A wall-mounted device developed at MIT and powered by artificial intelligence can detect Parkinson’s disease from ambient breathing patterns. There is no need for the user to interact with the device or change their behavior in order for it to work. Credit: Photo courtesy of the researchers.
Key Points:
- A new neural network can assess whether or not someone has Parkinson’s from their nocturnal breathing.
- The method is incredibly non-invasive, relying on a home device that looks similar to a Wi-Fi router that takes radio-based readings while the patient is asleep.
- The fastest-growing neurological disease in the world, Parkinson’s is the second-most common neurological disorder, after Alzheimer's disease.
Over the years, researchers have investigated the potential of detecting Parkinson’s using cerebrospinal fluid and neuroimaging, but these methods are invasive, costly and require access to specialized medical centers.
Now, a team of MIT researchers has developed an artificial intelligence model that can detect Parkinson’s from reading a person’s nocturnal breathing patterns. The AI model in combination with a new device can discern the severity of someone’s Parkinson’s disease and track the progression of disease over time.
The model is a neural network, a series of connected algorithms that mimic the way a human brain works. The team also developed a device with the appearance of a Wi-Fi router, but instead of providing internet access, it emits radio signals, analyzes their reflections off the surrounding environment and extracts the subject’s breathing patterns without any contact. The breathing signal is then fed to the neural network to assess Parkinson’s.
With this passive approach, Parkinson’s can be assessed every night at home while a person is asleep— and without touching or taxing their body or mental health.
“A relationship between Parkinson’s and breathing was noted as early as 1817, in the work of Dr. James Parkinson. This motivated us to consider the potential of detecting the disease from one’s breathing without looking at movements,” said Dina Katabi, principal investigator and professor in the department of electrical engineering and computer science at MIT. “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.”
The computer science professor says the results of the study, published in Nature Medicine, could enable significantly shorter clinical trials with fewer participants for Parkinson’s drug development.
“In terms of clinical care, the approach can help in the assessment of Parkinson’s patients in traditionally underserved communities, including those who live in rural areas and those with difficulty leaving home due to limited mobility or cognitive impairment,” said Katabi.
Information provided by MIT.