Researchers at the MIT Jameel Clinic have developed an artificial intelligence model that can detect Parkinson’s disease simply by reading a person’s breathing patterns. Parkinson’s disease is notoriously difficult to diagnose because it is based primarily on the onset of motor symptoms such as tremors, stiffness and sluggishness, but these symptoms often appear many years after the onset of the disease. The research is led by Professor Dina Katabi, Professor Thuan (1990) and Nicole Pham in the Department of Electrical Engineering and Computer Science at the Massachusetts Institute of Technology and Senior Investigator at the MIT Jameel Clinic, and her team.
The Jameel Clinic is the epicenter of AI and healthcare at MIT. It was co-founded in 2018 by MIT and Community Jameel, an independent global organization advancing science to help communities thrive in a rapidly changing world.
The tool in question is a neural network, a series of connected algorithms that mimic the functioning of a human brain, able to assess whether a person has Parkinson’s disease from their nocturnal breathing. that is, breathing patterns that occur during sleep. The neural network, which was trained by MIT doctoral student Yuzhe Yang and post-doctoral fellow Yuan Yuan, is also able to discern the severity of a person’s Parkinson’s disease and track their disease progression over time. time.
Yang is the first author of a new paper describing the work, published in Nature Medicine. Katabi, who is also affiliated with MIT’s Computer Science and Artificial Intelligence Laboratory and director of the Center for Wireless Networks and Mobile Computing, is the lead author. They are joined by Yuan and 12 colleagues from Rutgers University, University of Rochester Medical Center, Mayo Clinic, Massachusetts General Hospital and Boston University College of Health and Rehabilitation.
Over the years, researchers have investigated the potential for detecting Parkinson’s disease using cerebrospinal fluid and neuroimaging, but these methods are invasive, expensive, and require access to specialized medical centers.
MIT researchers have demonstrated that the AI assessment for Parkinson’s disease can be performed every night at home while the person is sleeping and without touching their body. To do this, the team developed a device that looks like a home Wi-Fi router, but instead of providing internet access, the device emits radio signals, analyzes their reflections on the surrounding environment and extracts the subject’s breathing patterns without any body traces. Contact. The respiratory signal is then transmitted to the neural network to passively assess Parkinson’s disease, and no effort is required on the part of the patient and caregiver.
Katabi said: “A relationship between Parkinson’s disease and respiration was noted as early as 1817, in the work of Dr. James Parkinson. This motivated us to consider the possibility of detecting the disease from the breath without looking at the movements. Some medical studies have shown that respiratory symptoms manifest years before motor symptoms, meaning that respiratory attributes could hold promise for risk assessment prior to the diagnosis of Parkinson’s disease.
“In terms of drug development, the results may enable clinical trials of significantly shorter duration and with fewer participants, ultimately accelerating the development of new therapies. In terms of clinical care, the approach can aid in the assessment of patients with Parkinson’s disease in traditionally underserved communities, including those who live in rural areas and those who have difficulty leaving their homes in due to reduced mobility or cognitive impairment,” added Katabi.
Ray Dorsey, professor of neurology at the University of Rochester and co-author of the paper, said: ‘We have had no therapeutic breakthroughs this century, which suggests that our current approaches to assessing new treatments are suboptimal. We have very limited information on the manifestations of the disease in their natural environment and the device (from Katabi) allows you to get objective and real assessments of how people are doing at home. The analogy I like to make (of current assessments of Parkinson’s disease) is a street lamp at night, and what we see from the street lamp is a very small segment… The completely non-contact sensor (from Katabi) helps us illuminate darkness.