE, MAE and MAPE were 6.15, 4.33 and 0.2858, respectively, for the AR (1, 2, 8) model, and 3.78, 3.38 and 0.1837, respectively, for the AR-Elman hybrid model. In the forecasting dataset, the RMSE, MAE and MAPE were 10.88, 8.75 and 0.2029, respectively, for the AR (1, 2, 8) model, and 8.86, 7.29 and 0.2006, respectively, for the AR-Elman hybrid model.

CONCLUSIONS

Both the single AR (1, 2, 8) model and the AR-Elman model could be used to predict the TB incidence in Kashgar, but the modelling and validation scale-dependent measures (RMSE, MAE and MAPE) in the AR (1, 2, 8) model were inferior to those in the AR-Elman hybrid model, which indicated that the AR-Elman hybrid model was better than the AR (1, 2, 8) model. The Box-Jenkins and ElmanNN hybrid method therefore can be highlighted in predicting the temporal trends of TB incidence in Kashgar, which may act as the potential for far-reaching implications for prevention and control of TB.

Comparison of ARIMA model and XGBoost model for prediction of human brucellosis in mainland China: a time-series study

OBJECTIVES

Human brucellosis is a public health problem endangering health and property in China. Predicting the trend and the seasonality of human brucellosis is of great significance for its prevention. In this study, a comparison between the autoregressive integrated moving average (ARIMA) model and the eXtreme Gradient Boosting (XGBoost) model was conducted to determine which was more suitable for predicting the occurrence of brucellosis in mainland China.

DESIGN

Time-series study.

SETTING

Mainland China.

METHODS

Data on human brucellosis in mainland China were provided by the National Health and Family Planning Commission of China. The data were divided into a training set and a test set. The training set was composed of the monthly incidence of human brucellosis in mainland China from January 2008 to June 2018, and the test set was composed of the monthly incidence from July 2018 to June 2019. The mean absolute error (MAE), root mean square error (RMSE) and mean absolute percentage error (MAPE) were used to evaluate the effects of model fitting and prediction.

RESULTS

The number of human brucellosis patients in mainland China increased from 30 002 in 2008 to 40 328 in 2018. There was an increasing trend and obvious seasonal distribution in the original time series. For the training set, the MAE, RSME and MAPE of the ARIMA(0,1,1)×(0,1,1)₁₂ model were 338.867, 450.223 and 10.323, respectively, and the MAE, RSME and MAPE of the XGBoost model were 189.332, 262.458 and 4.475, respectively. For the test set, the MAE, RSME and MAPE of the ARIMA(0,1,1)×(0,1,1)₁₂ model were 529.406, 586.059 and 17.676, respectively, and the MAE, RSME and MAPE of the XGBoost model were 249.307, 280.645 and 7.643, respectively.

CONCLUSIONS

The performance of the XGBoost model was better than that of the ARIMA model. The XGBoost model is more suitable for prediction cases of human brucellosis in mainland China.

Comparing the performance of time series models with or without meteorological factors in predicting incident pulmonary tuberculosis in eastern China

Background

Many studies have compared the performance of time series models in predicting pulmonary tuberculosis (PTB), but few have considered the role of meteorological factors in their prediction models. This study aims to explore whether incorporating meteorological factors can improve the performance of time series models in predicting PTB.

Methods

We collected the monthly reported number of PTB cases and records of six meteorological factors in three cities of China from 2005 to 2018. Based on this data, we constructed three time series models, including an autoregressive integrated moving average (ARIMA) model, the ARIMA with exogenous variables (ARIMAX) model, and a recurrent neural network (RNN) model. The ARIMAX and RNN models incorporated meteorological factors, while the ARIMA model did not. The mean absolute percentage error (MAPE) and root mean square error (RMSE) were used to evaluate the performance of the models in predicting PTB cases in 2018.

Results

Both the cross-correlation analysis and Spearman rank correlation test showed that PTB cases reported in the study areas were related to meteorological factors. The predictive performance of both the ARIMA and RNN models was improved after incorporating meteorological factors. The MAPEs of the ARIMA, ARIMAX, and RNN models were 12.54%, 11.96%, and 12.36% in Xuzhou, 15.57%, 11.16%, and 14.09% in Nantong, and 9.70%, 9.66%, and 12.50% in Wuxi, respectively. The RMSEs of the three models were 36.194, 33.956, and 34.785 in Xuzhou, 34.073, 25.884, and 31.828 in Nantong, and 19.545, 19.026, and 26.019 in Wuxi, respectively.

Conclusions

Our study revealed a possible link between PTB and meteorological factors. Taking meteorological factors into consideration increased the accuracy of time series models in predicting PTB, and the ARIMAX model was superior to the ARIMA and RNN models in study settings.

The long-term effects of meteorological parameters on pertussis infections in Chongqing, China, 2004-2018

Evidence on the long-term influence of climatic variables on pertussis is limited. This study aims to explore the long-term quantitative relationship between weather variability and pertussis. Data on the monthly number of pertussis cases and weather parameters in Chongqing in the period of 2004-2018 were collected. Then, we used a negative binomial multivariable regression model and cointegration testing to examine the association of variations in monthly meteorological parameters and pertussis. Descriptive statistics exhibited that the pertussis incidence rose from 0.251 per 100,000 people in 2004 to 3.661 per 100,000 persons in 2018, and pertussis was a seasonal illness, peaked in spring and summer. The results from the regression model that allowed for the long-term trends, seasonality, autoregression, and delayed effects after correcting for overdispersion showed that a 1 hPa increment in the delayed one-month air pressure contributed to a 3.559% (95% CI 0.746-6.293%) reduction in the monthly number of pertussis cases; a 10 mm increment in the monthly aggregate precipitation, a 1 °C increment in the monthly average temperature, and a 1 m/s increment in the monthly average wind velocity resulted in 3.641% (95% CI 0.960-6.330%), 19.496% (95% CI 2.368-39.490%), and 3.812 (95% CI 1.243-11.690)-fold increases in the monthly number of pertussis cases, respectively. The roles of the mentioned weather parameters in the transmission of pertussis were also evidenced by a sensitivity analysis. The cointegration testing suggested a significant value among variables. Climatic factors, particularly monthly temperature, precipitation, air pressure, and wind velocity, play a role in the transmission of pertussis. This finding will be of great help in understanding the epidemic trends of pertussis in the future, and weather variability should be taken into account in the prevention and control of pertussis.

Forecasting the epidemiological trends of COVID-19 prevalence and mortality using the advanced α-Sutte Indicator

Forecasting the epidemics of the diseases is very valuable in planning and supplying resources effectively. This study aims to estimate the epidemiological trends of the coronavirus disease 2019 (COVID-19) prevalence and mortality using the advanced α-Sutte Indicator, and its prediction accuracy level was compared with the most frequently adopted autoregressive integrated moving average (ARIMA) method. Time-series analysis was performed based on the total confirmed cases and deaths of COVID-19 in the world, Brazil, Peru, Canada and Chile between 27 February 2020 and 30 June 2020. By comparing the prediction reliability indices, including the root mean square error, mean absolute error, mean error rate, mean absolute percentage error and root mean square percentage error, the α-Sutte Indicator was found to produce lower forecasting error rates than the ARIMA model in all data apart from the prevalence testing set globally. The α-Sutte Indicator can be recommended as a useful tool to nowcast and forecast the COVID-19 prevalence and mortality of these regions except for the prevalence around the globe in the near future, which will help policymakers to plan and prepare health resources effectively. Also, the findings of our study may have managerial implications for the outbreak in other countries.

Estimating the Prevalence and Mortality of Coronavirus Disease 2019 (COVID-19) in the USA, the UK, Russia, and India

Objective

The aim of this study is to apply the advanced error-trend-seasonal (ETS) framework to forecast the prevalence and mortality series of COVID-19 in the USA, the UK, Russia, and India, and the predictive performance of the ETS framework was compared with the most frequently used autoregressive integrated moving average (ARIMA) model.

Materials and Methods

The prevalence and mortality data of COVID-19 in the USA, the UK, Russia, and India between 20 February 2020 and 15 May 2020 were extracted from the WHO website. Then, the data subsamples between 20 February 2020 and 3 May 2020 were treated as the training horizon, and the others were used as the testing horizon to construct the ARIMA models and the ETS models.

