Brain implant detects walking in Parkinson’s patients in real time: Study
Researchers call it a step toward more personalized, responsive therapies
Written by |
- A brain implant accurately detects walking in Parkinson's patients in real time.
- It records neural activity from movement-related brain regions with more than 95% accuracy.
- The technology aims to enable personalized, adaptive deep brain stimulation therapies.
A fully implanted brain device can identify when people with Parkinson’s disease are walking during their everyday lives, according to a new study from the University of California, San Francisco (UCSF).
By recording neural activity from movement-related brain regions while patients went about their normal routines at home, researchers detected walking with more than 95% accuracy. Wearable sensors were used to verify the movements.
“This is the first demonstration that a fully implanted device can be used to detect a specific movement state in humans during real-world activity,” senior study author Doris Wang, MD, PhD, a neurosurgeon and associate professor of neurological surgery at UCSF, said in a university news story. “Our findings show that it is possible to identify meaningful neural signals outside the laboratory, which is an important step toward more personalized and responsive neuromodulation therapies.”
The results were described in the study, “At-home movement state classification using totally implantable cortical-basal ganglia neural interface,” published in Science Advances.
Implanted device recorded neural activity from 2 brain regions
Parkinson’s disease is caused by the loss of dopamine-producing nerve cells in the brain. This leads to motor symptoms, including slowed movements, rigidity, and tremor. Patients often experience walking issues, such as short steps in which the feet slide rather than lifting from the ground, difficulty initiating movement, and instability during turning.
Deep brain stimulation (DBS) is a surgical treatment that involves implanting electrodes connected to a neurostimulator to deliver continuous stimulation to targeted brain areas, helping ease Parkinson’s motor symptoms. However, walking issues fluctuate during the day and can be unresponsive to DBS.
Because different Parkinson’s symptoms respond to different stimulation settings, doctors need reliable ways to detect what a person is doing in daily life, such as walking or standing. So far, this has not been extensively studied in real-world settings.
To address this problem, researchers aimed to develop a method to identify brain signals associated with walking in people with Parkinson’s during their normal daily activities. The team used an implantable bidirectional neurostimulator that could send electrical activity to the brain and record neural activity from two movement-related brain regions — the motor cortex and the globus pallidus. It was synchronized with wearable sensors to measure motion. The sensors provided movement measurements, allowing researchers to match brain activity during walking and other activities patients performed in their daily lives.
A total of four participants with Parkinson’s disease, two men and two women, were included in the study. All were undergoing evaluation for DBS. Two received implants in the left side of the brain, while the other two received implants in both sides. During the study, participants received conventional stimulation therapy.
The insights gained from naturalistic data collection will advance therapy for [Parkinson’s] and [have] the potential to accelerate [brain-computer interfaces] across a multitude of debilitating conditions.
Synchronized neural and movement data, including gait, posture, speed, and movement variations, were collected during more than 80 hours of natural, at-home daily activity. Data were then analyzed using machine learning, a type of artificial intelligence, allowing researchers to identify patterns of brain activity associated with walking. Based on these patterns, the system was able to classify patients’ movement states using the generated signals.
The results showed that walking could be distinguished from non-walking based only on neural signals, with an accuracy above 95%. The patterns varied across individuals, but the system had a sensitivity above 94% to accurately identify individuals who were walking, and a similar specificity to identify those who were not walking.
“We identified personalized neural biomarkers associated with gait and demonstrated that these signals can be used for real-time movement state classification within the constraints of an implanted device,” Wang said. “This establishes a framework for future adaptive DBS systems that could adjust stimulation in response to a patient’s activity state.”
The researchers noted that the study was small and designed to evaluate the system’s feasibility rather than its clinical efficacy. The team is now planning trials to evaluate whether stimulation settings optimized for walking can be dynamically applied using the identified patterns of brain activity.
“The insights gained from naturalistic data collection will advance therapy for [Parkinson’s] and [have] the potential to accelerate [brain-computer interfaces] across a multitude of debilitating conditions,” the researchers wrote.
