收藏切换
Cyclical characteristics analysis and machine learning based forecasting of viral hepatitis incidence in China
收藏切换
Qing-gang MENG1, Qian-qian WU2, Yi-ting ZHANG2, Xiao-yu LI2, Chao LIU2, 3
Modern Preventive Medicine | 2026, 53(5) : 782 - 787
Less
收藏切换
Modern Preventive Medicine | 2026, 53(5): 782-787
• Epidemiology and Statistical Methods •
Cyclical characteristics analysis and machine learning based forecasting of viral hepatitis incidence in China
Full
Qing-gang MENG1, Qian-qian WU2, Yi-ting ZHANG2, Xiao-yu LI2, Chao LIU2, 3
Affiliations
  • Institute of Science and Technology Innovation, Hebei University, Baoding, Hebei 071000, China
Published: 2026-03-10 doi: 10.20043/j.cnki.MPM.202509171
Outline
收藏切换
Objective

To reveal fluctuation patterns and cyclical characteristics of viral hepatitis incidence in China and to forecast its short-term trend, thereby supporting the optimization of prevention and control strategies.

Methods

Based on the monthly incidence data of viral hepatitis in China from January 2015 to January 2025 by the National Disease Control and Prevention Bureau, this study employed the Census X-13 Seasonal Adjustment Method to analyze the epidemiological patterns and temporal trends of viral hepatitis during this period. The HP filter was applied to dissect the cyclical patterns of incidence.Forecasting was conducted using a machine learning model (long short-term memory, LSTM) and a time-series model(SARIMA), and and the predictive performance of the models was evaluated.

Results

The number of viral hepatitis cases showed an overall increasing trend, with clear seasonal fluctuations observed each year, and the annual peak occurred in March—April. From January 2015 to January 2025, the incidence of viral hepatitis in China was divided into three complete cyclical cycles, with an average cycle length of 40 months. Notably, the amplitude of these cyclical fluctuations was unstable over time.The mean relative prediction errors for the LSTM model and the SARIMA model were 6.37% and 6.71%, respectively. The LSTM model demonstrated lower root mean square error and mean absolute error, indicating superior predictive performance.

Conclusion

Combining cyclical analysis and machine learning models can effectively improve prediction accuracy,contributing to achieving the goal of “Healthy China 2030”.

Viral hepatitis  /  Cyclical characteristics  /  Machine learning
孟庆刚, 武茜茜, 张义婷, 李晓钰, 刘超. 中国病毒性肝炎发病的循环周期特征分析与机器学习模型预测. 现代预防医学, 2026 , 53 (5) : 782 -787 . DOI: 10.20043/j.cnki.MPM.202509171
Qing-gang MENG, Qian-qian WU, Yi-ting ZHANG, Xiao-yu LI, Chao LIU. Cyclical characteristics analysis and machine learning based forecasting of viral hepatitis incidence in China[J]. Modern Preventive Medicine, 2026 , 53 (5) : 782 -787 . DOI: 10.20043/j.cnki.MPM.202509171
Year 2026 volume 53 Issue 5
32
16
Cite this Article
BibTeX
Article Info
doi: 10.20043/j.cnki.MPM.202509171
  • Receive Date:2025-09-13
  • Online Date:2026-11-02
  • Published:2026-03-10
Article Data
Affiliations
History
  • Received:2025-09-13
Funding
Affiliations
    Institute of Science and Technology Innovation, Hebei University, Baoding, Hebei 071000, China
References
Share
https://castjournals.cast.org.cn/joweb/xdyfyx/EN/10.20043/j.cnki.MPM.202509171
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
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
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