Abstract
INTRODUCTION: Mathematical models have been used to obtain long-term forecasts of the COVID-19 epidemic. METHODS: The daily COVID-19 case count in two Brazilian states was used to show the potential limitations of long-term forecasting through the application of a mathematical model to the data. RESULTS: The predicted number of cases at the end of the epidemic and at the moment that the peak occurs, is highly dependent on the length of the time series used in the predictive model. CONCLUSIONS: Predictions obtained during the course of the COVID-19 pandemic need to be viewed with caution.