Professor of Computer Science W&M Gang Zhou (left) and Ph.D. W&M. Candidate Ken Koltermann is part of a research team developing an innovative new treatment for the movement-related symptoms of Parkinson’s disease, which affects more than 10 million people worldwide.
Photo by Adrienne Bérard
by Adrienne Bérard
October 7, 2021
In science, there is a term called “ground truth,” the benchmark against which data is judged for accuracy. For William & Mary student Ken Koltermann, the term can best be described as “the truth on the ground.”
The third year doctorate. computer science candidate spent five months of the pandemic walking nearly two hours at a time collecting data on his gait – data that a team of researchers from W&M and Virginia Commonwealth University are using to develop a new treatment for a potentially dangerous symptom of Parkinson’s disease called gel walking (or FoG) – the temporary inability to move while walking.
“I volunteered for this,” Koltermann said. “I thought if I was leading the data collection for this project, I had to do it myself. “
It was hard work – and it was personal.
“My late grandmother actually suffered from Parkinson’s disease and her cases were extremely serious,” he said. “She has had episodes of freezing walking where she had frequent falls, which as you get older become more severe. It becomes easier to break bones, to suffer real injuries. She is the main reason why I got involved in this research.
There is currently no cure for Parkinson’s disease, Koltermann explained, only treatments like drugs and a surgery called deep brain stimulation, which only helps remove some of the symptoms rather than cure the disease.
Koltermann is part of an interdisciplinary research team made up of graduate students W&M Woosub Jung and Minglong Sun, W&M professor of computer science Gang Zhou, Ingrid Pretzer-Aboff, associate professor and senior nurse researcher at the VCU School of Nursing, and Leslie Cloud, associate professor of neurology at the VCU School of Medicine and director of the Parkinson’s disease program at VCU.
The team is developing an innovative new treatment for movement-related symptoms of Parkinson’s disease, which affects more than 10 million people worldwide. Treatment uses a combination of hardware and software to deliver targeted vibrations in response to certain symptoms of Parkinson’s disease, such as tremors and FoG.
“Within this team, we have two devices, one developed by Resonate Forward, LLC and the other co-developed by IT people at W&M,” Zhou said. “We use our combined expertise to design software to communicate with hardware and develop efficient processing. It is a totally interdisciplinary project.
The project recently received funding from the National Institute of Neurological Disorders and Stroke at the National Institutes of Health. Zhou explained that the research fills a critical gap in the way Parkinson’s disease is understood and treated. Freezing walking is a common but devastating manifestation of the disease, he said, and it is a symptom of the disease for which there is no cure or adequate medical or surgical treatment.
“Freezing the process can be very socially isolating. It is very burdensome, or at least trying, for family members who have to help their loved ones. It affects their psyche with fear of falling, ”said Pretzer-Aboff, who has studied vibration therapy in patients with Parkinson’s disease for more than a decade. “There are very few options for helping patients like this. We hope that using vibrations in this new way will give better results and give people a little bit of hope, a little more autonomy, freedom and a better quality of life.
Episodes of FoG are frequently triggered by environmental and psychological factors, such as starting to walk, walking in tight spaces, changing direction, approaching a visual target, and performing dual tasks, she explained. . Stressful and urgent situations, such as entering an elevator before the doors start to close, can also trigger a FoG event.
“Each person with Parkinson’s disease is unique in their sensitivity to these various triggers, which underscores the need for personalized treatment approaches,” the researchers wrote in their NIH grant proposal. “As such, a better understanding of the modifiable factors underlying FoG and a better understanding of the individual nuances in FoG experiments is warranted.”
The nuances of an individual’s gait are not easy to categorize. Ask Koltermann. From August to December 2020, he visited VCU’s physiotherapy clinic on a regular basis to collect real-time gait data on himself for the baseline of the study, using Protokinetics Zeno from the university.MT Gateway – a non-portable gait monitoring mat that is currently widely used in clinics to collect data on how people walk.
He also wore an UltiGesture band. It’s a quarter-sized piece of hardware co-developed by Zhou’s lab that carries an accelerometer and gyroscope that collect data, which is transmitted to a smartphone via Bluetooth. Artificial intelligence, also developed by Zhou’s lab, is integrated into an application on the smartphone, which analyzes the data to detect a basic gait and any anomalies in it.
“I walked for over 90 minutes straight with our device mounted on my ankles, just collecting data and comparing it to what we were getting from the carpet,” Koltermann explained.
In the end, the data he gathered was more than enough for the team to begin to categorize the different elements of an individual’s gait. Once he collected enough data on his own approach, Koltermann turned to artificial intelligence to take the next steps. He and the team developed a type of machine learning to classify the way he walks.
“Once that was done, we were able to confirm that we could accurately detect my gait with our device,” Koltermann said.
Zhou explained that hardware and software validation is an important step. The team’s UltiGesture device is very portable and costs around $ 10. The gait detection AI they developed can run on smartphones, which are also very portable and widely available. Compare that to currently available treadmills, which are only accessible in clinical or research settings and cost over $ 50,000.
“If we can show that our device is as precise as the mat, it could lead to a revolution in accessibility of healthcare – and not just for Parkinson’s disease,” Koltermann said. “This will make walking analysis much more accessible, especially for rural health systems and low income areas.”
The next phase of the research involves pairing the UltiGesture system with the VibeForward device, a small piece of equipment developed by Resonate Forward, LLC, which delivers localized vibrations to the ankle and foot to induce people with difficulty walking or stabilizing. .
“This technology has great potential to restore independence to patients who have Freezing of Gait,” Brian Berman, director of the Parkinson’s and Movement Disorders Center at VCU, said in a press release. “Our researchers continue to work on finding ways to dramatically improve the lives of people with Parkinson’s disease until a cure can be found.”
Together, the UltiGesture and VibeForward devices will ultimately be able to detect even the slightest hint of gait freeze during a patient’s gait and trigger the vibration of the ankle device – in one second – to help the wearer stay moving as usual.
“The current treatments available for Parkinson’s disease reduce symptoms, but they do not eliminate the real-time danger of falling off the gel from walking,” Zhou explained. “This system will be able to tell the difference between intentionally stopping and unintentionally stopping the walking freeze, and then it will be able to provide instant vibration treatment.”
There is also another element of the research, which Zhou says is still in its early stages, but could open up a whole new area of possibilities. His team plans to integrate environmental stimuli into the data fed to the artificial intelligence, making it possible to detect possible triggers of walking blockage, such as doors and elevators.
“It’s really about giving Parkinson’s patients a new level of freedom to navigate the world safely,” Zhou said. “With our environment-dependent classification framework, they will be free to navigate potentially triggering stimuli with much less risk of injury. We mark the environment for them, adjusting our algorithm to reconfigure and deliver the right dose of vibration based on that environment. Giving patients that element of freedom is a motivator here.