Hot Air

Nifty new tool to spot coronavirus outbreaks in U.S. communities early: Smart thermometers

“New tool” is the wrong phrase, I guess. The tool isn’t new. It’s value as an early detection system in the spread of a heretofore unknown deadly pathogen is what’s new.

This is my favorite story of the day. Ed wrote about using smart technology to track coronavirus this morning too, with the feds attempting to gather aggregated data from smartphones to fight COVID-19. That would involve tracking people’s daily movements, “including tracking whether people are keeping one another at safe distances to stem the outbreak,” to try to model the spread of the disease. Neat idea, said Ed, but maybe not something that can be effectively deployed in time to make a difference in this epidemic as opposed to the next one. Besides, the utility of the data would be limited by the fact that we wouldn’t know which smartphone users are sick and which aren’t as they move about.

But what if there were a smart technology that did give us a better idea of who’s sick and who isn’t, and where those people might be? What if that technology was already in sufficiently wide use that the aggregate data might show us where a fever-causing disease is breaking out right now and where it isn’t? What if employees at the company responsible for that tech had a proven track record of catching outbreaks before the CDC does? At a moment when America is effectively flying blind on coronavirus thanks to the testing fiasco, information like that would be very helpful in anticipating where scarce resources should be deployed as the disease gains traction locally.

That technology is already in place. And soon the map of hot spots will be online for everyone to look at.

Kinsa Health has sold or given away more than a million smart thermometers to households in which two million people reside, and thus can record fevers almost as soon as consumers experience them.

For the last few years, Kinsa’s interactive maps have accurately predicted the spread of flu around the United States about two weeks before the Centers for Disease Control and Prevention’s own surveillance tool, the weekly FluView tracker…

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. A sudden spike that far exceeds estimates for flu for a given date may well indicate the coronavirus has arrived

“This is very, very exciting,” said Dr. William Schaffner, a professor of preventive medicine at Vanderbilt University. “This is 21st-century disease surveillance, and we’ve been rooted in the mid-20th century with something very labor intensive.”

Kinsa stays ahead of the CDC because their thermometers relay temperature readings to the company instantly, where they’re automatically logged and aggregated geographically. By contrast, the CDC assembles its info about local outbreaks by aggregating data supplied piecemeal by local doctors and hospitals. According to the Times, Kinsa correctly detected the “double peak” of flu this year and has already apparently detected at least one cluster of coronavirus cases that was unknown at the time (in South Florida) but soon became evident to local authorities. They’re now seeing unusual numbers of fevers for this time of year in certain spots in Florida, Michigan, Arizona and eastern Texas that aren’t — yet — known to be COVID-19 hotspots.

Much smaller communities are already using smart thermometers this way. Here’s a story from a simpler, more innocent time (one month ago) about a school district that’s tracking Kinsa data to spot infections among kids in different grade levels. In a way, the coronavirus project is just scaling that idea up massively. Imagine the increase in efficiency if the feds could deploy precious test kits to areas where the disease is just beginning to take root instead of distributing them blindly across the country in some random manner. This is potentially the sort of thing that’ll return society to a semblance of normalcy, with early detection and targeted isolation of smaller populations while everyone else carries on with daily life with less draconian social distancing measures in place.

Kinsa says it’s going to put its data online, viewable to the public, 48 hours from now at www.healthweather.us. The main audiences for the site are federal and local health officials, obviously, but there should be interest among ordinary people too, to see how close the virus might be to them at a given moment. One potential wrinkle there: If the website catches on, how many people will check it and decide that they don’t need to take precautions if no fevers near them have been logged recently?

If the evidence over the next few weeks proves that this tech really does start detecting hot spots early, the feds should consider purchasing a bunch of thermometers and distributing them to widen the use of the technology. The more data points there are, the better detection gets. (And the more people who have thermometers, the sooner they’ll detect fevers in themselves and opt to self-quarantine.) Oh — and before you ask, yes, of course China is also already using “smart” technology to detect and record fevers in individuals. But as usual, their version of it is decidedly creepier than ours.

Leave a Reply