What you need to know
- Kinsa has used its smart thermometers to map illness around the U.S.
- The visualization shows fever-related illnesses.
- An atypical uptick in a given region could represent evidence of the coronavirus' spread.
Kinsa, a health-tech company that makes smart thermometers, recently released its "Health Weather Map," which uses data from its thermometers to map the prevalence of fever-inducing sickness across the United States. Take a look at its map of observed illnesses across the country.
While that's a lot of sick people, it's important to note that this is also flu season. So, many of these cases are what you'd expect this time of the year. More telling is the company's map of 'atypical illnesses,' which shows how much higher the rate of illness in a given region is compared to Kinsa's expectations based on previous data:
This data shows an unusually high rate of illnesses in pockets across the nation, with a particular concentration around the U.S. East Coast, as well as Florida.
While the company does not claim that the atypical data points necessarily represent cases of coronavirus, it does suggest that the map could serve as an early warning system for where and how quickly it's spreading.
At least some of the data also seems to match well with known coronavirus cases, with New York and Florida, for example, both reporting high numbers of suspected cases. This is also reflected in Kinsa's atypical illness map. On the other hand, despite the CDC reporting 652 confirmed cases of coronavirus in California at the time of writing, Kinsa's map shows almost nothing out of the ordinary in the Golden State.
"This method holds promise for real-time illness anomaly detection efforts used to identify emerging pandemics and severe flu outbreaks," reads the company's announcement. It hopes that the use of such data can help public health systems more accurately and more quickly track the spread of illnesses, both today and in the future.
You can read a detailed breakdown of the company's technical approach in coming up with this data here.