Google searches can predict coronavirus outbreaks weeks in advance, according to new research

Analyzing Google searches for certain keywords predicted regional COVID-19 outbreaks up to 2 weeks in advance, new research finds.

A recent study finds that analyzing Google searches for keywords related to COVID-19 predicts the spread of the disease.

The study, published in Mayo Clinic Proceedings, found strong correlations between Google searches and COVID-19 outbreaks in parts of the U.S. The researchers observed these correlations up to 16 days prior to the first reported cases in some states.

“Our study demonstrates that there is information present in Google Trends that precedes outbreaks,” said Mohamad Bydon, a Mayo Clinic neurosurgeon. “With predictive analysis, this data can be used for better allocating resources with regards to testing, personal protective equipment, medications and more,” he said

Ten crucial Google searches for COVID-19 keywords

The study focused on ten Google searches and phrases: COVID symptoms, Coronavirus symptoms, Coronavirus testing center, loss of smell, Lysol, antibody, face mask, Coronavirus vaccine, COVID stimulus check, and combinations of sore throat+shortness of breath+fatigue+cough.

Most of these keywords had moderate to strong correlations days before the first reports of coronavirus cases in specific areas.

“Each of these keywords had varying strengths of correlation with case numbers,” said Bydon. “If we had looked at 100 keywords, we may have found even stronger correlations to cases.

As the pandemic progresses, people will search for new and different information, so the search terms also need to evolve.”

The keywords face mask, Lysol, and COVID stimulus check had the strongest correlations in the United States as a whole.

They had with R values of 0.88, 0.82, and 0.79 respectively

Tracking COVID-19 keywords faster than traditional methods

Traditional surveillance, including widespread testing and public health reporting, can lag behind the incidence of infectious disease.

The need for more testing, and more rapid and accurate testing, is paramount.

Delayed or incomplete reporting of results can lead to inaccuracies, especially when it comes to public health decisions.

“If you wait for the hot spots to emerge in the news media coverage, it will be too late to respond effectively,” Dr. Bydon says. “In terms of national preparedness, this is a great way of helping to understand where future hot spots will emerge.”

The Mayo Clinic recently introduced an interactive COVID-19 tracking tool that reports the latest data for every county in all 50 states, and in Washington, D.C., with insight on how to assess risk and plan accordingly.

“This study demonstrates that there is information present in Google Trends that precedes outbreaks,” the authors write, “and this data should be utilized to allow for better resource allocation in regard to tests, personal protective equipment, medication, and more.”

Study: Correlations Between COVID-19 Cases and Google Trends Data in the United States: A State by State Analysis
Authors: Mohamad Bydon et al.
Published in: Mayo Clinic Proceedings
Publication date: August 20, 2020
Photo: via Pexels