Summary: It may be possible to optimize the stimulation parameters of brain implants in animals without human intervention. The study highlights the potential for autonomous optimization of prostheses implanted in the brain. Advance may prove beneficial for people with spinal cord injuries and conditions that affect movement.
Source: Montreal university
Scientists have long studied neurostimulation to treat paralysis and sensory deficits caused by strokes and spinal cord injuries, which in Canada affect some 380,000 people across the country.
A new study published in the journal Medicine Reports Unit demonstrates the possibility of autonomously optimizing the stimulation parameters of prostheses implanted in the brains of animals, without human intervention.
The work was carried out at the University of Montreal by neuroscience professors Marco Bonizzato, Numa Dancause and Marina Martinez, in collaboration with mathematics professor and researcher at Mila Guillaume Lajoie.
The study was born of a major interdisciplinary collaboration between researchers who combine expertise in neuroscience and artificial intelligence, two areas of expertise in which UdeM stands out internationally.
“A very promising phase”
“Neuroprosthetics, devices designed to restore connections between neurons following a loss of motor function, are entering a very promising phase in their development,” said Lajoie. “We demonstrate the benefits obtained by autonomously optimizing their parameters.”
If the performance of these prostheses has increased, it is thanks to the autonomous learning algorithms proposed by the researchers, adds Bonizzato.
“Optimization algorithms allow us to design highly refined neurostimulation protocols and customize treatments based on each patient’s condition.”
For its part, Dancause believes that while “there are several ways to stimulate the brain, the contribution of artificial intelligence is essential to make the most of the data collected and anticipate conditions that do not yet exist”.
Thanks to these technological advances, scientists are closer to finding new neuroprosthetic solutions to improve the treatment of pathologies such as spinal cord injury and stroke, or neuromodulation deep brain stimulation to treat conditions such as Parkinson’s disease.
About this neurotechnology research news
Author: Press office
Source: Montreal university
Contact: Press service – University of Montreal
Picture: Image is in public domain
Original research: Free access.
“Autonomic optimization of neuroprosthetic stimulation parameters that drive motor cortex and spinal cord outputs in rats and monkeys” by Marco Bonizzato et al. Medicine Reports Unit
Autonomous optimization of neuroprosthetic stimulation parameters that drive motor cortex and spinal cord outputs in rats and monkeys
- Autonomous learning algorithm optimizes complex neuromodulation patterns live
- It allows “intelligent” neuroprostheses, immediately relieving motor deficits
- The application is robust to changes, for example, due to plasticity or interface failure
- Knowledge transfer to experts/clinicians is supported by an open source framework
Neural stimulation can alleviate paralysis and sensory deficits. Novel high-density neural interfaces may enable refined, multi-pronged neurostimulation interventions. To achieve this, it is essential to develop algorithmic frameworks capable of handling optimization in large parameter spaces.
Here, we used an algorithmic class, Bayesian Optimization (BO) based on the Gaussian Process (GP), to solve this problem. We show that GP-BO effectively explores the neurostimulation space, outperforming other search strategies after testing only a fraction of possible combinations.
Through a series of real-time multidimensional neurostimulation experiments, we demonstrate optimization on various biological targets (brain, spinal cord), animal models (rats, non-human primates), in healthy subjects, and in neuroprosthetic intervention after an injury, for immediate and continuous learning over several sessions. GP-BO can integrate and enhance “prior” expert/clinical knowledge to dramatically improve its performance.
These results argue for a broader implementation of learning agents as structural elements in the design of neuroprostheses, allowing personalization and maximization of therapeutic efficacy.