MIT Researchers Monitor Sleep With AI, Radio Waves

If you've e'er suffered from a sleep disorder, there's a skilful run a risk you've had to stay overnight in a sleep lab hooked up to a bunch of electrodes and other sensors. Fortunately, researchers at MIT and Massachusetts General Hospital take come up with a manner to diagnose and study sleep bug that doesn't involve uncomfortable sensors connected to your torso.

The researchers use a wireless device most the size of a laptop, which emits low-power radio frequency signals that reflect off a patient's body. Analyzing those waves allows the researchers to remotely measure vital signs similar pulse and breathing rate. They too came upwards with a new AI algorithm that can translate these measurements into sleep stages. During a exam with 25 salubrious volunteers, the system was accurate 80 pct of the time.

"Imagine if your Wi-Fi router knows when you are dreaming, and tin can monitor whether you are having enough deep slumber, which is necessary for memory consolidation," MIT Professor of Electric Engineering science and Computer Science Dina Katabi, who led the report, said in a statement. "Our vision is developing health sensors that will disappear into the groundwork and capture physiological signals and important health metrics, without asking the user to change her behavior in any way."

MIT AI algorithm

The researchers plan to nowadays a paper on their technique at the International Briefing on Machine Learning on Aug. 9. In a statement, MIT graduate pupil Mingmin Zhao, kickoff writer on the paper, said this technique, while offer a more comfortable experience for patients, may also help doctors ameliorate understand sleep problems.

"We don't understand sleep well, and a high fraction of the population has sleep problems," Zhao said. "We have this engineering that, if we can make it piece of work, tin move u.s.a. from a earth where nosotros do sleep studies in one case every few months in the sleep lab to continuous sleep studies in the home."

Going forrad, the researchers program to use this technique to study how Parkinson's disease affects sleep. They also believe the technology could exist used to learn more virtually sleep disorders similar insomnia, sleep apnea, and epileptic seizures that occur during sleep.

"Our device … makes the job of the doctor and the sleep technologist much easier," Katabi said. "They don't have to go through the data and manually label it."

About Angela Moscaritolo

Angela Moscaritolo

Angela Moscaritolo is PCMag's skillful on fitness and smart dwelling products. Educational activity yoga for nearly 10 years has helped her in evaluating a range of connected health products including fitness trackers, center rate monitors, rowers, smart scales, stationary bikes, force training machines, treadmills, and more. Angela also tests smart dwelling devices from her ranch in Florida, including air purifiers, kitchen appliances, and robot vacuums, just to name a few.