Results

Based on the model evaluation criteria, the ARIMA (0,2,1) and ETS (M,MD,N), sparse coefficient ARIMA (0,2,(1,6)) and ETS (A,AD,M), ARIMA (1,1,1) and ETS (A,MD,A), together with ARIMA (2,2,1) and ETS (A,M,A) specifications were identified as the preferred ARIMA and ETS models for the prevalence data in the USA, the UK, Russia, and India, respectively; the ARIMA (0,2,1) and ETS (M,A,M), ARIMA (0,2,1) and ETS (M,A,N), ARIMA (0,2,1) and ETS (A,A,N), coupled with ARIMA (0,2,2) and ETS (M,M,N) specifications were selected as the optimal ARIMA and ETS models for the mortality data in these four countries, respectively. Among these best-fitting models, the ETS models produced smaller forecasting error rates than the ARIMA models in all the datasets.

Conclusion

The ETS framework can be used to nowcast and forecast the long-term temporal trends of the COVID-19 prevalence and mortality in the USA, the UK, Russia, and India, and which provides a notable performance improvement over the most frequently used ARIMA model. Our findings can aid governments as a reference to prepare for and respond to the COVID-19 pandemic both in restricting the transmission of the disease and in lowering the disease-related deaths in the upcoming days.

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.

Prediction of nosocomial infection incidence in the Department of Critical Care Medicine of Guizhou Province with a time series model

Background

The Department of Critical Care Medicine has the highest risk of nosocomial infection. This study used an autoregressive integrated moving average (ARIMA) model to simulate the prevalence of nosocomial infections in the Department of Critical Care Medicine of Guizhou Province. We also provided a policy basis for the prevention and control of hospital infection in the Department of Critical Care Medicine of Guizhou Province.

Methods

The data of ventilator-associated pneumonia, vascular catheter-related bloodstream infections, and urinary tract intubation-related urinary tract infections in nine tertiary A comprehensive treatment hospitals in Guizhou province from January 2014 to December 2019 were collected. The ARIMA time series model was used to evaluate the model fitting and prediction effects.

Results

After comparison, in the Department of Critical Care Medicine of Guizhou Province, the unsurpassed model of ventilator-associated pneumonia was the ARIMA (0,1,1) model, with a residual Ljuing-Box Q test result of Q=10.832 (P=0.865), suggesting it is a white noise sequence and its simulation and prediction effects are beneficial. The best model of vascular catheter-related bloodstream infection was the ARIMA (0,0,1) model, with a residual Ljuing-Box Q test result of Q=14.914 (P=0.602). These results suggest that it is a white noise sequence, and its simulation and prediction effects are sufficient. The optimal model of urinary tract intubation-related urinary tract infection is ARIMA (1,0,0), and the residual Ljuing-Box Q test result is Q=15.042 (P=0.592), suggesting it is a white noise sequence with an accurate simulation and prediction effect.

Conclusions

The ARIMA model can accurately simulate and predict nosocomial infection incidence rate in the Department of Critical Care Medicine of Guizhou Province, and can provide a reference for the prevention and control of nosocomial infections.

An Advanced Data-Driven Hybrid Model of SARIMA-NNNAR for Tuberculosis Incidence Time Series Forecasting in Qinghai Province, China

Purpose

Qinghai province has invariably been under an ongoing threat of tuberculosis (TB), which has not only been an obstacle to local development but also hampers the prevention and control process for ending the TB epidemic. Forecasting for future epidemics will serve as the base for early detection and planning resource requirements. Here, we aim to develop an advanced detection technique driven by the recent TB incidence series, by fusing a seasonal autoregressive integrated moving average (SARIMA) with a neural network nonlinear autoregression (NNNAR).

Methods

We collected the TB incidence data between January 2004 and December 2016. Subsequently, the subsamples from January 2004 to December 2015 were employed to measure the efficiency of the single SARIMA, NNNAR, and hybrid SARIMA-NNNAR approaches, whereas the hold-out subsamples were used to test their predictive performances. We finally selected the best-performing technique by considering minimum metrics including the mean absolute error, root-mean-squared error, mean absolute percentage error and mean error rate .

Results

During 2004–2016, the reported TB cases totaled 71,080 resulting in the morbidity of 97.624 per 100,000 persons annually in Qinghai province and showed notable peak activities in late winter and early spring. Moreover, the TB incidence rate was surging by 5% per year. According to the above-mentioned criteria, the best-fitting basic and hybrid techniques consisted of SARIMA(2,0,2)(1,1,0)₁₂, NNNAR(7,1,4)₁₂ and SARIMA(2,0,2)(1,1,0)₁₂-NNNAR(3,1,7)₁₂, respectively. Amongst them, the hybrid technique showed superiority in both mimic and predictive parts, with the lowest values of the measured metrics in both the parts. The sensitivity analysis indicated the same results.

