Google web searches can help predict Covid hotspots: Study
According to the study, published in the journal Mayo Clinic Proceedings, Strong correlations were found between keyword searches on the internet search engine Google Trends and Covid-19 outbreaks in parts of the US.
New York: By analysing Google web searches for keywords related to Covid-19, researchers have said that web-based analytics have demonstrated their value in predicting the spread of the infectious disease.
According to the study, published in the journal Mayo Clinic Proceedings, Strong correlations were found between keyword searches on the internet search engine Google Trends and Covid-19 outbreaks in parts of the US.
These correlations were observed 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, and with predictive analysis, this data can be used for better allocating resources with regards to testing, personal protective equipment, medications and more,” said study author Mohamad Bydon from Mayo Clinic — a health care company in the US.
“Looking at Google Trends data, we found that we were able to identify predictors of hotspots, using keywords, that would emerge over a six-week timeline,” Bydon added.
Several studies have noted the role of internet surveillance in early prediction of previous outbreaks such as H1N1 and Middle East respiratory syndrome.
There are several benefits to using internet surveillance methods versus traditional methods, and this study says a combination of the two methods is likely the key to effective surveillance.
The study searched for 10 keywords that were chosen based on how commonly they were used and emerging patterns on the internet and in Google News at that time.
The keywords were: Covid symptoms, Coronavirus symptoms, sore throat, shortness of breath+fatigue+cough, coronavirus testing centre, loss of smell, antibody, face mask and more.
Most of the keywords had moderate to strong correlations days before the first Covid-19 cases were reported in specific areas, with diminishing correlations following the first case.
“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,” Bydon added.
The use of web search surveillance data is important as an adjunct for data science teams who are attempting to predict outbreaks and new hotspots in a pandemic.
“Any delay in information could lead to missed opportunities to improve preparedness for an outbreak in a certain location,” the authors noted.
