Researchers have analysed web searches to help pinpoint areas where Covid-19 outbreaks could be developing.
Internet search data could form part of early Covid-19 response efforts by simply tracking Google search keywords. Publishing findings to Mayo Clinic Proceedings, researchers found strong correlations between keyword searches on Google Trends and Covid-19 outbreaks in parts of the US.
In some cases, these correlations were observed up to 16 days prior to the first reported cases in states.
As part of the study, 10 keywords were tracked:
- Covid symptoms
- Coronavirus symptoms
- Sore throat, shortness of breath, fatigue and cough
- Coronavirus testing centre
- Loss of smell
- 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,” said Dr Mohamad Bydon, principal investigator at the Mayo Clinic’s Neuro-Informatics Lab.
“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.”
Cannot rely on media coverage
Bydon said that the use of such analytics is important as an adjunct for data science teams who are attempting to predict outbreaks and new hot spots in a pandemic.
“If you wait for the hot spots to emerge in the news media coverage, it will be too late to respond effectively,” Bydon said. “In terms of national preparedness, this is a great way of helping to understand where future hot spots will emerge.”
Data science is playing a significant role in various efforts to trace and diagnose the novel coronavirus, SARS-CoV2. In July, one such data science breakthrough was revealed by a team of University of Oxford scientists.
In a pre-print paper, the team revealed Curial AI, a test using AI that can rapidly screen for Covid-19 in patients arriving in emergency departments. In initial testing, its two early-detection models were able to identify Covid-19 from lab tests, blood gas and vital signs in 115,394 emergency presentations and 72,310 admissions to hospital.