MIT's at-home gait monitor wirelessly tracks progression of Parkinson's
The progression of Parkinson’s is characterized by a deterioration in motor control, and researchers are beginning to explore how this might be monitored via a person’s walking patterns. A new MIT system aims to bring this into the home, wirelessly tracking a patient’s gait to offer evaluations of Parkinson’s severity with a new level of precision.
The system is described as a “human radar” and is an adaptation of technology we looked at last month, designed to diagnose Parkinson’s disease by tracking a person’s breathing patterns with the help of AI. It makes use of radio signals that reflect off a person’s body, detecting subtle movements that can reveal tell-tale signs of disease, or its progression.
For their latest work, the team led by MIT’s Dina Katabi fashioned the technology into a device the size of a Wi-Fi router and used it to study the walking behaviors of 50 participants, 34 with Parkinson’s, at home across the course of a year. The data gathered throughout the study involved more than 200,000 gait speed measurements, which were analyzed with the help of machine learning algorithms to track Parkinson’s progression and how patients were responding to medication.
“Monitoring the patient continuously as they move around the room enabled us to get really good measurements of their gait speed,” said team member Guo Zhang. “And with so much data, we were able to perform aggregation that allowed us to see very small differences.”
Among the findings were that gait speed declined almost twice as fast in those with Parkinson’s than those without, and that daily fluctuations in walking speed correlated with how well they were responding to their medicine. Ultimately, the team found that a clinician could use the system to more effectively track Parkinson’s progression and medication response than is possible with periodic clinical checkups.
“This radio-wave sensor can enable more care (and research) to migrate from hospitals to the home where it is most desired and needed,” said Ray Dorsey, co-author of this research paper. “Its potential is just beginning to be seen. We are moving toward a day where 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.”
The research was published in the journal Science Translational Medicine.