Review of Recent Advances in Implantable Brain-Computer Interfaces for the Restoration of Motor Function in Patients With Paralysis

Daokai Yang; Xiaogang Liu; Junhang Hu; Wei Zhang

doi:10.12659/MSM.951925

14 April 2026 : Review article

Review of Recent Advances in Implantable Brain-Computer Interfaces for the Restoration of Motor Function in Patients With Paralysis

Daokai Yang^{AEF 1,2}, Xiaogang Liu^{AEF 2}, Junhang Hu^{AEF 1,2}, Wei Zhang^{AEFG 1,2*}

DOI: 10.12659/MSM.951925

Med Sci Monit 2026; 32:e951925

Authors information Article notes Copyright and License information

Introduction Fundamental Mechanisms: Principles of Neural Signal Acquisition for BCIs Neural Decoding and Pattern Recognition Applications and Recent Progress Comparison of Invasive and Noninvasive Modalities Key Technological Innovations Clinical Translation Patient Outcome Assessment Current Limitations and Paths Forward Discussion and Outlook Clinical Translation and Current Trial Landscape Artificial Intelligence Models for Neural Decoding Future Directions Conclusions References

Related articles Order reprints Share article Share by email

View HTML version

Figure 2 Training–testing workflow for motor imagery electroencephalography(A) Training: labeled data undergo pre-processing (band-pass/notch filtering, artifact suppression) and spatial selection (channel selection/common spatial patterns [CSP]); features are extracted via common spatial patterns and a classifier, such as, extreme learning machine (ELM), is trained under supervision. (B) Testing: unseen data are processed through the identical pipeline, and the resulting features are fed to the trained model to output predicted labels.

Back to the Article

Review of Recent Advances in Implantable Brain-Computer Interfaces for the Restoration of Motor Function in Patients With Paralysis

Your Privacy