Skip to content
DraconiticResearch
Search Sources API
197,768 studies31 sourcesUpdated 1 h ago
Peer-reviewedCC BY-NC-ND 4.0BMC Infectious Diseases

Predicting hepatitis B incidence trends in China using Baidu Search Index and time series models: a comparative study of rolling forecasting and direct forecasting strategies

  • Xing Yang1
  • Huanzhuo Mai2,3,4
  • Liuyan Lan5
  • Wudi Wei4,6
  • Yulan Xie2,3,4
  • Tingyan Luo2,3,4
  • Zhuoxin Li2,3,4
  • Wei Shi1
  • Jiegang Huang2,3,4
  • Langhuan Lei1
6 affiliations
  1. 1Research Center, People’s Hospital of Guangxi Zhuang Autonomous Region and Guangxi Academy of Medical Sciences, 6, Taoyuan Road, Nanning, Guangxi 530021 China
  2. 2School of Public Health, Guangxi Medical University, 22, Shuangyong Road, Nanning, Guangxi 530021 China
  3. 3Key Laboratory of Prevention and Control of Highly Prevalent Diseases, Education Department of Guangxi Zhuang Autonomous Region, Guangxi Medical University, Nanning, Guangxi China
  4. 4Guangxi Key Laboratory of AIDS Prevention and Treatment, Guangxi Medical University, Nanning, Guangxi China
  5. 5Office of Hospital Quality and Safety Management Committee, People’s Hospital of Guangxi Zhuang Autonomous Region and Guangxi Academy of Medical Sciences, Nanning, Guangxi China
  6. 6Guangxi-ASEAN Collaborative Innovation Center for Major Disease Prevention and Treatment, Life Sciences Institute, Guangxi Medical University, Nanning, Guangxi China
Read full textDOICite

Abstract

Background: Time series models are extensively used for predicting infectious disease incidence through direct time series forecasting, and the Baidu Search Index (BSI) has recently been employed as a reference for analyzing disease trends. However, for predicting the hepatitis B incidence in China, it is essential to explore the most suitable models and forecasting methods, as well as the effectiveness of using BSI.

Methods: Data from the Chinese Center for Disease Control and Prevention, spanning January 2011 to December 2023, were used. Twelve models, including autoregressive integrated moving average (ARIMA), four deep learning models, and seven machine learning models were constructed to predict the reported incidence of hepatitis B in China. BSI-derived comprehensive search index (CSI) of hepatitis B-related keywords was employed as an exogenous variable for model construction. Both direct time-series forecasting and rolling forecasting were applied to predict the time series data in each model. Models’ predictive accuracy was evaluated using mean absolute percentage error (MAPE), weighted mean absolute percentage error (WMAPE), mean absolute error (MAE), mean square error (MSE), and root mean square error (RMSE), each accompanied by its 95% confidence interval (CI). Statistical significance was assessed using one-sided Diebold-Mariano tests.

Results: The ARIMA(0,1,1)(0,1,1)12 model (WMAPE = 0.0821, 95% CI 0.0512–0.1312) outperformed other models in predicting hepatitis B reported incidence. In the primary split with single-step rolling forecasting, incorporating the CSI improved point-estimate predictive performance for nearly all models forecasting hepatitis B reported incidence, particularly in ARIMAX(1,1,1)(0,1,2)12 (WMAPE 0.0548 vs. 0.0821), CNN (WMAPE 0.0845 vs. 0.1105), LSTM (WMAPE 0.0947 vs. 0.1067), Decision Tree (WMAPE 0.0972 vs. 0.1178), Random Forest (WMAPE 0.0956 vs. 0.1044), AdaBoost (WMAPE 0.0973 vs. 0.1049), and XGBoost (WMAPE 0.0996 vs.0.1039) models. Among these, statistically significant improvements were observed for ARIMA, CNN, and Decision Tree (P < 0.05).

Conclusions: This study provides evidence that ARIMA model demonstrates excellent predictive performance for forecasting hepatitis B incidence trends in China. Additionally, BSI could serve as an effective supplement to traditional surveillance systems by providing real-time contemporaneous information that enhances situational awareness. Furthermore, adopting rolling forecasting might improve predictive accuracy for certain models and in specific contexts.

Supplementary Information: The online version contains supplementary material available at https://doi.org/10.1186/s12879-026-14062-3.

