A new study from West Virginia University (WVU) Rockefeller Neuroscience Institute (RNI) uses a wearable device and artificial intelligence (AI) to predict COVID-19 up to 3 days before symptoms occur. The study has been an impressive undertaking involving over 1000 health care workers and frontline workers in hospitals across New York, Philadelphia, Nashville, and other critical COVID-19 hotspots.
The implementation of the digital health platform uses a custom smartphone application coupled with an Ōura smart ring to monitor biometric signals such as respiration and temperature. The platform also assesses psychological, cognitive, and behavioral data through surveys administered through a smartphone application.
We know that wearables tend to suffer from a lack of accuracy, particularly during activity. However, the Ōura ring appears to take measurements while the user is very still, especially during sleep. This presents an advantage as the accuracy of wearable devices greatly improves when the user isn’t moving. RNI noted that the Ōura ring has been the most accurate device they have tested.
Given some of the early warning signals for COVID-19 are fever and respiratory distress, it would make sense that a device able to measure respiration and temperature could be used as an early detector of COVID-19. In fact, we’ve seen a few wearable device companies attempt much of what RNI is doing as well as a few DIY attempts. RNI’s study has probably been the most thorough work released so far, but we’re sure that many more are upcoming.
The initial phase of the study was deployed among healthcare and frontline workers but is now open to the general public. Meanwhile the National Basketball Association (NBA) is coordinating its re-opening efforts using Ōura’s technology.
We hope to see more results emerge from RNI’s very important work. Until then, stay safe Hackaday.
That Oura web page looks terrible on my Brave browser
I hate, hate, hate when people or organizations publish detection systems and do not quite false positive and false negative rates. More often than not it is because one or both of them is not very good. Saying you can predict with “over 90% accuracy” sounds good but is useless (it’s an innumeracy trap).
Consider this. I have a COVID-19 detection system: You have COVID-19 right now. This system is100% accurate in detecting people who are sick. If you don’t like the false alarm rate, try my other system: You don’t have COVID-19 right now. This system is 100% accurate in detecting who are not sick. I can probably improve either system by making a decision based on a random draw from a distribution that roughly matches the mix between infected and uninfected. It might be as good or better than the Ōura based system from the article and cheaper.
Given the massive range of severity of covid19 cases, I also wonder how the device could be effective. For one person, they might not know they have it. (Pretty common for people under 50, quite common for people under 30). For another (say elderly at a nursing home) it’s quite likely to be severe, even life threatening.
I would think that any device looking for covid by detecting what amount to tiny pre-sympoms would need to take this range of symptoms into account somehow, but I don’t know of that would be possible without combining sensor data with demographic data / medical data on the specific patient.
There’s a weird, long-running habit of not publishing pretty important figures about corona and the response surrounding it. I’m not one of those denialists or anything, it’s obviously real and killing a ton of people. It’s just kinda fuckin shady how it’s reported on. Kind of like everything is now.
pretty expensive rings that can only track your pulse when you aren’t doing anything, has to be taken off if you are doing anything significant with your hands, and doesn’t report back your actual temperature…
And yes, as per the post above, ‘90% accuracy’ is a moronic statement – but I couldn’t read the source as the actual report page seems to be down…
That article was from months ago – I suspect if it had gone anywhere we would of heard about it by now…
However effective, or not, this device will be. It is certainly a better way to tackle covid-19 than oppressive civil liberties wrecking lockdowns. Well done the the WVU RNI team for thinking of anti-covid methods which don’t ruin quality of life.
Not to mention will result in the starvation of tens to hundreds of millions of people in the coming years.
https://www.nytimes.com/2020/04/22/world/africa/coronavirus-hunger-crisis.html
Hope everyone feels very warm and fuzzy about believing science or whatever they called this unprecedented, totally un-studied global experiment as if it was the one and only option. Saved a few wealthy first worlders, gonna slaughter millions and millions of the domestic and international poor. And that’s just from hunger. Wait for the wars this all sets off.
But they’ll yell at people who talk about the economy as if it’s this abstract thing that has no effects on people’s lives, because they’re that wealthy and privileged that they can afford to couch it in those terms. I already have more than ten friends and their families who are out on the street. Assholes.
We know how to “cure” economic problems. We may lack the political will to actually do so, (mostly because of the exccessive influence of the wealthy people you criticise above) but we do know how to do it.
What we _don’t_ know, is how to prevent (e.g, vaccinate for) or effectively cure covid19.
So, it makes sense to prioritise avoiding the disease over “saving” the economy.
Except if it has a high false positive rate and causes excessive shutdowns. Alternatively, the false negative rate could be high and the infection rate goes up. In both cases we are back where we started. The most likely scenario is that it is too expensive to be widely adopted to be effective.
The press release (which is the basis of this story7 on HaD) is optimistic. There is not enough information to make a decision, so why make a PR? I think it was a bit irresponsible for the researchers to publish a PR based on a study of 600 medical professionals. Sloppy decision for the PI to allow it.