Respiratory infectious diseases (e.g., COVID- 19) have brought huge damages to human society, and the accurate prediction of their transmission trends is essential for both the health system and policymakers. Most related studies concentrate on epidemic trend forecasting at the macroscopic level, which ignores the microscopic social interactions among individuals. Meanwhile, current microscopic models are still not able to sufficiently decipher the individual-based spreading process and lack valid quantitative tests. To tackle these problems, we propose an exposure-risk-based model at the microscopic level, including 4 modules: individual movement, virion-laden droplet movement, individual exposure risk estimation, and prediction of new cases. First, the front two modules reproduce the movements of individuals and the droplets of infectors’ expiratory activities. Then, the outputs are fed to the third module for estimating the personal exposure risk. Accordingly, the number of new cases is predicted in the final module. Our model outperforms 4 existing macroscopic or microscopic models through the forecast of new cases of COVID-19 in the United States. Specifically, mean absolute error, root mean square error and mean absolute percentage error by our model are 2454.70, 3170.51, and 3.38% smaller than the minimum results of comparison models, respectively. In sum, the proposed model successfully describes the scenarios from a microscopic perspective and shows great potential for predicting the transmission trends with different scenarios and management policies.
Respiratory infectious diseases (e.g., COVID- 19) have brought huge damages to human society, and the accurate prediction of their transmission trends is essential for both the health system and policymakers. Most related studies concentrate on epidemic trend forecasting at the macroscopic level, which ignores the microscopic social interactions among individuals. Meanwhile, current microscopic models are still not able to sufficiently decipher the individual-based spreading process and lack valid quantitative tests. To tackle these problems, we propose an exposure-risk-based model at the microscopic level, including 4 modules: individual movement, virion-laden droplet movement, individual exposure risk estimation, and prediction of new cases. First, the front two modules reproduce the movements of individuals and the droplets of infectors’ expiratory activities. Then, the outputs are fed to the third module for estimating the personal exposure risk. Accordingly, the number of new cases is predicted in the final module. Our model outperforms 4 existing macroscopic or microscopic models through the forecast of new cases of COVID-19 in the United States. Specifically, mean absolute error, root mean square error and mean absolute percentage error by our model are 2454.70, 3170.51, and 3.38% smaller than the minimum results of comparison models, respectively. In sum, the proposed model successfully describes the scenarios from a microscopic perspective and shows great potential for predicting the transmission trends with different scenarios and management policies.
Respiratory infectious diseases (e.g., COVID- 19) have brought huge damages to human society, and the accurate prediction of their transmission trends is essential for both the health system and policymakers. Most related studies concentrate on epidemic trend forecasting at the macroscopic level, which ignores the microscopic social interactions among individuals. Meanwhile, current microscopic models are still not able to sufficiently decipher the individual-based spreading process and lack valid quantitative tests. To tackle these problems, we propose an exposure-risk-based model at the microscopic level, including 4 modules: individual movement, virion-laden droplet movement, individual exposure risk estimation, and prediction of new cases. First, the front two modules reproduce the movements of individuals and the droplets of infectors’ expiratory activities. Then, the outputs are fed to the third module for estimating the personal exposure risk. Accordingly, the number of new cases is predicted in the final module. Our model outperforms 4 existing macroscopic or microscopic models through the forecast of new cases of COVID-19 in the United States. Specifically, mean absolute error, root mean square error and mean absolute percentage error by our model are 2454.70, 3170.51, and 3.38% smaller than the minimum results of comparison models, respectively. In sum, the proposed model successfully describes the scenarios from a microscopic perspective and shows great potential for predicting the transmission trends with different scenarios and management policies.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.