Each year, over 60,000 Americans are newly diagnosed with Parkinson’s disease (PD)—and that number is growing quickly. In fact, according to the World Health Organization, the prevalence of the neurological disorder has doubled in the past 25 years, and PD-related disability and deaths are “increasing faster than for any other neurological disorder.”
Unfortunately, the path to a Parkinson’s diagnosis can be lengthy and arduous due to a lack of diagnostic tests. That’s why one group of researchers from the Massachusetts Institute of Technology (MIT) is exploring new ways of detecting PD by looking at the way you breathe. Read on to learn about the surprising connection between your nighttime breathing patterns and your Parkinson’s risk—and to find out how the test’s artificial intelligence is pushing the field forward.
READ THIS NEXT: Michael J. Fox Says Having Parkinson’s Is “Nothing” Compared to This.
Parkinson’s disease is a progressive disorder, meaning it worsens over time. Most often it goes undiagnosed until common motor symptoms—tremor, rigidity, shuffling gait, or imbalance, for example—begin to appear. However, experts are increasingly looking at less common clinical manifestations of PD—as well as possible biomarkers—which could help lead to diagnosis sooner.
“A true determination of Parkinson’s disease is a clinical diagnosis, which means certain motor symptoms have to be present, but we now know more about some early signs of Parkinson’s disease that, while they don’t always lead to the condition, are connected,” experts from Johns Hopkins University wrote.
READ THIS NEXT: Neil Diamond Says Parkinson’s Means He Can Never Do This Again.
According to a new study conducted by MIT experts and published in the journal Nature Medicine, there’s a surprising connection between the way you breathe at night and your risk of Parkinson’s disease.
“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,” lead study author Dina Katabi, PhD, Professor of Electrical Engineering and Computer Science (EECS) at MIT told MIT News. “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.”
Researchers collected data on nocturnal breathing patterns from 7,600 people, 757 of whom had known cases of Parkinson’s disease. They then tested an artificial intelligence-based computer model’s ability to diagnose and track PD. They found that when they tracked subjects’ breathing for a period of 12 nights, the program could detect Parkinson’s with 95 percent accuracy.
The test, which could someday be administered from the comfort of one’s home, consists of two key components: a belt worn by the patient at night, and a device that emits radio signals to gather data on the patient’s breathing patterns. “The system extracts nocturnal breathing signals either from a breathing belt worn by the subject, or from radio signals that bounce off their body while asleep. It processes the breathing signals using a neural network to infer whether the person has PD, and if they do, assesses the severity of their PD,” the study authors explained.
Researchers say their findings could be among the best ways to detect Parkinson’s through biomarkers. “The literature has investigated a few potential PD biomarkers, among which cerebrospinal fluid, blood biochemical and neuroimaging have good accuracy. However, these biomarkers are costly, invasive and require access to specialized medical centers and, as a result, are not suitable for frequent testing to provide early diagnosis or continuous tracking of disease progression,” they wrote.
For more health news sent directly to your inbox, sign up for our daily newsletter.
In addition to providing new avenues to diagnosis, the researchers say their testing technology could also help to detect changes in the disease’s progression over time. “The scales currently used to measure disease progression in the clinic are relatively insensitive. They can also provide different results when used by different doctors. Compared with two different scales, the program was better at identifying small changes in Parkinson’s symptoms,” the team explained.
They added that their findings could help speed up clinical trials, ultimately leading to quicker 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.
It’s important to note that more research is needed to determine how effective AI algorithms are in clinical settings. “We need more data,” Katabi acknowledged while speaking to The Washington Post in September. “We have just started to produce these results, and we need more evidence.”