Prediction of pertussis Incidence based on deep learning and traditional time series model: A case study of LSTM and ARIMA
1
Department of Infection Management, Affiliated Hospital of Jiangnan University, Wuxi, China
2
School of public health, Southeast University, Nanjing, China
3
Department of immunization program, the Affiliated Wuxi Center for Disease Control and Prevention of Nanjing Medical University, Wuxi, China
4
East China Normal University, Shanghai, China
Popul. Med. 2026;8(Supplement Supplement 1):
ABSTRACT
OBJECTIVE:
Predict pertussis incidence in Wuxi using ARIMA and LSTM models to assess epidemic trends.
METHODS:
Monthly pertussis incidence data from 2013 to 2022 in Wuxi were used to build the models, and data from January 2023 to November 2024 verified their performance. RMSE and MAE evaluated predictive accuracy, and pertussis incidence from December 2024 to December 2025 was forecasted.
RESULTS:
Pertussis incidence in Wuxi fluctuated seasonally from January 2013 to November 2024, with a high-incidence state since April 2024. Both models fit well, but LSTM outperformed ARIMA, with lower RMSE and MAE. The Wilcoxon signed-rank test showed a significant difference in prediction errors (p = 0.001).
CONCLUSIONS:
The LSTM model better predicts pertussis incidence in Wuxi, offering valuable guidance for surveillance and prevention strategies.
Predict pertussis incidence in Wuxi using ARIMA and LSTM models to assess epidemic trends.
METHODS:
Monthly pertussis incidence data from 2013 to 2022 in Wuxi were used to build the models, and data from January 2023 to November 2024 verified their performance. RMSE and MAE evaluated predictive accuracy, and pertussis incidence from December 2024 to December 2025 was forecasted.
RESULTS:
Pertussis incidence in Wuxi fluctuated seasonally from January 2013 to November 2024, with a high-incidence state since April 2024. Both models fit well, but LSTM outperformed ARIMA, with lower RMSE and MAE. The Wilcoxon signed-rank test showed a significant difference in prediction errors (p = 0.001).
CONCLUSIONS:
The LSTM model better predicts pertussis incidence in Wuxi, offering valuable guidance for surveillance and prevention strategies.
| eISSN: | 2654-1459 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
