Researchers at the University of California, San Francisco (UCSF) have developed a new approach to help people with Parkinson’s disease who experience walking difficulties. The method combines deep brain stimulation (DBS) with artificial intelligence (AI) to personalize treatment and improve gait performance.
Deep brain stimulation involves implanting thin wires, or electrodes, into specific areas of the brain through minimally invasive surgery. These electrodes are connected under the skin to an electrical pulse generator in the chest, which sends signals to targeted regions of the brain. Doris Wang, MD, PhD, a neurosurgeon and associate professor at UCSF who led the research team alongside postdoctoral researcher Hamid Fekri Azgomi, PhD, explained: “DBS uses an implanted device. This is done with a minimally invasive surgery. I drill two very small holes in the skull, and then insert really thin wires or electrodes, which are the size of angel hair spaghetti and very flexible. The wires run from the side of the head all the way down to the chest under the skin. In the chest, these wires are connected to an electrical pulse generator. You can think of it as a pacemaker for the brain.”
Parkinson’s disease often leads to motor issues such as shuffling steps and freezing while walking due to changes in brain wave patterns caused by loss of dopamine neurons in a region called the basal ganglia. Wang noted: “In Parkinson’s disease, the destruction of dopamine neurons in brain’s basal ganglia area causes of variety of motor issues, including ‘Parkinson’s gait.’ People with the disease tend to shuffle when they walk and take many mini steps when they turn. They also have different step lengths between the left and right foot, and some patients freeze in place. These symptoms often lead to falls.”
Traditional treatments for gait problems in Parkinson’s patients have had limited success. “Among Parkinson’s patients’ major symptoms, gait has been quite difficult to treat,” said Wang. “The most severe types of gait disorder are really challenging to treat with either medication or DBS.” This challenge motivated her team to explore ways to adjust DBS specifically for walking difficulties.
The researchers evaluated patients’ walking using both clinical observations and neurophysiological data collected while participants walked laps under various DBS settings. They developed a Walking Performance Index that measured four features: arm swing amplitude, stride speed, stride length variability, and stride symmetry.
Using machine learning tools on this data helped determine optimal DBS settings tailored for each patient’s needs. Wang explained: “From these sessions, we gathered data and used machine learning to identify the DBS settings that improved each patients’ gait. AI helped predict the settings that might be best for different patients.” The results showed that not all patients benefited from identical settings; some required higher frequencies while others did better with lower ones.
By examining how these adjustments affected activity in motor networks within participants’ brains, researchers identified specific brain waves linked with improved walking performance.
According to Wang: “The personalized settings for each patient led to meaningful improvements in walking, such as faster more stable steps, without worsening other symptoms.” She added that future work will focus on developing adaptive algorithms so that patients can automatically switch between standard DBS modes and those optimized for walking depending on their movement state.
This research was supported by funding from NIH.
