LAUSANNE — Researchers at EPFL developed an adaptive deep brain stimulation approach published in Nature Medicine in June 2026. This system uses artificial intelligence to adjust stimulation parameters in real time based on patient mobility.

The adaptive stimulation improved walking, stair climbing, and standing in study participants. Deep brain stimulation has been used for over 30 years to treat motor symptoms of Parkinson's disease. Over 200,000 patients worldwide have been implanted with deep brain stimulation systems.

Conventional deep brain stimulation delivers continuous electrical pulses to specific brain regions to reduce rigidity and tremor. However, the therapy has limited effectiveness in treating walking impairments associated with Parkinson's disease. The new therapy dynamically adjusts stimulation based on locomotor activity rather than delivering fixed parameters.

Mr. F, a study participant, said, "Before, I could barely walk because my legs would feel heavy or sometimes move uncontrollably. Now, as the stimulation adapts to what I'm doing, I can walk better and for longer stretches." The system modulates electrical stimulation within seconds to align with ongoing movement.

Jocelyne Bloch, head of neurosurgery at CHUV, said, "Walking problems often respond differently to deep brain stimulation than tremor or rigidity, something clinicians have recognized for years. Our work shows that stimulation settings can be adjusted automatically to meet a person's needs as they move." She added, "Turning deep brain stimulation into an intelligent therapy opens entirely new possibilities for patients, especially those living with severe walking impairments." The researchers trained neural decoders using artificial intelligence and data from 40 patients to detect locomotor states from brain activity. This study was conducted through the NeuroRestore interdisciplinary center, which integrates clinical and neurotechnology expertise.

EPFL researchers collaborated with Medtronic to refine implanted technology for targeting gait problems. Eduardo Moraud, an EPFL professor, said, "This work shows that we can decode many of these activities from neural biomarkers and adapt stimulation to match their physiological demands, helping patients move more naturally." The researchers noted that the findings are preliminary and will require larger studies for validation. The research team plans a follow-up study to evaluate long-term outcomes and expand the patient cohort.

No independent assessment was available for this report.