Mounting evidence suggests that there is an undetected pool of COVID-19 asymptomatic but infectious cases. Estimating the number of asymptomatic infections has been crucial to understand the virus and contain its spread, which is, however, hard to be accurately counted.
A new study proposes an approach of Machine Learning based fine-grained Simulator (MLSim), which integrates multiple practical factors including disease progress in the incubation period, cross-region population movement, undetected asymptomatic patients, and prevention and containment strength. In this way, interactions among these factors are modeled by virtual transmission dynamics with several undetermined parameters, which are determined from epidemic data by machine learning techniques. When MLSim learns to match the real data closely, it also models the number of asymptomatic patients. MLSim is learned from the open Chinese global epidemic data.
In this way, authors found that only 35% infections were detected in China and 65% infections were asymptomatic and had self-healed ―MLSim assumes that latent infections are currently asymptomatic and if they don’t show ob-vious symptoms and be quarantined in the whole incubation period, they will self-heal―. Authors point to MLSim showed better forecast accuracy than the SEIR and LSTM-based prediction models.
In summary, the simulator revealed the potential great number of undetected asymptomatic infections, which poses a great risk to the virus containment.
Link to the paper: https://doi.org/10.1101/2020.04.19.20068072
Editorial Disclaimer: information published during the 2020 COVID-19 pandemic may be updated frequently to reflect the dynamic nature of current understanding.