Google Trends as a method to predict new COVID-19 cases

ABSTRACT In this paper, we develop a method that can detect and predict the emergence of new cases of COVID-19 at an early stage. With this method, we try to lay the empirical basis for the development of the model of digital monitoring and prediction of the occurrence of new cases of COVID-19 in Croatia, relying on the analytical tool Google Trends (GT). Results In Croatia search activities using GT for terms such as ‘‘PCR +Covid”, “PCR + test”, and symptoms “cough + corona”, “pneumonia + corona”; “muscle pain + corona” correlate strongly with officially reported cases of the disease. Google Trends tools are suitable for predicting the emergence of new COVID-19 cases in Croatia, and that the data collected by this method correlate with official data. The benefit of this method is reliable estimates that can enable public health officials to prepare and better respond to the possible return of a pandemic in certain parts of the country. If a region experiences an early, sharp increase in Covid-19-like-illness Google searches, it may be possible to focus additional resources on that region to identify the etiology of the outbreak, providing extra medical capacity or raising local media awareness as necessary. Because the relative frequency of certain queries is highly correlated with the percentage of physician visits in which a patient presents with Covid-19 symptoms, this method can serve as an early alarm to predict the emergence of new cases of COVID-19 in the specific area in Croatia.