Faux Router Could Detect Parkinson’s Painlessly Just From Patients’ Breathing
It’s often said that Parkinson’s disease is one of the most difficult to diagnose, with symptoms tending to only show up years after the illness has taken root.
Scientists have suggested using cerebrospinal fluid and neuroimaging as possible tests, though those methods are invasive, prohibitively expensive, and require access to specialized medical equipment that would be unsuitable for frequent appointments.
But what if an artificial intelligence (AI) model could detect the onset of the disease just from monitoring one’s breathing patterns?
That’s what Dina Katabi and Nicole Pham from the Department of Electrical Engineering and Computer Science (EECS) at MIT set out to prove when they developed a neural network that could assess if an individual was stricken with Parkinson’s based on their nocturnal breathing.
Comprising a series of algorithms that mimic the human brain, the AI model collects data when a patient is asleep, and can even track the progression and determine the severity of the disease over time.
The best part? This entire process is non-invasive, with the researchers demonstrating that the neural network could overlook the patient every night at home without having to come into contact with their body.
Instead, the device is disguised as a home Wi-Fi router, but instead of broadband, it emits radio signals that analyze the reflections bouncing off the surrounding environment, and collects data on the patient’s breathing patterns from afar.
The signals are then fed to the AI network which will detect for Parkinson’s passively, requiring no input or effort from the subject or caregiver at all.
“A relationship between Parkinson’s and breathing was noted as early as 1817, in the work of Dr James Parkinson. That motivated us to consider the potential of detecting the disease from one’s breathing without looking at movements,” Katabi explained.
“Some medical studies have shown that respiratory symptoms manifest years before motor symptoms, meaning that breathing attributes could be promising for risk assessment prior to Parkinson’s diagnosis,” she added.
With the disease now being the fastest-growing neurological condition in the world, just second most common behind Alzheimer’s, this study could potentially have an important impact on drug development and clinical care.
Other than allowing clinical trials to be held for shorter durations and with fewer participants, the approach could help assess patients in underserved communities, those living in rural areas, or those unable to leave home due to limited mobility or cognitive decline.
“We have very limited information about manifestations of the disease in their natural environment and [Katabi’s] device allows you to get objective, real-world assessments of how people are doing at home,” quipped Ray Dorsey, Professor of Neurology at the University of Rochester.
“The analogy I like to draw [of current Parkinson’s assessments] is a street lamp at night, and what we see from the street lamp is a very small segment… [Katabi’s] entirely contactless sensor helps us illuminate the darkness.”
