AI system
- System
-
Clinatec epidural wireless brain-machine interface with adaptive decoder driving a four-limb exoskeleton and virtual avatar
- Model
-
Not assessed
- Release
-
Not assessed
- Application developer
-
CEA-Clinatec (public research institute, not a company) with Grenoble University Hospital
- Role
-
Not assessed
- Configuration
-
Not assessed
- Inputs and outputs
-
Not assessed
- Autonomy
-
Not assessed
- Workflow
-
Chronic bilateral epidural ECoG recorders with wireless transmission. Adaptive, incrementally trained decoder with idle-state support. Progressive training on mental tasks over 24 months.
- Human oversight
-
Not assessed
- Relation to AI
-
The adaptive decoding algorithm converts epidural ECoG into effector commands. The same group later described it as a recursive exponentially weighted Markov-switching multilinear mixture-of-experts model. Without it the implants record only. The exoskeleton itself was ceiling-suspended in the laboratory.
- AI contribution
-
The adaptive decoding algorithm converts epidural ECoG into effector commands. The same group later described it as a recursive exponentially weighted Markov-switching multilinear mixture-of-experts model. Without it the implants record only. The exoskeleton itself was ceiling-suspended in the laboratory.
Benefits
- Outcome identifiers
-
Not assessed
- Benefit
-
64.0% success using the avatar at home and 70.9% with the exoskeleton in the laboratory
- Category
-
Improved Accessibility
- Status
-
Not assessed
- Beneficiary groups
-
People. Society.
- Beneficiaries
-
Not assessed
- Reach
-
Not assessed
- Distribution and access
-
Not assessed
- Duration
-
Not assessed
- Expected?
-
Yes
- Costs and harms
-
Not assessed
Measurement
- Studies
-
Not assessed
- Study design
-
Not assessed
- Measurement
-
Not assessed
- Setting and sample
-
Not assessed
- Measures
-
64.0% success using the avatar at home and 70.9% with the exoskeleton in the laboratory
- Comparison
-
Not assessed
- Results
-
64.0% success using the avatar at home and 70.9% with the exoskeleton in the laboratory
- Additional value from AI
-
Not assessed
- Limitations
-
Not assessed
- Denominators
-
Not assessed
- Materials for replication
-
Not assessed
Money
- Kind of value
-
Not assessed
- Amount
-
Not assessed
- Currency and prices
-
Not assessed
- Period and unit
-
Not assessed
- Realization
-
Not assessed
- Recipients and payers
-
Not assessed
- Gross or net
-
Not assessed
- Included costs
-
Not assessed
- Comparison
-
Not assessed
- Method
-
Not assessed
- Return and payback
-
Not assessed
People and places
- Participants
-
Developer: CEA-Clinatec (public research institute, not a company) with Grenoble University Hospital. Operator: Clinatec research center / Grenoble University Hospital clinical trial.
- Jurisdictions
-
Benefit: Grenoble,
France. Developer: France. Operator: France. - Ownership and control
-
Not assessed
- Dependencies
-
Not assessed
- Cross-border connections
-
Not assessed
- Geopolitical implications
-
Not assessed
Follow-up
- Conditions for replication
-
Stable epidural signal quality over years. Decoder recalibration roughly every seven weeks. Laboratory suspension system for safe exoskeleton walking.
- Replication attempts
-
1 follow-up entries. Benefit recurred: 1.
- Later findings
-
30 March 2022. The same patient was still controlling the exoskeleton bimanually more than three years after implantation, with a decoder stable for six months without recalibration.
- Availability
-
Not assessed
- Institutional decision
-
Not assessed
- Grounds
-
Not assessed
- Action and result
-
Not assessed
- Success criterion
-
Not assessed
Evidence
- Source numbers
-
AIBD-0053-source-0001–0003
- Citations
-
Numbered references below.
- Language
-
Not assessed
- Source relationships
-
Developer
- Original evidence
-
Not assessed
- Access and versions
-
Not assessed
- Supported findings
-
Not assessed
- Evidence links
-
Not assessed
- Evidence strength
-
Not assessed
- Missing evidence
-
Not assessed
Grades
- Assessed benefits
-
People. Society.
- Depth
-
People: 2. Society: 1.
- Reasons
-
People: One identifiable participant gained brain-controlled walking simulation and eight-degree-of-freedom arm control, exercised at home with an avatar and in the lab with the exoskeleton. It did not yet provide everyday mobility. Society: Single-patient proof of concept for semi-invasive long-term BCI. No population effect.
- Observed or intended
-
Not assessed
- Rubric
-
Not assessed
- Assessor and date
-
Not assessed
- Alternative assessments
-
Not assessed
- Fill
-
The makers' claim
Entry details
- Kind
-
Not assessed
- Related entries
-
Not assessed
- Field
-
Neurotechnology / mobility rehabilitation. People with tetraplegia.
- Purpose
-
Restore mobility to people with tetraplegia by decoding brain signals to drive an exoskeleton
- Dates
-
Date basis unassessed: 2017 (precision unassessed). Updated: 21 October 2026.
- Stage
-
Not assessed
- Version
-
SHA-256: c81e4df8b066…
References
- Other identifiers
-
Not assessed
- Category mappings
-
Not assessed
- Brief
-
Not assessed
- Revisions
-
4 revisions. Latest: 21 October 2026.
Sources
-
Peer-reviewed study Developer
Benabid AL, Costecalde T, Eliseyev A, et al. (2019). An exoskeleton controlled by an epidural wireless brain-machine interface in a tetraplegic patient: a proof-of-concept demonstration. Lancet Neurology 18(12):1112-1122.
Epidural electrocorticographic (ECoG) signals were processed online by an adaptive decoding algorithm to send commands to effectors (virtual avatar or exoskeleton).
the patient cortically controlled a programme that simulated walking and made bimanual, multi-joint, upper-limb movements with eight degrees of freedom during various reach-and-touch tasks
-
Peer-reviewed study Developer
Moly A, Costecalde T, Martel F, et al. (2022). An adaptive closed-loop ECoG decoder for long-term and stable bimanual control of an exoskeleton by a tetraplegic. Journal of Neural Engineering 19(2).
The stable over a period of six months (without decoder recalibration) eight-dimensional alternative bimanual control of the exoskeleton and its virtual avatar is demonstrated.