摘要：Coronavirus disease 2019 (COVID-19) has spread throughout the world. The prediction of the number of cases has become essential to governments’ ability to define policies and take countermeasures in advance. The numbers of cases have been estimated using compartment models of infectious diseases such as the susceptible-infected-removed (SIR) model and its derived models. However, the required use of hypothetical future values for parameters, such as the effective reproduction number or infection rate, increases the uncertainty of the prediction results. Here, we describe our model for forecasting future COVID-19 cases based on observed data by considering the time delay (
t
delay). We used machine learning to estimate the future infection rate based on real-time mobility, temperature, and relative humidity. We then used this calculation with the susceptible-exposed-infectious-removed (SEIR) model to forecast future cases with less uncertainty. The results suggest that changes in mobility affect observed infection rates with 5–10 days of time delay. This window should be accounted for in the decision-making phase especially during periods with predicted infection surges. Our prediction model helps governments and medical institutions to take targeted early countermeasures at critical decision points regarding mobility to avoid significant levels of infection rise.