Conclusion

The best-mimicking SARIMA-NNNAR hybrid model outperforms the best-simulating basic SARIMA and NNNAR models, and has a potential application in forecasting and assessing the TB epidemic trends in Qinghai. Furthermore, faced with the major challenge of the ongoing upsurge in TB incidence in Qinghai, there is an urgent need for formulating specific preventive and control measures.

Secular Seasonality and Trend Forecasting of Tuberculosis Incidence Rate in China Using the Advanced Error-Trend-Seasonal Framework

Objective

Tuberculosis (TB) is a major public health problem in China, and contriving a long-term forecast is a useful aid for better launching prevention initiatives. Regrettably, such a forecasting method with robust and accurate performance is still lacking. Here, we aim to investigate its potential of the error-trend-seasonal (ETS) framework through a series of comparative experiments to analyze and forecast its secular epidemic seasonality and trends of TB incidence in China.

Methods

We collected the TB incidence data from January 1997 to August 2019, and then partitioning the data into eight different training and testing subsamples. Thereafter, we constructed the ETS and seasonal autoregressive integrated moving average (SARIMA) models based on the training subsamples, and multiple performance indices including the mean absolute deviation, mean absolute percentage error, root-mean-squared error, and mean error rate were adopted to assess their simulation and projection effects.

Results

In the light of the above performance measures, the ETS models provided a pronounced improvement for the long-term seasonality and trend forecasting in TB incidence rate over the SARIMA models, be it in various training or testing subsets apart from the 48-step ahead forecasting. The descriptive results to the data revealed that TB incidence showed notable seasonal characteristics with predominant peaks of spring and early summer and began to be plunging at on average 3.722% per year since 2008. However, this rate reduced to 2.613% per year since 2015 and furthermore such a trend would be predicted to continue in years ahead.

Conclusion

The ETS framework has the ability to conduct long-term forecasting for TB incidence, which may be beneficial for the long-term planning of the TB prevention and control. Additionally, considering the predicted dropping rate of TB morbidity, more particular strategies should be formulated to dramatically accelerate progress towards the goals of the End TB Strategy.

Forecasting the seasonality and trend of pulmonary tuberculosis in Jiangsu Province of China using advanced statistical time-series analyses

Objective

Forecasting the seasonality and trend of pulmonary tuberculosis is important for the rational allocation of health resources; however, this foresting is often hampered by inappropriate prediction methods. In this study, we performed validation research by comparing the accuracy of the autoregressive integrated moving average (ARIMA) model and the back-propagation neural network (BPNN) model in a southeastern province of China.

Methods

We applied the data from 462,214 notified pulmonary tuberculosis cases registered from January 2005 to December 2015 in Jiangsu Province to modulate and construct the ARIMA and BPNN models. Cases registered in 2016 were used to assess the prediction accuracy of the models. The root mean square error (RMSE), mean absolute percentage error (MAPE), mean absolute error (MAE) and mean error rate (MER) were used to evaluate the model fitting and forecasting effect.

Results

During 2005–2015, the annual pulmonary tuberculosis notification rate in Jiangsu Province was 56.35/100,000, ranging from 40.85/100,000 to 79.36/100,000. Through screening and comparison, the ARIMA (0, 1, 2) (0, 1, 1)₁₂ and BPNN (3-9-1) were defined as the optimal fitting models. In the fitting dataset, the RMSE, MAPE, MAE and MER were 0.3901, 6.0498, 0.2740 and 0.0608, respectively, for the ARIMA (0, 1, 2) (0, 1, 1)₁₂ model, 0.3236, 6.0113, 0.2508 and 0.0587, respectively, for the BPNN model. In the forecasting dataset, the RMSE, MAPE, MAE and MER were 0.1758, 4.6041, 0.1368 and 0.0444, respectively, for the ARIMA (0, 1, 2) (0, 1, 1)₁₂ model, and 0.1382, 3.2172, 0.1018 and 0.0330, respectively, for the BPNN model.

Conclusion

Both the ARIMA and BPNN models can be used to predict the seasonality and trend of pulmonary tuberculosis in the Chinese population, but the BPNN model shows better performance. Applying statistical techniques by considering local characteristics may enable more accurate mathematical modeling.