Kinsa's crowdsourced smart thermometer data now rivals the CDC at tracking flu trends

By Jonah Comstock
04:24 pm

Kinsa is one of the leading digital health companies in the smart thermometer space, but the company’s mission has never been to sell thermometers. Instead, Kinsa has always seen itself as a big data company. With the recent public launch of Kinsa Insights, that aspect of the company is taking center stage.

“The core hypothesis of the company is ‘Could we find a way to communicate with someone who’s just fallen ill to help them and, as a byproduct of that, understand where and when illness is spreading more broadly?” CEO Inder Singh told MobiHealthNews. “It works. It’s super cool and the fidelity of the data is so much even higher than what I expected.”

The company collects aggregated, de-identified data every time a user takes their temperature or their child’s temperature, or interacts with the app, which allows users to self-report symptoms.

Singh says Kinsa waited through two and a half flu seasons to see how the company’s data matched up with the CDC’s flu statistics. Now the company is able to boast an R-Squared of 0.96, which represents an extremely close match to CDC’s data. 

“And we’re getting ours in realtime, while their data streams in over the course of several weeks,” he said. “So we’re getting ours in realtime much earlier than any other data set, except perhaps social media, and certainly it’s more accurate than social media because it’s real illness data. It’s not a proxy from searches or conversations, it’s direct data.”

Kinsa does a few different things with that data. For one thing, the company shares it back with the users it came from. Through a program in schools, parents can see flu trend data for their child’s school specifically. Some top-level data is available at the Kinsa Insights Blog. Larger stakeholders — like health systems and, especially, manufacturers — have to pay for the data.

“People want to understand when the peak of flu season is,” Singh said. “How much more product do I need to produce? How many more antivirals do I need to produce? How much more cold medicine or disinfectants? And you see businesses whose products are highly correlated with illness that are not cold medicines. People buy toothbrushes after they’re ill. Orange juice sales spike in the context of flu. And soup, for example. The national level data, just knowing how intense overall flu season is and when it’s going to peak, that is perhaps the most important data to sell to companies. The local data is more useful to parents, doctors, and others.”

Kinsa has big plans going forward. The company is developing forecasting capabilities so that it can use data not only to describe current flu trends, but predict them as well. And they have aspirations to take their model global.

“I think there’s a big opportunity within the space we’re already in — infectious illness, leading with the thermometer, the first device a person grabs in the home,” Singh said. “So let’s help them and at the same time, let’s refine this system that allows us to know where and when disease is spreading and allows us to communicate that to various different health actors that can respond early. That’s the vision.”


The latest news in digital health delivered daily to your inbox.

Thank you for subscribing!
Error! Something went wrong!