Be part of the knowledge.

We’re glad to see you’re enjoying ReachMD…
but how about a more personalized experience?

Register for free

AI Supports Rehabilitation After Spinal Cord Injury

ReachMD Healthcare Image
Credit: FAU/Georg Pöhlein

An intelligent suit is being designed with the hope that it will significantly improve rehabilitation in patients after a serious spinal cord injury. The AI-supported solution will be developed over the next three years by researchers from Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) working in collaboration with Heidelberg University and Heidelberg University Hospital. It combines electrical simulation of muscles with support for movement using artificial tendons, and reacts to patients' intended movements.

Injuries to the spinal cord as a result of traffic or sport accidents, tumor operations or infections have a dramatic impact on the lives of those affected. Daily activities like eating and drinking, getting dressed or personal hygiene are no longer possible, or if so, then only to a very limited extent.

However, injuries like this are not necessarily irreversible. For example, if the long nerve fibers are not separated entirely from the brain, some remnants of motor control remain. "In such cases there is a good chance of regaining at least some mobility," explains Prof. Dr. Claudio Castellini from the Chair of Assistive Intelligent Robotics at FAU. "The potential for regeneration is particularly high in the first twelve months after the injury, when new neurons can be generated and new networks created."

Standard treatment does not exploit the full potential

The rehabilitation of arm and hand function is mainly based on the repeated execution of mobility exercises, where patients are required, for example, to grasp a cylinder and move it to a certain place. Patients are supported by qualified therapists, or at times also by robots. The methods used include functional electrical simulation (FES), in which electrodes trigger targeted muscle contractions, as well as exoskeletons or suits. These are orthoses that support and assist movement using pulley mechanisms or inflatable air chambers.

"Although great progress has been made in recent years, the therapies which are currently available do not correspond to the principles of motor learning," Castellini explains. "Firstly, especially weak muscles are not targeted sufficiently, and secondly, patients are not actively encouraged to execute useful motor exercises. Our experience has shown that this leads to patient engagement waning over time." Combined with the fact that current rehabilitation measures are not sufficiently tailored to patients' individual requirements and abilities, this means that the full potential for treatment is not fully exploited.

Integrated suit recognizes intended movements

Over the next three years, Claudio Castellini aims to work together with the Institute of Computer Science at Heidelberg University and the Department of Experimental Neurohabilitation at Heidelberg University Hospital to develop a suit that is hoped to significantly improve the success of therapy after spinal cord injuries. The Exo-Suit consists of a compression jacket, arm cuffs and gloves and combines the support systems available to date such as FES and pulley mechanics, but has one special addition: AI-supported recognition of patients' intended movements.

"Integrated sensors measure muscle activity," explains Marek Sierotowicz, a doctoral candidate involved in the project. "Self-learning algorithms take this input and use it to calculate the patient's intended movement and adjust the assistance systems accordingly." Specifically, this means that the AI tells the FES system and the Exo-Suit where muscle contractions should be triggered or pulleys tautened in order to support the intended movement.

Monitoring intention allows targeted and gentle therapy

FAU is predominantly responsible for developing methods to perceive the patient's intended movements. For this to work, researchers first have to construct a complete virtual model of the anatomical structure of the muscles and skeleton and train it accordingly. "We will carry out our initial tests with people who are not disabled and gather as much data as possible," says Sierotowicz. "The better we train AI, the more reliably we will be able to recognize movement patterns and the more accurately the assistance systems will be able to work in the future."

That is not only necessary for precise movement support, the intelligent interplay between EFS and robotic pulley systems also ensure a more gentle treatment. Experience has shown that using FES alone requires a high intensity of simulation and patients often find it unpleasant. Researchers are convinced that their invention will lead to a significant improvement in the success of rehabilitation after a spinal cord injury.

Provided by Friedrich–Alexander University Erlangen–Nurnberg

Citation: AI supports rehabilitation after spinal cord injury (2023, June 30) retrieved 30 June 2023 from

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.

Facebook Comments

Schedule12 Jun 2024