Development and comparison of predictive models for sexually transmitted diseases—AIDS, gonorrhea, and syphilis in China, 2011–2021

Zhu, Zhixin; Zhu, Xiaoxia; Zhan, Yancen; Gu, Lanfang; Chen, Liang; Li, Xiuyang

doi:10.3389/fpubh.2022.966813

Cited by 11 publications

(8 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, our study differs from the previous findings. Zhu et al ( 33 ) used ARIMA, Elman neural network (ERNN), ARIMA-ERNN hybrid, and long short-term memory (LSTM) models to forecast syphilis in mainland China, and their findings showed that the prediction performance of LSTM outperformed ARIMA, ERNN, and ARIMA-ERNN hybrid models. This may be related to data characteristics and sample size.…”

Section: Discussionmentioning

confidence: 99%

Research of Combined ES-BP Model in Predicting Syphilis Incidence 1982-2020 in Mainland China

Zhao

2023

ijph

View full text Add to dashboard Cite

Background: Syphilis remains a major public health concern in China. We aimed to construct an optimum model to forecast syphilis epidemic trends and provide effective precautionary measures for prevention and control. Methods: Data on the incidence of syphilis between 1982 and 2020 were obtained from the China Health Statistics Yearbook. An exponential smoothing model (ES model) and a BP neural network model were constructed, and on this basis, the ES-BP combination model was created. The prediction performance was assessed to compare the MAE (Mean Absolute Error), MSE (Mean Squared Error), MAPE (Mean Absolute Percentage Error), and RMSE (Root Mean Square Error). Results: The optimum ES model was Brown’s linear trend model, which had the lowest MAE and MAPE values, and its residual was a white noise sequence (P=0.359). The optimum BP neural network model had three layers with the number of nodes in the input, hidden, and output layers set to 5, 11, and 1, and the mean values of MAE, MSE, and RMSE by five-fold cross-validation were 1.519, 6.894, and 1.969, respectively. The ES-BP combination model had three layers, with model nodes 1, 4, and 1. The lowest mean values of MAE, MSE, and RMSE obtained by five-fold cross-validation were 1.265, 5.739, and 2.105, respectively. Conclusion: The ES, BP neural network, and ES-BP combination models can be used to predict syphilis incidence, but the prediction performance of the ES-BP combination model is better than that of a basic ES model and a basic BP neural network model.

show abstract

Section: Discussionmentioning

confidence: 99%

Research of Combined ES-BP Model in Predicting Syphilis Incidence 1982-2020 in Mainland China

Zhao

2023

ijph

View full text Add to dashboard Cite

show abstract

“…If the time series contains significant seasonal characteristics, the model can be identified as a SARIMA model. The SARIMA model is expressed as SARIMA (p, d, q) (P, D, Q)s and can be expressed as [ 26 , 27 ]: where p, q, P, and Q denote the order of auto-regression, the order of moving average, seasonal auto regression lag, and seasonal moving average, respectively. D and d denote the degree of seasonal and degree of trend differences, respectively, and s denotes the length of the seasonal period.…”

Section: Methodsmentioning

confidence: 99%

Research on hand, foot and mouth disease incidence forecasting using hybrid model in mainland China

Zhao¹,

Zhang²,

Zhang

et al. 2023

BMC Public Health

View full text Add to dashboard Cite

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.

show abstract

“…The analysis was completed using Joinpoint 4.9.1.0 software. 16 The optimal Joinpoint model was fitted to assess the annual percent change (APC) and average annual percent change (AAPC) of gonorrhea incidence from 2004 to 2021, with an APC > 0 indicating an increase in the incidence during the study period and APC < 0 indicating the opposite. If there was no connection point during the study period, we assumed that the APC = AAPC, which meant that the overall trend of the data increased or decreased without changes.…”

Section: Methodsmentioning

confidence: 99%

“…The ARIMA model was used to predict the number of gonorrhea cases. 16–18 The model was fitted using 2004–2020 Chinese gonorrhea incidence data as the training set. Then, the autocorrelation and partial autocorrelation plots of the data series were plotted to test whether the data were a smooth time series, and the model was tested for statistical significance by the Ljung – Box test (Q18).…”

Section: Methodsmentioning

confidence: 99%

Analysis and prediction of the incidence and prevalence trends of gonorrhea in China

Chen,

et al. 2023

Human Vaccines & Immunotherapeutics

View full text Add to dashboard Cite

To understand the epidemiological trend of gonorrhea in China from 2004 to 2021, predict the prevalence of the disease, and provide basic theory and data support for monitoring and managing gonorrhea. Gonorrhea incidence data in China from 2004 to 2021 were collected through the China Public Health Science Data Center and National Administration of Disease Prevention and Control, and the incidence and epidemiological characteristics were analyzed. Statistical analysis was performed using Joinpoint and autoregressive integrated moving average (ARIMA) models. A linear correlation model was used to analyze the correlation between gross domestic product (GDP) and the incidence rate. From 2004 to 2021, a total of 2,289,435 cases of gonorrhea were reported in China, with an average reported incidence rate of 9.46/100,000 people and a downward followed by an upward trend. Individuals with gonorrhea were primarily 20–30 y of age, with 1,034,847 cases (53.38%) from 2004 to 2018. The trend of increasing incidence was most obvious in the 10–20 age group (5,811 cases in 2004 to 12,752 cases in 2018, AAPC = 6.1, P < .001). The incidence of gonorrhea in China was negatively correlated with GDP from 2004 to 2021 ( r = -0.547, P = .019). The correlation coefficient between the average incidence growth rate of each region from 2012 to 2018 and the average growth rate of regional GDP was 0.673 ( P < .01). The root mean square error (RMSE) of the ARIMA model was 4.89%, showing powerful performance. There would be 97,910 gonorrhea cases in 2023 as predicted by the model.

show abstract

Development and comparison of predictive models for sexually transmitted diseases—AIDS, gonorrhea, and syphilis in China, 2011–2021

Cited by 11 publications

References 46 publications

Research of Combined ES-BP Model in Predicting Syphilis Incidence 1982-2020 in Mainland China

Research of Combined ES-BP Model in Predicting Syphilis Incidence 1982-2020 in Mainland China

Research on hand, foot and mouth disease incidence forecasting using hybrid model in mainland China

Analysis and prediction of the incidence and prevalence trends of gonorrhea in China

Contact Info

Product

Resources

About