September 23, 2022
Parkinson’s disease is the fastest growing neurological disease, currently affecting more than 10 million people worldwide, yet clinicians still face significant challenges in tracking its severity. A home device has now been developed that can assess the progression of the condition between clinic visits.
Image: N. Fuller, SayoStudio
Clinicians typically assess patients by testing motor and cognitive function during clinic visits. These semi-subjective measurements are often distorted by external factors. Perhaps the patient is tired after the long drive to the hospital. More than 40% of her Parkinson’s patients do not receive care from a neurologist or Parkinson’s specialist because they are too far from urban areas or have difficulty moving.
To address these issues, researchers such as MIT have demonstrated home devices that can monitor patient movement and walking speed. It can be used to assess the severity of Parkinson’s disease, disease progression, and patient response to medication.
Roughly the size of a Wi-Fi router, the device passively collects data using wireless signals that bounce off a patient’s body as they move around the home. Patients do not need to wear gadgets or change their behavior. (For example, recent research has shown that this type of device can be used to detect Parkinson’s disease from breathing patterns in sleeping people.)
Researchers used these devices to conduct a one-year home study of 50 participants. They use machine learning algorithms to analyze large amounts of passively collected data (more than 200,000 walking speed measurements) to help clinicians assess Parkinson’s disease progression and medication response in regular clinic visits. We have shown that it can be tracked more effectively than evaluation in .
“We can have a device at home that can monitor patients and remotely inform doctors about disease progression and how patients are responding to medications, so they can be cared for even when they are unable to come to the hospital. Clinics – now they have real and reliable information – that actually goes a long way toward improving equity and access.
This work utilizes a radio device previously developed in the Katabi lab that analyzes radio signals bouncing off the human body. It uses a fraction of your Wi-Fi router’s power to transmit the signal. These ultra-low power signals do not interfere with other wireless devices in your home. Radio signals pass through walls and other solids, but are reflected back to humans by the moisture in their bodies.
This creates a “human radar” that can track the movement of people in a room. Radio waves always travel at the same speed, so the length of time it takes for a signal to reflect off a device indicates a person’s movement.
The device incorporates a machine-learning classifier that can detect precise radio signals reflected from patients, even when other people are moving around the room. Sophisticated algorithms use these motion data to calculate walking speed (how fast a person is walking).
The device works in the background and runs all day, every day, so it can collect an enormous amount of data. Researchers wanted to see if machine learning could be applied to these datasets to gain insight into disease over time.
They recruited 50 participants, 34 of whom had Parkinson’s disease, and conducted a one-year study of gait measurements at home. Throughout the study, researchers collected over 200,000 individual measurements of her, which were averaged to smooth out variability due to conditions unrelated to health status. disease. (For example, a patient may rush to respond to an alarm or walk slowly while talking on the phone.)
They used statistical methods to analyze the data and found that walking speed at home could be used to effectively track the progression and severity of Parkinson’s disease. For example, people with Parkinson’s disease were shown to lose walking speed almost twice as fast as those without.
“By continuously monitoring patients as they move around the room, we were able to accurately measure their walking speed. We were able to see small differences in ,” says Zhang.
Better, Faster Results
Drilling down on these variability provided some key insights. For example, researchers have shown that daily fluctuations in patients’ walking speed correspond to their response to medication. Walking speed may improve after medication and begin to decline after a few hours as the medication wears off.
“This allows you to objectively measure how your mobility responds to medication. It was very cumbersome to do,” says Liu.
Clinicians can use these data to adjust dosage more effectively and accurately. This is especially important because drugs used to treat the symptoms of the disease can cause serious side effects if the patient takes too much.
Researchers were able to demonstrate statistically significant results on Parkinson’s disease progression in just 50 people studied for one year. In contrast, an oft-cited study by the Michael J. Fox Foundation involved more than 500 individuals and was monitored for more than five years, says Katabi.
“For pharma and biotech companies looking to develop treatments for this disease, this could significantly reduce the burden and costs and accelerate the development of new treatments,” she adds.
Katabi attributes much of the research’s success to a dedicated team of scientists and clinicians who worked together to tackle the many challenges encountered along the way. For one, the research began before the Covid-19 pandemic, so his team members first visited people’s homes to set up the devices. When that became impossible, they developed an easy-to-use phone app to allow participants to remotely assist in deploying devices at home.
Over the course of the study, they learned to automate the process and reduce effort, especially for participants and the clinical team.
This knowledge has proven useful in deploying the device in home studies of other neurological diseases such as Alzheimer’s disease, ALS and Huntington’s disease. They also explored how these methods could be used in combination with other research from the Katavi Institute showing that Parkinson’s disease can be diagnosed by monitoring respiration to help diagnose and follow up the disease earlier. We would like to collect a comprehensive set of markers that we can use. and handle it.
“This radio sensor will allow us to move more care (and research) out of the hospital and into the home where it is most wanted and needed,” said Professor of Neurology at the University of Rochester Medical Center. , says Ending co-author Ray Dorsey. Parkinson’s disease, and co-author of this research paper.
“We are just beginning to see the possibilities. We are getting closer to diagnosing and predicting disease at home. In the future, events such as falls and heart attacks can be predicted and ideally prevented.” maybe.”