Study on the prediction effect of a combined model of SARIMA and LSTM based on SSA for influenza in Shanxi Province, China

Zhao, Zhiyang; Zhai, Mengmeng; Li, Guohua; Gao, Xuefen; Song, Wenzhu; Wang, Xuchun; Ren, Hao; Cui, Yu; Qiao, Yuchao; Ren, Jiahui; Chen, Limin; Qiu, Lixia

doi:10.1186/s12879-023-08025-1

Cited by 21 publications

(10 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The following one-month data was used as the output for prediction, and the number of nodes in the output layer was set to 1. Since the number of hidden layer nodes has a great impact on the model accuracy, the empirical formula [ 25 ] was used to determine the range of node number M. In this paper, the number of hidden layer nodes was first determined under the condition that the number of hidden layers was fixed as 1. The M calculated by the experimental formula was 5–13.…”

Section: Resultsmentioning

confidence: 99%

A hybrid model for tuberculosis forecasting based on empirical mode decomposition in China

Zhao,

Liu,

Zhao

et al. 2023

BMC Infect Dis

Self Cite

View full text Add to dashboard Cite

Background Pulmonary Tuberculosis is a major public health problem endangering people's health, a scientifically accurate predictive model is of great practical significance for the prevention and treatment of pulmonary tuberculosis. Methods The reported incidence data of pulmonary tuberculosis were from the National Public Health Science Data Center (https://www.phsciencedata.cn/). The ARIMA, LSTM, EMD-SARIMA, EMD-LSTM, EMD-ARMA-LSTM models were established using the reported monthly incidence of tuberculosis reported in China from January 2008 to December 2018. The MSE, MAE, RMSE and MAPE were used to evaluate the performance of the models to determine the best model. Results Comparing decomposition-based single model with undecomposed single model, it was found that: when predicting the incidence trend in the next year, compared with SARIMA model, the MSE, MAE, RMSE and MAPE of EMD-SARIMA decreased by 39.3%, 19.0%, 22.1% and 19.8%, respectively. The MSE, MAE, RMSE and MAPE of EMD-LSTM were reduced by 40.5%, 12.8%, 22.9% and 12.7%, respectively, compared with the LSTM model; Comparing the decomposition-based hybrid model with the decomposition-based single model, it was found that: when predicting the incidence trend in the next year, compared with EMD-SARIMA model, the MSE, MAE, RMSE and MAPE of EMD-ARMA-LSTM model decreased by 21.7%, 10.6%, 11.5% and 11.2%, respectively. The MSE, MAE, RMSE and MAPE of EMD-ARMA-LSTM were reduced by 16.7%, 9.6%, 8.7% and 12.3%, respectively, compared with EMD-LSTM model. Furthermore, the performance of the model were consistent when predicting the incidence trend in the next 3 months, 6 months and 9 months. Conclusion The prediction performance of the decomposition-based single model is better than that of the undecomposed single model, and the prediction performance of the combined model using the advantages of different models is better than that of the decomposition-based single model, so the EMD-ARMA-LSTM combination model can improve the prediction accuracy better than other models, which can provide a theoretical basis for predicting the epidemic trend of pulmonary tuberculosis and formulating prevention and control policies.

show abstract

Section: Resultsmentioning

confidence: 99%

A hybrid model for tuberculosis forecasting based on empirical mode decomposition in China

Zhao,

Liu,

Zhao

et al. 2023

BMC Infect Dis

Self Cite

View full text Add to dashboard Cite

show abstract

“…ILI is a year-round disease burden that causes varying degrees of illness, sometimes leading to hospitalization and death [ 30 ]. However, current time series surveys and projections for ILI in Chongqing are using the national influenza surveillance system [ 9 , 17 , 18 , 31 – 33 ] and are likely to underestimate ILI’s burden on hospital operations. Therefore, in this study, we applied the SARIMAX time series method, which can effectively capture the cyclical and seasonal changes of diseases [ 34 , 35 ], to the personal electronic medical data stored in hospitals for many years, to check the prevalence time and intensity of ILI in Chongqing, so as to predict the medical resources needed by the actual treatment of ILI in hospitals.…”

Section: Discussionmentioning

confidence: 99%

Seasonality of influenza-like illness and short-term forecasting model in Chongqing from 2010 to 2022

Chen,

Xiao

2024

BMC Infect Dis

View full text Add to dashboard Cite

Background Influenza-like illness (ILI) imposes a significant burden on patients, employers and society. However, there is no analysis and prediction at the hospital level in Chongqing. We aimed to characterize the seasonality of ILI, examine age heterogeneity in visits, and predict ILI peaks and assess whether they affect hospital operations. Methods The multiplicative decomposition model was employed to decompose the trend and seasonality of ILI, and the Seasonal Auto-Regressive Integrated Moving Average with exogenous factors (SARIMAX) model was used for the trend and short-term prediction of ILI. We used Grid Search and Akaike information criterion (AIC) to calibrate and verify the optimal hyperparameters, and verified the residuals of the multiplicative decomposition and SARIMAX model, which are both white noise. Results During the 12-year study period, ILI showed a continuous upward trend, peaking in winter (Dec. - Jan.) and a small spike in May-June in the 2–4-year-old high-risk group for severe disease. The mean length of stay (LOS) in ILI peaked around summer (about Aug.), and the LOS in the 0–1 and ≥ 65 years old severely high-risk group was more irregular than the others. We found some anomalies in the predictive analysis of the test set, which were basically consistent with the dynamic zero-COVID policy at the time. Conclusion The ILI patient visits showed a clear cyclical and seasonal pattern. ILI prevention and control activities can be conducted seasonally on an annual basis, and age heterogeneity should be considered in the health resource planning. Targeted immunization policies are essential to mitigate potential pandemic threats. The SARIMAX model has good short-term forecasting ability and accuracy. It can help explore the epidemiological characteristics of ILI and provide an early warning and decision-making basis for the allocation of medical resources related to ILI visits.

show abstract

“…Jainonthee et al [23] used STL to determine the seasonality of two diseases. Zhao et al [24] used STL to analyze influenza seasonality in China, then compared SARIMA, SARIMA-LSTM, and SSA-SARIMA-LSTM models for prediction.…”

Section: Related Workmentioning

confidence: 99%

Temporal Analysis of Infectious Diseases: A Case Study on COVID-19

Liu¹,

Tian²,

Wu³

2023

ATAMS

View full text Add to dashboard Cite

Historically, infectious diseases have greatly impacted human health, necessitating a robust understanding of their trends, processes, and transmission. This study focuses on the COVID-19 pandemic, employing mathematical, statistical, and machine-learning methods to examine its time-series data. We quantify data irregularity using approximate entropy, revealing higher volatility in the U.S., Italy, and India compared to China. We employ the Dynamic Time Warping algorithm to assess regional similarity, finding a strong correlation between the U.S. and Italy. The Seasonal Trend Decomposition using the LOESS algorithm illuminates strong trend degrees in all observed regions, but China's prevention measures show marked effectiveness. These tools, whilst already valuable, still present opportunities for development in both theory and practice.

show abstract

Study on the prediction effect of a combined model of SARIMA and LSTM based on SSA for influenza in Shanxi Province, China

Cited by 21 publications

References 31 publications

A hybrid model for tuberculosis forecasting based on empirical mode decomposition in China

A hybrid model for tuberculosis forecasting based on empirical mode decomposition in China

Seasonality of influenza-like illness and short-term forecasting model in Chongqing from 2010 to 2022

Temporal Analysis of Infectious Diseases: A Case Study on COVID-19

Contact Info

Product

Resources

About