PARIS: Researchers at the Massachusetts Institute of Technology (MIT) have developed an original and relatively powerful device that can detect signs of Parkinson’s disease in certain individuals during their sleep.
Artificial intelligence analyses the respiratory patterns of patients to discern the potential presence of neurological problems related to this disease.
With this solution, the person being tested doesn’t need to interact with the device or modify their behaviour for it to work.
In fact, the device takes the form of a box hung on the wall. The device will then measure the respiratory activity of the individual during their sleep, before the results are submitted to an artificial intelligence.
The quality of the individual’s nighttime breathing can be measured in two ways, either from radio signals that bounce off their body or from a breathing belt they wear while sleeping.
A neural network, ie, a series of algorithms, is able to deduce whether or not the person has Parkinson’s disease. If the device makes a diagnosis of Parkinson’s, it can even assess the severity, according to the Movement Disorder Society’s (MDS) Unified Parkinson’s Disease Rating Scale.
To date, the research team’s algorithm has been tested on 7,687 people, including 757 Parkinson’s patients, with correct diagnoses in over 85% of cases.
This stress-free, touchless solution could one day represent a significant advance in the detection of this disease when it is optimized and its results are fully reliable.
This research is supported by the National Science Foundation (NSF) and the Michael J Fox Foundation, named for the famous Canadian-American actor who has been afflicted with this degenerative disease since 1991.