Related

  1. Spatial epidemiology of hepatitis C in Khenchela Province, Algeria: identifying HCV incidence hotspots and implications for regional public health
    Manel Mansouri, Brahim Brahamia, Nabil Mega
    BMC Public HealthPeer-reviewedCC BY-NC-ND 4.0Epidemiology & public healthCrossref
  2. A methodological exploration of monthly incidence rate of hepatitis B in China: a time series and machine learning analysis
    Minquan Guan, Zhouying Hu, Yichen Lin +2
    BMC Public HealthPeer-reviewedCC BY-NC-ND 4.0Epidemiology & public healthCrossref
  3. Meteorological forecasting of respiratory diseases incidence with geospatial and machine learning methods
    Benjamín Arroquia-Cuadros, Ángel Marqués-Mateu, Pablo Fdez-Arroyabe +1
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textPharmacology & toxicologyCrossref
  4. A data-driven approach to hepatitis C forecasting using machine learning and epidemiological models
    Abdul Mannan, Jamshaid Ul Rahman, Ebraheem Alzahrani +1
    PLOS OnePeer-reviewedCC BY 4.0Full textMicrobiologyNeurosciencePLOS
  5. Trends in hepatitis E virus incidence and seroprevalence in the Netherlands, 1988 to 2025.
    Franke A Quee, Boris M Hogema, Katja van den Hurk +2
    Euro surveillance : bulletin Europeen sur les maladies transmissibles = European communicable disease bulletinPeer-reviewedCC BYFull textGeneral medicineEurope PMCPMC

Cite

BibTeXRIS
BibTeX
@article{yang2026predicting,
  title = {{Predicting hepatitis B incidence trends in China using Baidu Search Index and time series models: a comparative study of rolling forecasting and direct forecasting strategies}},
  author = {Xing Yang and Huanzhuo Mai and Liuyan Lan and Wudi Wei and Yulan Xie and Tingyan Luo and Zhuoxin Li and Wei Shi and Jiegang Huang and Langhuan Lei},
  journal = {BMC Infectious Diseases},
  year = {2026},
  month = jul,
  doi = {10.1186/s12879-026-14062-3},
  url = {https://doi.org/10.1186/s12879-026-14062-3},
  note = {CC BY-NC-ND 4.0},
}
RIS
TY  - JOUR
TI  - Predicting hepatitis B incidence trends in China using Baidu Search Index and time series models: a comparative study of rolling forecasting and direct forecasting strategies
AU  - Xing Yang
AU  - Huanzhuo Mai
AU  - Liuyan Lan
AU  - Wudi Wei
AU  - Yulan Xie
AU  - Tingyan Luo
AU  - Zhuoxin Li
AU  - Wei Shi
AU  - Jiegang Huang
AU  - Langhuan Lei
PY  - 2026
DA  - 2026/07/29
JO  - BMC Infectious Diseases
DO  - 10.1186/s12879-026-14062-3
UR  - https://doi.org/10.1186/s12879-026-14062-3
AB  - Background: Time series models are extensively used for predicting infectious disease incidence through direct time series forecasting, and the Baidu Search Index (BSI) has recently been employed as a reference for analyzing disease trends. However, for predicting the hepatitis B incidence in China, it is essential to explore the most suitable models and forecasting methods, as well as the effectiveness of using BSI.  Methods: Data from the Chinese Center for Disease Control and Prevention, spanning January 2011 to December 2023, were used. Twelve models, including autoregressive integrated moving average (ARIMA), four deep learning models, and seven machine learning models were constructed to predict the reported incidence of hepatitis B in China. BSI-derived comprehensive search index (CSI) of hepatitis B-related keywords was employed as an exogenous variable for model construction. Both direct time-series forecasting and rolling forecasting were applied to predict the time series data in each model. Models’ predictive accuracy was evaluated using mean absolute percentage error (MAPE), weighted mean absolute percentage error (WMAPE), mean absolute error (MAE), mean square error (MSE), and root mean square error (RMSE), each accompanied by its 95% confidence interval (CI). Statistical significance was assessed using one-sided Diebold-Mariano tests.  Results: The ARIMA(0,1,1)(0,1,1)12 model (WMAPE = 0.0821, 95% CI 0.0512–0.1312) outperformed other models in predicting hepatitis B reported incidence. In the primary split with single-step rolling forecasting, incorporating the CSI improved point-estimate predictive performance for nearly all models forecasting hepatitis B reported incidence, particularly in ARIMAX(1,1,1)(0,1,2)12 (WMAPE 0.0548 vs. 0.0821), CNN (WMAPE 0.0845 vs. 0.1105), LSTM (WMAPE 0.0947 vs. 0.1067), Decision Tree (WMAPE 0.0972 vs. 0.1178), Random Forest (WMAPE 0.0956 vs. 0.1044), AdaBoost (WMAPE 0.0973 vs. 0.1049), and XGBoost (WMAPE 0.0996 vs.0.1039) models. Among these, statistically significant improvements were observed for ARIMA, CNN, and Decision Tree (P < 0.05).  Conclusions: This study provides evidence that ARIMA model demonstrates excellent predictive performance for forecasting hepatitis B incidence trends in China. Additionally, BSI could serve as an effective supplement to traditional surveillance systems by providing real-time contemporaneous information that enhances situational awareness. Furthermore, adopting rolling forecasting might improve predictive accuracy for certain models and in specific contexts.  Supplementary Information: The online version contains supplementary material available at https://doi.org/10.1186/s12879-026-14062-3.
SN  - 1471-2334
ER  -