[Image courtesy of MIT]
Researchers at the Massachusetts Institute of Technology recently developed an artificial intelligence model that can detect Parkinson’s from breathing patterns.
The diagnostic algorithm uses a series of connected algorithms that mimic how a human brain works to analyze whether a patient has Parkinson’s from their sleep breathing patterns. MIT PhD student Yuzhe Yang and postdoc Yuan Yuan also trained the neural network to discern the severity of someone’s Parkinson’s disease (PD) and track the progression of the disease.
In the past, researchers have studied the potential of using cerebrospinal fluid and neuroimaging to detect PD. Still, that method can be invasive, costly and require specialized medical centers, according to the researchers.
MIT’s research team developed a device that looks like a home Wi-Fi router that emits radio signals, analyzes their reflections off the surrounding environment and detects breathing patterns without touching the body. The breathing signals are sent to the neural network that assesses Parkinson’s in a passive manner without help from the patient or caregiver.
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, senior author on the study. “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.”
Parkinson’s disease is the second-most common neurological disorder after Alzheimer’s disease. More than 10 million people around the world are living with PD, according to the Parkinson’s Foundation.
Katabi, the director of the Center for Wireless Networks and Mobile Computing, suggests that the study could provide important implications for PD drug development and clinical care.
“In terms of drug development, the results can enable clinical trials with a significantly shorter duration and fewer participants, ultimately accelerating the development of new therapies. 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,” Katabi said.
The research was performed in a collaboration with the University of Rochester, the Mayo Clinic and Massachusetts General Hospital. It was sponsored by the National Institutes of Health, National Science Foundation and the Michael J. Fox Foundation. The research paper was published in the journal Nature Medicine.