Modified SEIR and AI prediction of the epidemics trend of COVID-19 in China under public health interventions

摘要: Background: The coronavirus disease 2019 (COVID-19) outbreak originating in Wuhan, Hubei province, China, coincided with chunyun, the period of mass migration for annual Spring Festival. To contain its spread, China adopted unprecedented nationwide interventions on January 23 2020. These policies included large-scale quarantine, strict controls travel and extensive monitoring suspected cases. However, it is unknown whether these have had an impact epidemic. We sought to show how control measures impacted containment Methods: integrated population data before after most updated COVID-19 epidemiological into Susceptible-Exposed-Infectious-Removed (SEIR) model derive epidemic curve. also used artificial intelligence (AI) approach, trained 2003 SARS data, predict Results: found that should peak by late February, showing gradual decline end April. A five-day delay implementation would increased size mainland three-fold. Lifting quarantine lead a second province mid-March extend April, result corroborated machine learning prediction. Conclusions: Our dynamic SEIR was effective predicting peaks sizes. 2020 indispensable reducing eventual size.