Many of us are familiar with activity-tracking apps and dedicated pieces of kit such as Fitbit’s wearables. They’re just the tip of the home health monitoring iceberg, however. There are devices that can monitor heart rates, blood pressures and numerous other metrics that can be used to build up a picture of a user’s overall health.
Take, for example, Sleep Number’s range of “smart beds.” You might not think that you need your bed to tell you how well you slept. The fact that you’re rested or tired might give you some indication. However, perceived sleep problems can be difficult for an individual sleeper to view objectively. The smart beds are packed with sensors that can detect the tiniest of motions.
Sensors can measure how well you sleep
Sleep Number Vice President of Science and Research Pete Bils told NPR’s Morning Edition: "The sensors detect any motion of your body. When your heart beats, your body actually presses on the mattress and we pick that up. When you breathe, your chest moves and we pick that up."
The bed sends these numbers and other data to an algorithm and, once the numbers are crunched, it tells you how well you slept. The answer may or may not come as a surprise but is likely to be more accurate than your own feelings based on how clear or fuzzy your head feels. The smart beds can also do other things, such as automatically adjusting to make you more comfortable based on your preferred sleeping positions, detecting snoring and/or elevating your head to prevent snoring, and even heating your feet if they’re cold.
The company has even bigger plans for the beds in the future. Their algorithms are being fed with the anonymised data from users in order to learn and “get smarter” – not the only previously dumb object for which this claim is being made.
"We collect 4 million biometric data points each night from hundreds of thousands of sleepers," said Bils.
"There are signatures that change in your sleep that are indicative of something bigger. We are starting to identify what those changes represent – whether it's a heart issue or a breathing issue or a sleep disorder."
Machine learning still “a work in progress”
University of Bath Data Scientist Lukasz Piwek said that the smart bed algorithm seems like “a work in progress”, however.
"Based on available research, it's difficult to create sophisticated machine learning predictions like sleep apnea or heart rate conditions,” he added.
Clinicians around the world are increasingly issuing patients with diagnosed conditions with equipment that they can use to monitor their own physical wellbeing. Some suggest that extending this idea so that healthy people are also self-monitoring could be hugely valuable in preventing ill-health in the first place.
Partners HealthCare Vice President for Connected Health Dr. Joseph Kvedar envisages "a world where everything is measured, everything is proactive and preventative, and we react to it before you get sick.”
One of the problems lies in motivating healthy people to monitor themselves to any great degree. At-home monitoring is likely to play a bigger part in preventative healthcare going forward, but it doesn’t have all the answers just yet.
