Our illness insights are created from individual users who have opted in to share their anonymous temperature readings and symptoms. In a conference call with a reporter, Dr. Dalziel and Kinsa’s senior data scientist, Sam Chamberlain, showed twin maps overlaying one another: the first showing where this year’s flu season currently is, and another showing ZIP codes where high fevers are two or three times as common as they ought to be, according to the flu model. Through retail sales and school donations, Kinsa has amassed a user base broadly consistent with the overall. predict the flu season in the United States up to 12 weeks out, before the local government implemented aggressive social distancing orders, The state has since seen a surge in positive COVID-19 cases. The data, which is shared publicly, gives epidemiologists and public health officials a head start when it comes to stopping the spread. Kinsa smart thermometers are designed and built from the ground up to be used with the free Kinsa app. “This is very, very exciting,” said Dr. William Schaffner, a professor of preventive medicine at Vanderbilt University. Kinsa has created an early warning system from their network of connected thermometers that helps public health officials identify where outbreaks of influenza-like illness (ILI) are occurring. Kinsa’s latest map of fever spikes shows areas that are known to have many cases of Covid-19, the illness caused by the coronavirus. by Donald G. McNeil Jr. NYTimes.com March 18, 2020 “. The company can “see” clusters of fever among its customers instantly, in other words. Figure 3. Epidemiological evidence suggests that women of childbearing age are at higher risk for complications related to the flu, though there is mixed evidence that show that women suffer from higher infection rates than men3. close window. I repeat my question from yesterday: Has Seattle flattened the curve? Company scientists are uniquely positioned to identify unusual clusters of fever because they have years of data for expected flu cases in each ZIP code. One problem with the map is that there’s insufficient data for many counties. This is represented by the trend line that has an R. value of .9. . For example, COVID-19 tests are administered several days after patients first experience symptoms and some test results take a few days to process. If you’re interested in tracking your own illness and contributing to Kinsa’s public health data, you can pre-order one of Kinsa’s thermometers here. This relationship is statistically significant, with a correlation of 0.58. As you can see, the rate of illness is very much atypical — but: That rate is coming down. I checked the other four boroughs of NYC and they’re all following the same trend, atypical but declining back towards typical rates in the past few days. The closer this number is to 1, the higher the correlation. New York is the focus of most of the country’s attention because of the soaring number of positive tests there, but if Kinsa is right then we have a big — big — problem brewing in Florida. The current flu season in Brooklyn is waning as winter ends. These anonymous readings are aggregated and turned into population health insights, which are then shared with the community so that everyone can be better informed about how illness is spreading around them. “We can’t say for sure that these anomalous fever spikes are Covid-19, but we believe this is the earliest signal of where it’s occurring,” Mr. Singh said. Thus, much of Kinsa’s work has focused on providing families with school age children with the tools and knowledge they need to triage symptoms and stop the spread to their broader community. “We’re nervous about putting this out there because we’ve built it so fast,” said Mr. Singh, a former executive at the Clinton Health Access Initiative, which gets medicines to the poor. And now we can too. Within days, testing showed that South Florida had indeed become an epicenter. Kinsa publishes its atypical illness data at healthweather.us. In collaboration with Benjamin Dalziel, Associate Professor at Oregon State University, our data team has shown that they can forecast and, When comparing the cumulative cases of positive COVID-19 with Kinsa’s cumulative atypical illness data, a correlation is seen. The Kinsa site could be a valuable resource, and the more people who use their product, the greater it’ll be. Screenshot of health weather map for March 27, 2020. This is represented by the trend line that has an R2 value of .9. Kinsa The map measures observed illness levels, but Kinsa is clear it's not directly measuring COVID-19 infections. Demand for Kinsa’s smart thermometers has skyrocketed since the coronavirus pandemic began, Mr. Singh said, and the company is now selling 10,000 a day, which is creating production problems but also multiplying the amount of data coming in each day. This chart shows the correlation between Kinsa’s cumulative atypical illness level and the CDC’s cumulative positive cases of COVID-19. Through retail sales and school donations, Kinsa has amassed a user base broadly consistent with the overall US population distribution by age. Because influenza usually produces higher, more protracted fevers than common colds do, the company’s software estimates which ZIP codes appear to be hit by flu rather than by other, milder cold viruses. For the last five years, the company has tracked the flu down to the county level. Kinsa for Families. Nor does the map (yet) have a feature that lets you see growth in atypical illness in real time. By providing more thermometers to these communities, we strive to give the individuals in power the information they need to save lives.