TinyML-powered closed-loop DBS for Parkinson's disease
Official title: TinyML-Driven Closed-Loop Deep Brain Stimulation for Parkinson's Disease
Funded at Michigan Technological University · NIH-11444690 · Data updated 2026-11-12
A small, energy-efficient brain-stimulation system using lightweight AI runs on an implanted device to adapt DBS in real time for people with Parkinson's disease.
Quick facts
| Grant type | R15 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Michigan Technological University NIH-funded |
| Lab location | 1 site (Houghton, United States) |
| Project start | September 14, 2026 |
| Project end | August 31, 2029 |
| Funding year | 2026 |
| Award (this year) | $549,740 |
| NIH project number | 1R15NS151160-01 |
| Project ID | NIH-11444690 on NIH RePORTER |
Who could benefit from this research
✓Could help
People with advanced Parkinson's disease who are candidates for DBS and could benefit from adaptive, implantable stimulation.
✕Less likely to help
Patients who are not suitable for DBS or who do not respond to DBS in general may not benefit.
What this research studies
This project aims to create a tiny machine learning driven closed-loop deep brain stimulation platform that can adjust stimulation based on neural signals and behavior. The approach focuses on making the device fast and power-efficient enough to run on an implant, reducing side effects and conserving battery life. By using reinforcement learning with lightweight algorithms, the team hopes to personalize therapy for individual patients and improve symptom control.
Why it matters
Potential benefit: It could offer more precise symptom relief with fewer side effects and longer device life for people with Parkinson's.
How similar studies have gone: Previous work shows adaptive DBS can improve outcomes, but this project focuses on a tiny, embedded solution that is novel and potentially more practical.
Where this research is happening
-
Michigan Technological University
Houghton, United States Active
Researchers
- Principal investigator: Yu, Chunxiu — Michigan Technological University
- Study coordinator: Yu, Chunxiu
Related research
Other NIH-funded projects on the same topics.
-
Adaptive deep brain stimulation to help Parkinson's patients respond to daily changes
A new, smarter brain stimulation approach for Parkinson’s disease aims to automatically adjust therapy throughout the day to better control symptoms.
-
Adaptive Deep Brain Stimulation for Parkinson's Disease
A safety-focused study tests a new brain-stimulation device that could tailor therapy for people with Parkinson’s by adapting stimulation based on brain signals and sleep stages.
-
Theta Burst Deep Brain Stimulation for Cognitive and Motor Benefits in Parkinson’s-Related Dementia
A study from USC will test a new brain stimulation approach to help people with Parkinson’s disease and Lewy body dementia improve thinking skills and movement.
-
Spatiotemporal Tuning of Deep Brain Stimulation for Parkinson’s Disease
Aims to personalize deep brain stimulation by adjusting where and when the brain is stimulated to better control Parkinson’s symptoms.
-
Understanding sleep problems in Parkinson’s disease using at-home brain recordings and adaptive stimulation
Scientists are testing how brain signals during sleep relate to sleep problems in Parkinson’s and whether a special DBS device at home can improve sleep by adapting stimulation.
-
Subthalamic Deep Brain Stimulation to Help with Visuo-Vestibular Conflicts in Parkinson's
A study to improve how people with Parkinson's use visual and balance cues when moving, by optimizing deep brain stimulation in the subthalamic nucleus to help navigation and balance.
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page.