Predicting COVID-19 hot spots


    COVID-19 hotspots

    A recent study demonstrated that Google search trends could help in predicting COVID-19 hot spots.  

    Web-based activity detection tools can play an important role in the early detection of infectious diseases. These internet search behaviour tools may also help in the timely preparedness of health care systems to avoid the adverse consequences of being caught by surprise. In the context of the current pandemic, predicting COVID-19 hot spots could help with health care planning. One of the most prominent tools is Google trend.

    Google trend has proven valuable for correlation assessments and forecasting models of several infectious diseases, including influenza, Middle East respiratory syndrome (MERS), Zika virus, and more.

    A team of scientists led by Dr. Shyam J. Kurian explored whether there is a correlation between keywords searched by the general public in Google and the number of COVID-19 cases in the U.S. on a state-to-state basis. They studied the correlations between the number of new patients from January 22, 2020, to April 6, 2020 and ten keywords.

    The Mayo Clinic Proceedings published the findings of this study.

    The ten keywords that the team studied were:

    • COVID symptoms
    • Coronavirus symptoms
    • Sore throat+shortness of breath+fatigue+cough
    • Coronavirus testing centre
    • Loss of smell
    • Lysol
    • Antibody
    • Face mask
    • Coronavirus vaccine
    • COVID stimulus check

    Among the ten keywords analyzed from Google Trends, face mask, Lysol, and COVID stimulus check had the strongest correlations when looking at the United States as a whole. The authors observed strong correlations up to sixteen days before the first reported cases in some states. This finding demonstrates the feasibility of syndromic surveillance of internet search terms to predict COVID-19 hot spots. This information will enable health care systems to better allocate resources with regards to testing, personal protective equipment, medications, and more.


    Shyam J Kurian, Atiq Ur Rehman Bhatti, Mohammed Ali Alvi, Henry H Ting, Curtis Storlie, Patrick M Wilson, Nilay D Shah, Hongfang Liu, Mohamad Bydon.  Correlations Between COVID-19 Cases and Google Trends Data in the United States: A State-by-State Analysis. Mayo Clin Proc. 2020 Nov;95(11):2370-2381. doi: 10.1016/j.mayocp.2020.08.022. Epub 2020 Aug 20.

    Image by Simon Steinberger from Pixabay 

    Source link



    Please enter your comment!
    Please enter your name here