A home monitoring system can help overcome some of the challenges of caring for patients with Parkinson’s disease. Because people with neurological conditions are often elderly and may need assistance with travel, obtaining specialized care at health centers can be difficult. But by installing radio sensors, researchers could track the progression of symptoms and even changes in medication, all without patients leaving the comfort of their homes. The results were described in jurn The science of translational medicine on Wednesday.
Parkinson’s disease is a progressive neurological disorder that affects the whole body, but is best known for its effect on mobility – it often starts with muscle stiffness and can progress to tremors, weakness and other movement disorders. About a million Americans live with the disease, while only 60 percent of Parkinson’s patients on Medicare see a neurologist or other specialist. “We’re asking a lot from the patient community,” says James Beck, chief scientist at the Parkinson’s Foundation, who was not involved in the study.
Standard disease assessment is highly subjective and time-consuming, says Yincheng Liu, a graduate student in machine perception and health at MIT and lead author of the study. “We can’t ask patients to come to the clinic every day or every week,” says Liu. “This technology gives us the ability to continuously monitor patients and provide more objective assessments.”
The new study’s approach involves mounting a sensor the size of a picture frame on the wall of 50 people’s homes: 34 with Parkinson’s disease and 16 without. The sensor produces radio waves similar to an ultra-weak WiFi signal that act as a human-detecting radar. The researchers used this radar to track walking speed, which they could average over hours or days to measure the patient’s mobility.
“There are a lot of different sensors” in development to track Parkinson’s disease, including smartwatches and phone apps, Beck says. “What’s interesting about this approach is that it’s completely passive. … Being able to track a person moving in almost real time is really exciting.”
The researchers compared mobility at home with conventional clinical measures of Parkinson’s disease. After controlling for age and other factors that may affect gait, the research team found that a patient’s walking speed, as determined by the sensor, correlated closely with the in-depth assessment of the disease: the motor examination part of the Comprehensive Parkinson’s Test, which assesses the patient’s hand movements, speech and gait . Quick assessments often used by doctors, such as the time it takes someone to get up from a chair, do not match this test.
A home monitor helps to avoid the so-called “white coat effect”. “When we do the test in front of the doctor, we try to make it as good as possible,” says Liu. A short test in a clinic may reflect someone’s effort but not their endurance – it’s a bit like determining a car’s top speed but not its mileage.
Home measurements of gait also revealed a decline in patients’ mobility long before clinical measurements could observe the decline. Everyone’s walking speed decreased over the course of the year-long study, but those with Parkinson’s disease walked twice as fast – a progression that could not be detected on a comprehensive examination.
Walking is just one approach to measuring this daily function, and previous work with the device has shown that it can also capture a person’s full silhouette. Liu says that they are interested in finding out whether it also records stride length and arm movement, or other motor functions.
[Related: This AI can see people through walls. Here’s how.]
Researchers say the home monitor could also improve the way the disease is treated. Although Parkinson’s disease is incurable, its symptoms can be controlled with a drug called levadopa.
“Essentially, when a patient takes this drug, their movement and cognitive function improves,” says Liu. But the effect wears off at different rates for different people. And the drug can cause side effects, including involuntary movements. “I liken it to drinking coffee,” says Liu: “Too little and you get a migraine; too much and you will become nervous and anxious. Therefore, patients and doctors must figure out the optimal dose and timing. “The traditional way to do this is to write in a journal every thirty minutes for two weeks,” Liu says. He says he tried to keep such a journal to understand what the patient’s assessment looked like. “It’s really hard.”
With daily gait measurements, the physician could more clearly see the effects of medication adjustments. In the study, “when we compare the patient’s walking speed with the diary, we find that they are correlated,” says Liu. The study was observational, so researchers did not intentionally adjust patients’ medications, but two patients did change their medication schedules during the study. These changes were reflected in their walking speed throughout each day – they had fewer falls due to low mobility. “The doctor can really look at that fluctuation curve and try to change the dosage little by little.”
Beck says that such clinical trials are still in the validation phase.’ It may be years before it becomes a widely used tool, he says, but “I think it has a head start.”