Among three motor intent-induced modalities — motor attempt (the patient tries to move a paralyzed limb), motor observation, and motor imagery — motor attempt was the only one consistently associated with significant therapeutic effects across meta-analyses. For feedback, electrical stimulation showed consistent effectiveness, while robot-assisted and visual feedback produced heterogeneous results. The review also found that higher weekly session frequency and moderate session durations of approximately 20 to 60 minutes were linked to consistent motor recovery.
The authors conclude that BCI-based training is an effective rehabilitation approach for upper-extremity function in stroke patients with moderate to severe motor impairments, and that combining motor attempts with electrical stimulation may enhance outcomes. However, they note that stroke type, age, intervention period, total sessions, total training time, and durability of long-term effects were inconsistent across the included evidence, and further research is needed to clarify these variables.