AI detects early-stage Parkinson’s disease from breathing patterns

The hands of a man with Parkinson’s disease are shaking. [Astrid860/Getty Images]

Scientists from MIT’s Department of Electrical Engineering and Computer Science (EECS) and the MIT Jameel Clinic have developed an artificial intelligence (AI) tool that can detect early-stage Parkinson’s disease by analyzing respiratory patterns a person. The tool has the potential to significantly improve the diagnosis of this fast-growing neurological disease, which currently relies on the onset of motor symptoms such as tremors, stiffness and sluggishness that do not appear until years later. appearance of the disease.

The research was done in collaboration with the University of Rochester, Mayo Clinic and Massachusetts General Hospital, and is sponsored by the National Institutes of Health.

The team, led by Dina Katabi, a professor at the EECS and a principal investigator at the MIT Jameel Clinic, developed the tool via a neural network capable of discerning the presence of Parkinson’s disease via the nocturnal breathing patterns of a person, the way they breathe while they sleep. The neural network, which was trained by MIT doctoral student Yuzhe Yang and post-doctoral fellow Yuan Yuan, can also diagnose disease severity and track its progress.

“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 one’s breath without looking at the movements,” said Katabi, lead author of the paper, which appears in natural medicine. “Some medical studies have shown that respiratory symptoms manifest years before motor symptoms, which means that respiratory attributes could hold promise for risk assessment before the diagnosis of Parkinson’s disease.”

To collect the data needed to train the AI ​​tool, the MIT team developed a non-invasive, non-touch device that resembles a WiFi router and can be placed in the room where a patient sleeps. To collect breathing patterns without physical contact, the device emits radio signals, analyzes their reflections from the surrounding environment, and then extracts the subject’s breathing patterns. This data is then transmitted to the neural network for analysis, without any task on the part of the patient or caregiver.

The device has the potential to aid in disease diagnosis and is an improvement over some previous efforts that attempted to use cerebrospinal fluid and neuroimaging to detect disease markers. But these methods are both invasive and require patients to have access to specialized medical centers, which makes them impractical for the early iterative tests needed for early diagnosis.

Katabi said the new device has the potential to affect both clinical care and the development of new drugs targeting the disease.

“In terms of drug development, the results may enable clinical trials of significantly shorter duration and fewer participants, ultimately accelerating the development of new therapies,” she noted. “In terms of clinical care, the approach may 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. due to reduced mobility or cognitive impairment.”

According to Ray Dorsey, professor of neurology at the University of Rochester, specialist in Parkinson’s disease and co-author of the article: “We have had no therapeutic breakthroughs in this century, which suggests that our approaches to evaluate new treatments are suboptimal”. He added that the device developed by Katabi’s team fills a gap in previous research on Parkinson’s disease: the lack of data derived from manifestations of the disease in the natural environment.

“The analogy I like to make [of current Parkinson’s assessments] is a street lamp at night,” Dorsey said, “and what we see from the street lamp is a very small segment…[Katabi’s] Completely non-contact sensor helps us light up the darkness.

Leave a Reply