Hybrid Brain-Computer Interface Controlled Soft Robotic Glove for Stroke Rehabilitation

Area of Science:

• Neuroscience and Biomedical Engineering
• Rehabilitation Technology

Background:

• Existing brain-computer interface (BCI) systems for stroke hand rehabilitation often use static visual cues, limiting performance.
• Motor imagination (MI) and steady-state visual evoked potential (SSVEP) are key BCI paradigms with potential for improvement.

Purpose of the Study:

• To develop an innovative hybrid BCI paradigm combining MI and SSVEP for enhanced hand rehabilitation.
• To integrate a soft robotic glove with the hybrid BCI for a comprehensive "peripheral - central - peripheral" rehabilitation system.
• To validate the system's effectiveness in healthy subjects and stroke patients.

Main Methods:

• A hybrid BCI paradigm was created using sequential visual stimulation of decomposed hand gripping actions at distinct frequencies (34 Hz for left, 35 Hz for right).
• Motor imagery (MI) and steady-state visual evoked potential (SSVEP) signals were decoded using Filter Bank Common Spatial Pattern (FBCSP) and Filter Bank Canonical Correlation Analysis (FBCCA) algorithms.
• A novel fusion algorithm was developed to combine MI and SSVEP outputs for final system decision-making.

Main Results:

• The hybrid BCI system achieved high accuracy in healthy subjects (95.83 ± 6.83%) and significant accuracy in stroke patients (63.33 ± 10.38%).
• Individual MI and SSVEP accuracies in healthy subjects (81.67 ± 15.63% and 95.14 ± 7.47%) were surpassed by the fused system's accuracy.
• Accuracy rates exceeding 50% were observed in both healthy participants and stroke patients, confirming system efficacy.

Conclusions:

• The proposed hybrid BCI system integrating MI, SSVEP, and a soft robotic glove is effective for hand rehabilitation.
• The novel fusion algorithm significantly enhances BCI performance compared to individual MI or SSVEP.
• This "peripheral - central - peripheral" approach offers a promising, natural, and friendly rehabilitation strategy for stroke survivors.