Myoelectric Control Based on a Generic Musculoskeletal Model: Toward a Multi-User Neural-Machine Interface.

Area of Science:

• Biomedical Engineering
• Neuroscience
• Rehabilitation Technology

Background:

• Electromyography (EMG)-based neural-machine interfaces (NMIs) are crucial for prosthetic control.
• Existing NMIs often require extensive user-specific calibration and customization.
• Predicting coordinated metacarpophalangeal (MCP) and wrist movements remains a challenge.

Purpose of the Study:

• To develop a user-generic EMG-based NMI for continuous prediction of coordinated MCP and wrist flexion/extension.
• To minimize calibration requirements for NMIs.
• To evaluate the performance of a user-generic model against user-specific models.

Main Methods:

• Developed a user-generic musculoskeletal model using experimental data from able-bodied subjects and various upper limb postures.
• Implemented a novel EMG-based NMI centered on this generic model.
• Evaluated the NMI online with able-bodied subjects and a transradial amputee performing virtual hand/wrist posture matching tasks.
• Compared the performance of the generic model with a user-specific customized model.

Main Results:

• All subjects successfully completed virtual tasks using the user-generic NMI.
• The generic model demonstrated comparable completion times to the specific model.
• The generic model resulted in fewer overshoots and improved path efficiency.
• Able-bodied subjects outperformed the amputee subject, but both could utilize the NMI.

Conclusions:

• A user-generic EMG-based NMI using a musculoskeletal model is feasible for predicting coordinated MCP and wrist motion.
• This approach can accommodate multiple users, including upper limb amputees.
• The developed NMI addresses limitations of current NMIs by reducing calibration and customization needs.