
Researchers have devised a new way to monitor sleep stages without sensors attached to the body. Their device uses an advanced artificial intelligence algorithm to analyze the radio signals around the person and translate those measurements into sleep stages: light, deep, or rapid eye movement (REM). [Image from Christine Daniloff/MIT]
Traditionally, physicians measure sleep disorders through electrodes or other sensors attached to a patient. The new method, however, is a device that uses an advanced artificial intelligence algorithm that analyzes radio signals surrounding a patient and translates those signals into the light, deep and rapid eye movement (REM) sleep stages.
“Imagine if your WiFi router knows when you are dreaming and can monitor whether you are having enough deep sleep, which is necessary for memory consolidation,” said Dina Katabi, leader of the study, in a press release. “Our vision is developing health sensors that will disappear into the background and capture physiological signals and important health metrics without asking the user to change her behavior in any way.”
Katabi and her team recently used wireless signals and sensors to help diagnose cognitive decline and cardiac disease. The same sensors were used for the sleep disorder study. A wireless device about the size of a laptop emits low-power radio frequency signals that bounce off of a person’s body. The slight movement of the body changes the frequency of the waves and the waves can be an indicator of vital signs like pulse and breathing rate.
“It’s a smart WiFi-like box that sits in the home and analyzes these reflections and discovers all of these changes in the body through a signature that the body leaves on the RF signal,” Katabi said.
Katabi suggested that the sensors from her previously developed WiGait could be useful for monitoring sleep, which typically has to be done in a sleep lab while a patient is hooked up to different machines.
“The opportunity is very big because we don’t understand sleep well and a high fraction of the population has sleep problems,” said Mingmin Zhao, an MIT graduate student and the study’s first author. “We have this technology that, if we can make it work, can move us from a world where we do sleep studies once every few months in the sleep lab to continuous sleep studies in the home.”
One of the most common sleep disorders is sleep apnea. Sleep apnea occurs when there is a pause in breaking or shortness of breath while sleeping. According to the American Sleep Apnea Association, about 22 million Americans are living with sleep apnea.
To reach their goal, the researchers had to develop an algorithm that could translate their measurements from the radio waves into sleep stages. The artificial intelligence algorithm was based on deep neural networks that can help eliminate unnecessary information. The researchers claim that their algorithm is able to be used in different locations with different people without the need for calibration.
“The surrounding conditions introduce a lot of unwanted variation in what you measure. The novelty lies in preserving the sleep signal while removing the rest,” said Tommi Jaakkola, one of the authors of the study.
The researchers tested their algorithm in 25 healthy volunteers and they found that it was 80% accurate.
“Our device allows you not only to remove all of these sensors that you put on the person, and make it a much better experience that can be done at home, it also makes the job of the doctor and sleep technologist much easier,” Katabi said. “They don’t have to go through the data and manually label it.”
Katabi and her team also trained the algorithms to bounce off of objects in the room and only measure the data that people provide.
They hope to use the technology to study how Parkinson’s disease relates to sleep.
“When you think about Parkinson’s, you think about it as a movement disorder, but the disease is also associated with very complex sleep deficiencies, which are not very well understood,” Katabi said.
The research team also suggests that the algorithm could be used to study the sleep changes that come with Alzheimer’s disease and other sleep disorders.
[Want to stay more on top of MDO content? Subscribe to our weekly e-newsletter.]