Prediction of the COVID-19 infectivity and the sustainable impact on public health under deep learning algorithm

Weiwei Wang; Jinghui Cai; Jiali Xu; Yuxiang Wang; Yulin Zou

doi:10.1007/s00500-021-06142-0

Prediction of the COVID-19 infectivity and the sustainable impact on public health under deep learning algorithm

Soft comput. 2023;27(5):2695-2704. doi: 10.1007/s00500-021-06142-0. Epub 2021 Aug 21.

Authors

Weiwei Wang¹, Jinghui Cai², Jiali Xu³, Yuxiang Wang⁴, Yulin Zou⁵

Affiliations

¹ College of Media and International Culture, Zhejiang University, Hangzhou, 310058 China.
² College of Information Science and Technology, Jinan University, Guangzhou, 510000 China.
³ School of Mathematics, Shanghai University of Finance and Economics, Shanghai, 200433 China.
⁴ Whiting School of Engineering, Johns Hopkins University, Baltimore, 21218 USA.
⁵ The Third Clinical Medical College of China Three Gorges University, Gezhouba Central Hospital of Sinopharm, Yichang, 443002 China.

Abstract

The aim is to explore the development trend of COVID-19 (Corona Virus Disease 2019) and predict the infectivity of 2019-nCoV (2019 Novel Coronavirus), as well as its impact on public health. First, the existing data are analyzed through data pre-processing to extract useful feature factors. Then, the LSTM (Long-Short Term Memory) prediction model in the deep learning algorithm is used to predict the epidemic situation in Hubei Province, outside Hubei nationwide, and the whole country, respectively. Meanwhile, the impact of intervention time changes on the epidemic situation is compared. The results show that the prediction results are almost consistent with the actual values. Specifically, Hubei Province abolishes quarantine restrictions after the Spring Festival holiday, and the first COVID-19 peak is reached in late February, while the second COVID-19 peak has been reached in early March. Finally, the cumulative number of diagnoses reaches 85,000 cases, with an increase of 15,000 cases compared with the nationwide cases outside Hubei under the continuous implementation of prevention and control measures. Under the prediction of the proposed LSTM model, if the nationwide implementation of prevention and control interventions is postponed by 5 days, the epidemic will peak in early March, and the cumulative number of diagnoses will be about 200,000; and if the intervention measures are implemented five days earlier, the epidemic will peak in mid-February, with a cumulative number of diagnoses of approximately 40,000. Meanwhile, the proposed LSTM model predicts the RMSE values of the epidemic situation in Hubei Province, outside Hubei nationwide, and the whole country as 34.63, 75.42, and 50.27, respectively. Under model comparison analysis, the prediction error of the proposed LSTM model is small and has better applicability over similar algorithms. The results show that the LSTM model is effective and has high performance in infectious disease prediction, and the research results can provide scientific and effective references for subsequent related research.

Keywords: 2019-nCoV; Deep learning algorithm; Infectivity; Prediction model; Public health.