A new artificial intelligence model developed by MIT can make an early detection of Parkinson’s disease — which is notoriously difficult to diagnose — from a person’s breathing patterns, the university announced Monday.
A news release about the technology said Parkinson’s disease is difficult to diagnose because it relies heavily on the onset of motor symptoms, such as tremors, stiffness and slowness, which often appear years after the onset of the disease. .
But Dina Katabi, a professor of electrical engineering and computer science at MIT, and her team have now developed an artificial intelligence model that can detect Parkinson’s disease from a person’s breathing patterns, the release said.
The technology is a neural network – a series of linked algorithms that mimic the way the human brain works – capable of assessing whether someone has Parkinson’s from the way they breathe while they sleep.
The neural network, which was trained by MIT doctoral student Yuzhe Yang and postdoc Yuan Yuan, is also able to discern the severity of someone’s Parkinson’s and track the progression of their disease over time, the release said.
“A relationship between Parkinson’s and breathing was noted as early as 1817, in the work of Dr. James Parkinson. This motivated us to explore the potential of detecting disease from someone’s breath without seeing the movements,” Katabi said in the release.
“Several medical studies have shown that respiratory symptoms appear years before motor symptoms, meaning that respiratory attributes may hold promise for risk assessment prior to Parkinson’s diagnosis.”
Over the years, researchers have tried to detect Parkinson’s using cerebrospinal fluid and neuroimaging, but such methods are invasive, expensive and require access to specialized medical centers, the release said. This makes these methods unsuitable for frequent testing, which could allow early diagnosis and continuous monitoring of disease progression.
But the researchers knew that with the new AI model, the detection of Parkinson’s could be done every night at home, while the patient is asleep and without touching his body.
So they developed a device that looks like a Wi-Fi router, but instead of providing Internet access, the device emits radio signals, analyzes reflections from the surrounding environment and monitors the person’s breathing patterns without any physical contact, the release said. The respiratory signal is then fed into the neural network to assess Parkinson’s.
The research team’s algorithm was then tested on 7,687 individuals, including 757 Parkinson’s patients.
The fastest growing neurological disease in the world, Parkinson’s is the second most common neurological disorder, after Alzheimer’s disease, the release said. In the US alone, over a million people live with this disease.
“In terms of clinical care, the approach could help assess Parkinson’s patients in traditionally underserved communities, including those living in rural areas and those with difficulty leaving home due to limited mobility or cognitive impairment, Katabi said in the announcement.
Yang is the first author and Katabi is the senior author of a new paper describing the technology that was published Monday in Nature Medicine. Other authors include researchers from Rutgers University, the University of Rochester Medical Center, the Mayo Clinic, Massachusetts General Hospital and Boston University.
Stay up to date on all the latest news from Boston.com