Wearables Can Detect The Flu? Well…Maybe…

flow chart for Assessment of the Feasibility of Using Noninvasive Wearable Biometric Monitoring Sensors to Detect Influenza and the Common Cold Before Symptom Onset paper

Surprisingly there are no pre-symptomatic screening methods for the common cold or the flu, allowing these viruses to spread unbeknownst to the infected. However, if we could detect when infected people will get sick even before they were showing symptoms, we could do a lot more to contain the flu or common cold and possibly save lives. Well, that’s what this group of researchers in this highly collaborative study set out to accomplish using data from wearable devices.

Participants of the study were given an E4 wristband, a research-grade wearable that measures heart rate, skin temperature, electrodermal activity, and movement. They then wore the E4 before and after inoculation of either influenza or rhinovirus. The researchers used 25 binary, random forest classification models to predict whether or not participants were infected based on the physiological data reported by the E4 sensor. Their results are pretty lengthy, so I’ll only highlight a few major discussion points. In one particular analysis, they found that at 36 hours after inoculation their model had an accuracy of 89% with a 100% sensitivity and a 67% specificity. Those aren’t exactly world-shaking numbers, but something the researchers thought was pretty promising nonetheless.

One major consideration for the accuracy of their model is the quality of the data reported by the wearable. Namely, if the data reported by the wearable isn’t reliable itself, no model derived from such data can be trustworthy either. We’ve discussed those points here at Hackaday before. Another major consideration is the lack of a control group. You definitely need to know if the model is simply tagging everyone as “infected” (which specificity does give us an idea of, to be fair) and a control group of participants who have not been inoculated with either virus would be one possible way to answer that question. Fortunately, the researchers admit this limitation of their work and we hope they will remedy this in future studies.

Studies like this are becoming increasingly common and the ongoing pandemic has motivated these physiological monitoring studies even further. It seems like wearables are here to stay as the academic research involving these devices seems to intensify each day. We’d love to see what kind of data could be obtained by a community-developed device, as we’ve seen some pretty impressive DIY biosensor projects over the years.

15 thoughts on “Wearables Can Detect The Flu? Well…Maybe…

  1. Intellectual Property fraud, all smartwatches contain pirated sensor software owned by brand Smart Watch. Many brands passing off selling thousands of counterfeits online and highstreet shops.

  2. Since wearing my Fitbit HR, I noticed when my resting heart rate jumped up by 40 BPM two days before I broke with this trendy new disease going around, after I got over it resting heart rate went back down. Until I actually got sick my raised heart rate was the only symptom!

  3. “…if we could detect when infected people will get sick even before they were showing symptoms, we could do a lot more to contain the flu or common cold and possibly save lives. ”

    Well, I believe if a person is infected they are already sick. But, that could just my amateurish way of looking at it…

    Now, if the end-goal to “contain the flu or common cold” is to get everyone to wear some fitbit-like device that reports their vitals to some central authority (government or otherwise) or raise an alarm in the presence of another device reporting “flu-like symptoms” in its wearer then I must strenuously object. Personal liberty (at least in the US) comes before the mobs paranoid germaphobia.

    1. Have you considered the possibility that some people might not want to contribute to the spread of disease, and would take measures to avoid doing so if they knew they had pre-symptoms?

      It is perfectly possible for such a system to respect an individual’s privacy – once a model had been trained (on volunteer data) all of the user’s data could be evaluated on their own devices, there is no need for telemetry – although one can imagine companies wanting to it to pass information to the tissue-lemsip complex for advertising profit…

      Not everything is a conspiracy, you know.

      1. LOL Training a model? You’re proposing the use of a wearable ML or “AI” device to determine, for a person, whether they’re sick or not? Really? The use of a standard low-tech thermometer doesn’t cut it? OK, so, the wearable tells them they’re sick and they leave the house anyway. What then?

        The misuse of gadgets to monitor and track an individual isn’t science fiction. Facebook? Google? Heck the state of California demands location data from cell providers if they think a subscriber has spent 51% of their time in the state. So they can wring tax money out of them, of course.

        Theorizing the possibility of such a system being misused to the detriment of the individual is hardly a conspiracy theory.

        1. I think you misunderstood me, I am not saying such a system could not be abused: rather, the fact that such systems could exist does not prove they are being misused – I am reasonably sure I alluded to that in my first response.

          Fankly, I would rather you hide in a cabin in the woods because you think the government if planning on coming to take all of your guns, it’s safer for everyone else (at least you won’t spread so many germs)

    2. Yup, there’s the dumb. And this is why we can’t have nice things.

      Being sick sucks. Unfortunately given there are animal reservoirs of many infectious agents in the wild nothing we can do will ever completely eliminate being sick from the human experience.

      But you know, if we did a few simple things like not go out while contagious unless absolutely necessary and if we do try to contain our germs to ourselves… we could reach a minimum unavoidable amount of infection. All of us could enjoy fewer days of sickness.

      But any mention of it and the free-dumb crowd comes out thinking they are all William Wallace, ready to fight and die for their right to spread viri. Somehow they need the liberty to go mingle around others on those specific days that they are contagious in order to pursue their happiness. They can’t take those few days off, stay at home and still consider themselves to be free.

      And no, don’t try to tell me that all those people calling in sick is financially untenable. Study after study has shown that if people would just stay home when they are sick the reduced spread would result in fewer missed working days overall, not more.

      Seriously, why do you people like snot, stomach pains, diarrhea and vomit so much?

  4. There are no pre-flu symptoms? I am not sure about that because in the 1 or 2 days before any physical symptoms, I usually feel depression or euphoria, unusual passage of time, deja vu, confusion and/or feeling like the real world is happening on TV.

  5. The bigger problem is probably that working people would need to have the ability to take off substantial consecutive days from their job to avoid spreading disease. That is a problem for understaffed businesses, but also for workers paid hourly or daily.

    1. Yeah, can you imagine a world where human’s well being is the priority in the society’s organization of developped country ? with this kind of reasoning, you could end up with tax funded universal healthcare and education, social security net, cost of life adjusted minimum wage, paid sick days and m(p)aternity leave, regulated prices on basic necesities such as rent, food, energy, water, transport…

      Yeah, I guess it would be a problem for businesses, but that would be a hell of a hack

Leave a Reply

Please be kind and respectful to help make the comments section excellent. (Comment Policy)

This site uses Akismet to reduce spam. Learn how your comment data is processed.