Can big data beat the flu?

Can Big Data Beat the Flu?

This year’s flu virus is one of the worst in recent history, according to public health data.

As of January 2018, 49 states reported their flu activity as “widespread,” the highest on a scale beginning with “no activity.” The reason for the spike might be that this year’s flu vaccine is not as effective as it has been in years past at preventing infection (though, it may still help prevent flu-related deaths).

Our best defense against the flu and other diseases is the ability of public health organizations to track and understand it. Data about the spread of a disease and its severity can help manage an outbreak when it happens, and can also contribute to developing more effective vaccines. The near-eradication of polio in the United States (and, increasingly, the world) is a commonly-cited example of this process in action.

According to one San Francisco-based company, the existing methods for gathering disease data aren’t sufficient, so it’s working on a solution in the form of an internet-connected thermometer. The five-year-old company has created a number of these “smart” thermometer products designed to aggregate individual thermometer measurements and put them to work in understanding the spread of contagious diseases on a national (and maybe one day, global) scale.

Powering A Real-Time Understanding of DiseaseCan big data beat the flu?

Kinsa was founded on the idea that data science can help solve macro-level health issues.

Erin Koehler, Kinsa’s VP of Product and one of the company’s founders, explains: “There’s a thermometer in every family’s household. What if we could connect that thermometer to the cloud to build intelligence on fever, the primary indicator for contagious illness? If we could map and aggregate that data, we would have a real-time understanding of how illness is spreading.”

While some strategies do exist to track the spread of contagious diseases, Koehler says they are fraught with problems. One method gathers information about the flu by testing individual samples from hospitals around the country.

“This introduces weeks of delay. By the time the data is out, the disease has already moved on,” Koehler says. Another popular method to track the spread of the flu is through social media analysis or search-based tools that track keyword activity. These are also problematic because the searches, though they may contain the keyword “fever,” don’t always indicate a real illness.

Kinsa’s solution addresses these issues head-on, by gathering real-time data directly from the source—people who are sick—to create a picture of the nation’s health. The approach was validated in a recent study that found Kinsa’s approach significantly improves flu forecasting.

This year, the company reports it has thermometers in over 500,000 U.S. homes, and receives 25,000 readings daily. Kinsa suggests the incidence of the flu has increased over the course of January 2018.

Kinsa Illness by County, Jan. 1 – Feb. 12 from Kinsa on Vimeo.

A Business Model Built on Data

The latest Kinsa thermometer is a Bluetooth device that works like any other oral thermometer. After users take a reading, it is sent to an app on their phone, Can big data beat the flu?which maintains a history for their doctor. But, beyond that, the key is that readings—anonymized but geolocated—are aggregated on Kinsa’s servers and analyzed on a macro scale.

“For example, we can see in a city how many people are taking temperature readings and compare that to another area or to the previous year. We can then use that information to determine if it’s an early flu season, or if there are geographical or other patterns we can understand,” Koehler says.

Kinsa’s business model isn’t focused on profiting from the thermometers themselves—the newest model, launched last month, costs just $20. Instead, the company bases its business around selling anonymous, aggregated flu data to other companies.

“Our clients are cold and flu-related,” says Koehler, “selling cleaning products, soup, or over-the-counter medications. They all want to understand where and when an illness is spreading so they can be ready for it. So far, the response has been very positive. Companies are getting intelligence they can’t really get anywhere else.”

And while data pays the bills for Kinsa, for Koehler altruism is a clear goal of the company’s activities. From her work in the public health service during the 1990s and early 2000s, studying the spread of HIV and malaria in the developing world, she saw firsthand the kind of impact connected technology can have.

“Over time we want to help arm government and public health entities with this information,” she says. “Eventually we want to get to the point of predicting the spread of illness and improving vaccine production.”


This content is produced by WIRED Brand Lab in collaboration with Western Digital Corporation.

Forward-Looking Statements

Certain blog and other posts on this website may contain forward-looking statements, including statements relating to expectations in the market for our products and applications of our products. These forward-looking statements are subject to risks and uncertainties that could cause actual results to differ materially from those expressed in the forward-looking statements, including development challenges or delays, changes in markets, demand, global economic conditions and other risks and uncertainties listed in Western Digital Corporation’s most recent quarterly and annual reports filed with the Securities and Exchange Commission, to which your attention is directed. Readers are cautioned not to place undue reliance on these forward-looking statements and we undertake no obligation to update these forward-looking statements to reflect subsequent events or circumstances.

Leave a Reply