A new device, developed by researchers at the Massachusetts Institute of Technology (MIT) and Massachusetts General Hospital in the US, has been developed to non-intrusively diagnose and monitor sleep disorders.
The device is designed to avoid attachment of sensors or electrodes to sleep disorder patients in order to prevent further disruption of their sleep.
Using an advanced artificial intelligence (AI) algorithm, the device analyses radio signals around a person and translates them into measurements of sleep stages such as light, deep, or rapid eye movement (REM).
MIT Electrical Engineering and Computer Science professor Dina Katabi said: “Imagine if your Wi-Fi router knows when you are dreaming, and can monitor whether you are having enough deep sleep, which is necessary for memory consolidation.
“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 behaviour in any way.”
The new sleep monitoring technique is based on professor Katabi’s previously developed radio-based sensors.
A wireless device present in these sensors emits low-power radio frequency (RF) that reflect off the body and are altered with any slight body movement.
The researchers further developed the new AI algorithm based on the existing deep neural networks that are used to extract and analyse information from the radio signals received by the sensor.
When testing 25 healthy volunteers, the team found the new device to be 80% accurate with findings that are comparable to those determined using EEG measurements.
The team has also trained their algorithm to ignore wireless signals from other objects in the room and to only capture data from the sleeping person.
Researchers are planning to use the device for assessing the affects of Parkinson’s disease on sleep.
It can also be used to study sleep changes caused by Alzheimer’s disease, insomnia, sleep apnea, as well as epileptic seizures that occur during sleep and are difficult to detect.
Image: The sensors consist of a wireless device, about the size of a laptop computer, that emits low-power radio frequency (RF) signals. Photo: courtesy of Shichao Yue.