Parkinson’s disease is the fastest growing neurological disease, now affecting more than 10 million people worldwide, but clinicians still face enormous challenges in tracking its severity and progression.
Clinicians typically assess patients by testing motor skills and cognitive function during clinic visits. These semi-subjective measurements are often skewed by outside factors – perhaps a patient is tired after a long drive to the hospital. More than 40% of people with Parkinson’s disease are never treated by a neurologist or a Parkinson’s disease specialist, often because they live too far from an urban center or have difficulty getting around.
In an effort to address these issues, researchers at MIT and elsewhere have demonstrated a home-based device capable of monitoring a patient’s movement and walking speed, which can be used to assess the severity of Parkinson’s disease. , disease progression and patient response to medication. .
The device, which is about the size of a Wi-Fi router, collects data passively using radio signals that reflect off the patient’s body as they move around their home. The patient does not need to wear a gadget or change their behavior. (A recent study, for example, showed that this type of device could be used to detect Parkinson’s disease from a person’s breathing patterns while they sleep.)
Researchers used these devices to conduct a year-long home study with 50 participants. They showed that by using machine learning algorithms to analyze the treasure trove of data they collected passively (over 200,000 measurements of walking speed), a clinician could track the progression of Parkinson’s disease and drug response more effectively than it would with periodic in-clinic assessments.
“By being able to have a device in the home that can monitor a patient and notify the doctor remotely of the patient’s disease progression and drug response so that they can attend to the patient even if the patient cannot come to the clinic – now they have real, reliable information – which goes a long way to improving equity and access,” says lead author Dina Katabi, Professor Thuan and Nicole Pham in the Department of Electrical Engineering and Computer Science (EECS), and a Principal Investigator at the Computer Science and Artificial Intelligence Laboratory (CSAIL) and MIT Jameel Clinic.
Co-lead authors are EECS graduate students Yingcheng Liu and Guo Zhang. The research is published today in Science Translational Medicine.
A human radar
This work uses a wireless device previously developed in the Katabi lab that analyzes radio signals bouncing off people’s bodies. It transmits signals that use a tiny fraction of the power of a Wi-Fi router – these very low power signals don’t interfere with other wireless devices in the home. As radio signals pass through walls and other solid objects, they are reflected back by humans due to water in our bodies.
This creates a “human radar” that can track a person’s movement in a room. Radio waves always travel at the same speed, so the time it takes for the signals to reflect on the device indicates how the person is moving.
The device incorporates a machine learning classifier that can detect accurate radio signals reflected from the patient even when other people are moving around the room. Advanced algorithms use this motion data to calculate gait speed, i.e. how fast the person is walking.
Because the device runs in the background and works all day, every day, it can collect a massive amount of data. The researchers wanted to see if they could apply machine learning to these datasets to better understand disease over time.
They brought together 50 participants, 34 of whom had Parkinson’s disease, and conducted a year-long study of home walking measures. During the study, the researchers collected more than 200,000 individual measurements which they averaged to smooth out variability due to conditions not relevant to the disease. (For example, a patient may rush to respond to an alarm or walk more slowly when talking on the phone.)
They used statistical methods to analyze the data and found that home walking speed can be used to effectively track the progression and severity of Parkinson’s disease. For example, they showed that walking speed decreased almost twice as fast for people with Parkinson’s disease as for those without.
“Continuous monitoring of the patient as they move around the room allowed us to get very good measurements of their walking speed. And with so much data, we were able to do an aggregation that allowed us to see very small differences,” says Zhang.
Better and faster results
Exploring these variabilities provided key insights. For example, researchers have shown that daily fluctuations in a patient’s walking speed correlate with how they respond to their medications – walking speed may improve after one dose, then start to decrease after a few hours. , as the impact of the drugs fades.
“This allows us to objectively measure how your mobility is responding to your medications. Previously, it was very cumbersome to do because this drug effect could only be measured by asking the patient to keep a diary,” says Liu.
A clinician could use this data to adjust drug dosage more efficiently and accurately. This is particularly important because the drugs used to treat the symptoms of the disease can cause serious side effects if the patient receives too much.
The researchers were able to demonstrate statistically significant results regarding the progression of Parkinson’s disease after studying 50 people for just one year. In contrast, an oft-cited study from the Michael J. Fox Foundation involved more than 500 people and monitored them for more than five years, Katabi says.
“For a pharmaceutical company or a biotechnology company trying to develop drugs for this disease, this could significantly reduce the burden and cost and accelerate the development of new therapies,” she adds.
Katabi credits much of the study’s success to the dedicated team of scientists and clinicians who worked together to tackle the many challenges that arose along the way. For one thing, they started the study before the Covid-19 pandemic hit, so team members first went to people’s homes to install the devices. When that was no longer possible, they developed a user-friendly phone app to remotely assist participants when deploying the device at home.
During the study, they learned to automate processes and reduce effort, especially for participants and the clinical team.
This knowledge will prove useful when looking to deploy devices in home studies of other neurological disorders, such as Alzheimer’s disease, ALS and Huntington’s disease. They also want to explore how these methods could be used, in conjunction with other work from the Katabi lab showing that Parkinson’s disease can be diagnosed by monitoring breathing, to collect a holistic set of markers that could diagnose the disease early and later. be used to track and process it.
“This radio wave sensor may allow more care (and research) to migrate from hospitals to home where it is most wanted and needed,” says Ray Dorsey, professor of neurology at the University of Rochester Medical Center. , co-author of Ending Parkinson’s disease, and co-author of this research paper. “His potential is just beginning to be felt. We are heading towards a day when we can diagnose and predict disease at home. In the future, we may even be able to predict and ideally prevent events like falls and heart attacks. »
This work is supported, in part, by the National Institutes of Health and the Michael J. Fox Foundation.
#Wireless #home #device #tracks #disease #progression #patients #Parkinsons #disease