Mayo Clinic Research: Google Web Searches Help Predict COVID-19 Spread
A new Mayo Clinic study demonstrates the value of web-based analytics being able to predict the spread of infectious disease. The research specifically indicates the value of analyzing Google web searches for keywords related to COVID-19, according to officials from the Rochester, Minn.-based health system.
Strong correlations were found between keyword searches on the internet search engine Google Trends and COVID-19 outbreaks in parts of the U.S., according to the study published in Mayo Clinic Proceedings. 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 Mohamad Bydon, M.D., a Mayo Clinic neurosurgeon and principal investigator at Mayo's Neuro-Informatics Laboratory.
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, Mayo researchers said.
"The Neuro-Informatics team is focused on analytics for neural diseases and neuroscience. However, when the novel coronavirus emerged, my team and I directed resources toward better understanding and tracking the spread of the pandemic," said. Bydon, the study's senior author. "Looking at Google Trends data, we found that we were able to identify predictors of hot spots, using keywords, that would emerge over a six-week timeline."
The study specifically 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 center
- Loss of smell
- Lysol
- Antibody
- Face mask
- Coronavirus vaccine
- COVID stimulus check
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," explained 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."
Mayo researchers believe the use of web search surveillance data is important as an adjunct for data science teams who are attempting to predict outbreaks and new hot spots in a pandemic. "Any delay in information could lead to missed opportunities to improve preparedness for an outbreak in a certain location," said Bydon.
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 when data is released and public health decisions are being made.
"If you wait for the hot spots to emerge in the news media coverage, it will be too late to respond effectively," Bydon contends. "In terms of national preparedness, this is a great way of helping to understand where future hot spots will emerge."
