STIMO
Personalized epidural electrical stimulation of the lumbar spinal cord for clinically applicable therapy to restore mobility after paralyzing spinal cord injury
Abstract
Every year, 250 000 people worldwide suffer a spinal cord injury (SCI) that leaves them with a chronic paraplegia — permanent loss of ability to move their legs. Consequently, about 2.5 million people suffer from chronic paraplegia caused by SCI. SCI interrupts axons passing along the spinal cord, thereby isolating motor neuron pools from the brain inputs. To date, there are no effective treatments that can reconnect these interrupted axons.
In a recent breakthrough, the neuroprosthesis called STIMO was developed. STIMO can restore walking after paralyzing SCI using epidural electrical stimulation (EES). It is an implanted stimulator surgically inserted in the epidural space of the lumbar spinal cord (see Fig. 1). An external controller sends wireless commands to STIMO, which then delivers EES directly over the spinal cord. Once activated, motor neurons contract the muscles they innervate to generate movements of the legs. The current STIMO therapy requires long-lasting calibration procedures that have to be performed by highly-trained experts.
This project is funded by PHRT.
People
Collaborators
Oleg received his Ph.D. in Computer science from the Moscow Institute of Physics and Technologies in 2021. His research interests include Bayesian model selection in application to deep learning models and natural language processing. During his studies, he worked on projects related to plagiarism detection and multilingual text processing.
Leonid joined SDSC in 2022 to design data-driven solutions for academic research projects. His research interests are in the areas of uncertainty quantification, ensemble learning, and probabilistic modeling. Leonid graduated from Moscow State University and defended his PhD at HSE University in 2021. Leonid has experience working in financial services, where he was engaged in projects related to pricing, product bundling, and uplift modeling. His recent cross-disciplinary collaborations involve applications in medicine and physics.
Mathieu Salzmann is the Deputy Chief Data Scientist of the Swiss Data Science Center and a Senior Scientist and Lecturer at EPFL. He received his PhD from EPFL in 2009 and, between 2009 and 2015, has held post-doctoral and researcher positions at UC Berkeley, TTI-Chicago, and NICTA and the Australian National University. From May 2020 to February 2024, he was also a part-time Senior GNC Engineer at ClearSpace. Mathieu Salzmann has broad interests in machine learning and deep learning, with a particular focus on computer vision. He has published over 100 articles at top-tier peer-reviewed machine learning and computer vision venues and is a strong believer in collaborative work.
Guillaume Obozinski graduated with a PhD in Statistics from UC Berkeley in 2009. He did his postdoc and held until 2012 a researcher position in the Willow and Sierra teams at INRIA and Ecole Normale Supérieure in Paris. He was then Research Faculty at Ecole des Ponts ParisTech until 2018. Guillaume has broad interests in statistics and machine learning and worked over time on sparse modeling, optimization for large scale learning, graphical models, relational learning and semantic embeddings, with applications in various domains from computational biology to computer vision.
PI | Partners:
NeuroRestore:
- Prof. Dr. Grégoire Courtine
- Prof. Dr. Jocelyne Bloch
- Dr. Robin Demesmaeker
- Dr. Grégory Dumont
- Alice Bruel
description
Motivation
The goal of this project is to develop and clinically validate procedures to achieve the most effective and clinically applicable therapy by:
- Personalizing the selection of the most effective lead out of four available,
- Personalizing the placement of the selected lead in the most effective location,
- Personalizing the EES protocols to enable the most effective lower-limb motor activities.
We will design these procedures to be used by treating physicians through a web-based portal with less involvement of experts and with a limited amount of data. Our goal is to enhance usability and automation to facilitate broader adoption of the STIMO therapy.
Proposed Approach / Solution
The structure and framework of the spinal circuitry that governs the firing of motor neurons in response to complex EES protocols is largely unknown. We will therefore model the response of each motor neuron pool using either a “black box” neural network, more abstract state space models suited to model the dynamics of neural circuitry response or hybrids of the two. These spinal circuity models will exploit the general relationship between EES parameters and muscle responses. We will calibrate personalized spinal circuitry models, as well as a “general” spinal circuitry model from previously recorded data of patients in which the personalized bioelectrical spinal model and proprioceptive maps have been generated. The project overview is presented in Fig. 2.
Impact
The success of this project will considerably enhance the STIMO therapy and open a clear path towards its widespread use. As a commercial partner in the consortium, ONWARD Medical will directly pursue the next steps towards regulatory approval and worldwide distribution of the personalized STIMO therapy, thereby ensuring that our work transforms the lives of many people paralyzed by spinal cord injury and decreases the overwhelming societal and economic burden of paraplegia.
Presentation
Gallery
Annexe
Additional resources
Bibliography
- Fabien B. Wagner et al. “Targeted neurotechnology restores walking in humans with spinal cord injury”. In: Nature, 563.7729 (2018), pp. 65–71.
- Andreas Rowald et al. “Activity-dependent spinal cord neuromodulation rapidly restores trunk and leg motor functions after complete paralysis”. In: Nature Medicine, 28.2 (2022), pp. 260–271.
- Marco Capogrosso et al. “A Computational Model for Epidural Electrical Stimulation of Spinal Sensorimotor Circuits”. In: The Journal of Neuroscience, 33.49 (2013), pp. 19326–19340.
- Eduardo Martin Moraud et al. “Mechanisms Underlying the Neuromodulation of Spinal Circuits for Correcting Gait and Balance Deficits after Spinal Cord Injury”. In: Neuron, 89.4 (2016), pp. 814–828.
- Emanuele Formento et al. “Electrical spinal cord stimulation must preserve proprioception to enable locomotion in humans with spinal cord injury”. In: Nature Neuroscience, 21.12 (2018), pp. 1728–1741.
Publications
More projects
ML-L3DNDT
BioDetect
IRMA
FLBI
News
Latest news
Smartair | An active learning algorithm for real-time acquisition and regression of flow field data
Smartair | An active learning algorithm for real-time acquisition and regression of flow field data
The Promise of AI in Pharmaceutical Manufacturing
The Promise of AI in Pharmaceutical Manufacturing
Efficient and scalable graph generation through iterative local expansion
Efficient and scalable graph generation through iterative local expansion
Contact us
Let’s talk Data Science
Do you need our services or expertise?
Contact us for your next Data Science project!