Huashan Hospital

Ten native Mandarin speakers read aloud six single-vowel rhymes while optically pumped magnetometer magnetoencephalography (OPM-MEG) and EEG recorded the same task. In the 150-500 ms window after stimulus onset, OPM-MEG decoded significantly more accurately than EEG with all five classifiers tested. The best-performing combination, common spatial pattern features with a linear support vector machine, reached a mean accuracy of 60.3% for OPM-MEG versus 56.7% for EEG. That suggests speech BCIs that need no implanted electrodes and do not restrict head movement may have a clearer signal path than EEG.

NeuroXess registered a prospective, multicenter, single-arm trial (NCT07720882) enrolling people with tetraplegia caused by spinal cord injury to evaluate the safety and clinical efficacy of an implantable BCI system for compensatory hand movement and upper-limb functional replacement. The study is at the registration stage with no results yet.

Intracranial recordings from ten epilepsy patients show that neural activity during cued limb motor imagery changes with the phase of the task: low-frequency (8-30 Hz) activity was mostly suppressed during preparation and switched to activation once imagery began, while high-frequency (60-115 Hz) responses were stronger, more widely distributed, and at some contacts followed an activation-then-suppression sequence. The stereoelectroencephalography (sEEG) data indicate that responses are not uniform but shift with task stage and brain region, which the authors tie to stage-aware feature design for BCIs and to neurorehabilitation.

The trial split 54 stroke patients with hand impairment into three groups using kinesthetic, hybrid and visuomotor imagery to drive BCI training, with upper-limb Fugl-Meyer score as the primary endpoint. The registration record does not yet report which imagery mode worked best.

NeuroXess and Huashan Hospital reported a single-patient test of a 256-channel flexible implantable BCI. In postoperative training, decoding accuracy reached 71% across 142 commonly used Mandarin syllables, with per-character latency below 100 milliseconds. The participant had a language-area tumor and epilepsy, so the company-reported result does not establish performance in people who have lost speech.