Human-centric AI news and analysis

Here’s how AI can help you sleep

The American Academy of Sleep Medicine has given support to sleeptech

Modern life is turning us into sleep-deprived zombies.

The traditional distractions of jobs, family, and friends have been exacerbated in recent years by irregular work, long commutes, smartphones, and all-night benders — leaving us with little time to snooze. And that’s without mentioning what keeps us up at night, whether it’s drunken revelers in the street, existential angst, or the horrifying screams next door.

It’s therefore unsurprising that two-thirds of adults in developed nations don’t get the nightly eight hours of kip recommended by the World Health Organization, which doctors warn is leading us down a cheery path towards chronic diseases, mental health disorders, and dysfunctional relationships.

But don’t worry my fellow insomniacs, restful nights may soon be on the way. And it’s all thanks to AI of course, the digital age’s panacea/snake oil.

That’s according to the boffins at the American Academy of Sleep Medicine, who believe AI can improve the treatment of sleep disorders.

[Read: If your employees don’t get enough sleep, that’s on you]

In a statement published yesterday, they explain that the vast volumes of data collected through sleep studies are ripe for algorithmic analysis.

The first application they suggest is in polysomnograms tests, which diagnose sleep disorders by analyzing brain waves, oxygen levels in the blood, heart rates, respiration, and eye and leg movements. Adding AI could both streamline the process and unearth new insights that can predict health outcomes.

But they also envision AI transcending the sleep lab to develop personalized treatments.

A growing industry

The American Academy of Sleep Medicine isn’t the first group of academics to support using AI to help you sleep. In 2018, researchers from Stanford University found that a neural network could detect sleep issues more accurately than a human technician.

“Right now [sleep test scoring] is done by technicians, and clearly, there is no reason why it couldn’t be done by a computer,” Dr Emmanuel Mignot, an author of the study and the director of the Stanford Center for Sleep Sciences and Medicine, told the Sleep Review journal last year.

These scientific endorsements will help legitimize the growing list of products using AI to help you sleep.

They include SleepScore, an app that tracks your breathing rate and movements through your smartphone’s microphone and speaker; DREEM, a headband that sends you soporific sounds through bone conduction; HEKA, a smart mattress that adjusts its position when you toss and turn; and Sleep.ai, an armband that detects snoring and then emits a vibration that pushes you onto your side.

Their combined efforts show that there’s a vast range of ways that AI could help you sleep – even if it can’t yet mute the drunks shouting outside your window.

Published March 3, 2020 — 15:43 UTC

Corona coverage

Read our daily coverage on how the tech industry is responding to the coronavirus and subscribe to our weekly newsletter Coronavirus in Context.

For tips and tricks on working remotely, check out our Growth Quarters articles here or follow us on Twitter.