收藏切换
Comparison of SARIMA and its combined models in predicting the incidence of hand foot and mouth disease
收藏切换
PDF
Li-xia SONG1, Wen-hai LU2, Zhen ZHANG1, Yan LU1, Qiu-ying LV1, Yan-peng CHENG1, 3, Zhi-gao CHEN1
Modern Preventive Medicine | 2025, 52(8) : 1490 - 1496
Less
收藏切换
Modern Preventive Medicine | 2025, 52(8): 1490-1496
Disease Control and Prevention
Comparison of SARIMA and its combined models in predicting the incidence of hand foot and mouth disease
Full
Li-xia SONG1, Wen-hai LU2, Zhen ZHANG1, Yan LU1, Qiu-ying LV1, Yan-peng CHENG1, 3, Zhi-gao CHEN1
Affiliations
  • Department of Infectious Disease Control, Shenzhen Center for Disease Control and Prevention, Shenzhen,Guangdong 518055, China
Published: 2025-04-25 doi: 10.20043/j.cnki.MPM.202411104
Outline
收藏切换
Objective

To compare the prediction effect of SARIMA and its combined models on the incidence of hand foot and mouth disease (HFMD), and to explore the influence of COVID-19 on the SARIMA model.

Methods

The incidence trend of HFMD in Shenzhen was analyzed through the time series decomposition method. A SARIMA model was established based on the monthly incidence of HFMD from 2011 to 2023. The optimal model was selected by comparing the performance of MAE, MSE, RMSE, and MAPE, and was used to construct a combined model with the SVR model and the XGBoost model. The incidence from January to July 2024 was predicted using the optimal model.

Results

The incidence trend of HFMD in Shenzhen from 2011 to 2023 was seasonal, and the peak was from May to June and September to October each year. The SARIMA model that did not include incidence data during the COVID-19 pandemic outperformed the included model. Based on MAE, MSE and RMSE indicators, the combined model performed better than the single SARIMA model when the prediction time exceeded 4 months. The SARMI-SVR model wassuperior to the SARMI-XGBoost model in overall performance, especially in the performance of MAPE.

Conclusion

Including the incidence data during the COVID-19 epidemic will degrade the performance of the SARIMA model. The prediction effect of SARMI-SVR model is better than SARIMA model and SARMI-XGboost model, which can be used to predict the incidence of HFMD and provide a reference for disease surveillance and early warning.

Hand foot and mouth disease  /  SARIMA model  /  SVR model  /  XGBoost model  /  Prediction
Li-xia SONG, Wen-hai LU, Zhen ZHANG, Yan LU, Qiu-ying LV, Yan-peng CHENG, Zhi-gao CHEN. Comparison of SARIMA and its combined models in predicting the incidence of hand foot and mouth disease[J]. Modern Preventive Medicine, 2025 , 52 (8) : 1490 -1496 . DOI: 10.20043/j.cnki.MPM.202411104
Year 2025 volume 52 Issue 8
PDF
64
30
Cite this Article
BibTeX
Article Info
doi: 10.20043/j.cnki.MPM.202411104
  • Receive Date:2024-11-05
  • Online Date:2026-03-17
  • Published:2025-04-25
Article Data
Affiliations
History
  • Received:2024-11-05
Funding
Affiliations
    Department of Infectious Disease Control, Shenzhen Center for Disease Control and Prevention, Shenzhen,Guangdong 518055, China
References
Share
https://castjournals.cast.org.cn/joweb/xdyfyx/EN/10.20043/j.cnki.MPM.202411104
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT