Deep brain stimulation (DBS) has been used for more than 30 years to treat the motor symptoms of Parkinson’s disease. More than 200,000 patients worldwide have now been implanted with these systems, which deliver continuous electrical stimulation to specific deep areas of the brain to reduce stiffness and tremors. However, despite clinical success, traditional deep brain stimulation (DBS) remains limited in its ability to address one of the disease’s most disabling symptoms: gait disturbance.
Researchers in Lausanne develop a new approach, natural medicineadapting DBS in real time to patient movements in everyday situations. Thanks to artificial intelligence, the system continuously interprets the patient’s activity and adjusts stimulation in real time to improve simple movements such as walking, climbing stairs, and even standing up.
Adapt stimuli to real-life situations
“Before, I could barely walk because my legs felt heavy and sometimes moved uncontrollably. Now, I can walk better and for longer stretches because the stimulation adapts to my actions,” says Mr. F., one of the study participants. Unlike traditional DBS, which delivers stimulation continuously with fixed parameters, the new treatment dynamically adjusts stimulation based on the patient’s ongoing motor activity.
Daily motor activities include a variety of activities, such as standing, walking, running, turning, and overcoming obstacles, each of which imposes different motor requirements. This study shows that we can decipher many of these activities from neural biomarkers and adapt stimulation to suit physiological demands, helping patients move more naturally. ”
Eduardo Moraud, EPFL Professor of Neuromodulation and New Medtronic Professor
Using artificial intelligence on data from 40 patients, researchers developed a neural decoder that detects various motor states directly from brain activity in real time. These signals are used to adjust the stimulation within seconds, allowing the treatment to be tailored as the movement unfolds.
This approach is based on clinically established DBS systems. Through collaboration with industry partner Medtronic, researchers were able to access and refine key aspects of the technology to target gait problems, enabling the development of adaptive real-time stimulation strategies.
From clinic to everyday use
“Gait problems often respond differently to DBS than tremor or rigidity, something clinicians have known for years. Our study shows that stimulation settings can be automatically adjusted to match a person’s movements,” said Jocelyn Block, director of neurosurgery at CHUV and senior co-author of the study.
The study, co-directed by Bloch and conducted within the NeuroRestore Interdisciplinary Center, brings together CHUV’s clinical expertise and EPFL’s leadership in neurotechnology to accelerate the translation of next-generation therapies. “Turning deep brain stimulation into an intelligent treatment opens up entirely new possibilities for patients, especially those with severe walking disabilities,” Professor Block explains.
The research team is considering conducting follow-up studies to evaluate the long-term results of this treatment and expand the approach to a larger patient population.
sauce:
Federal Institute of Technology Lausanne (EPFL)
Reference magazines:
Scafa, S. Others. (2026). Activity-dependent adaptive deep brain stimulation improves gait in Parkinson’s disease. natural medicine. DOI: 10.1038/s41591-026-04432-4. https://www.nature.com/articles/s41591-026-04432-4
