Video-based motor assessment could enable scalable assessment of neurological function, but rare-disease applications are constrained by extreme data scarcity and poor generalization from small cohorts. We develop and evaluate a smartphone-based balance-assessment framework in NF2-related schwannomatosis (NF2-SWN), an ultra-rare disorder for which objective balance assessment is clinically valuable yet logistically challenging. At its core, a staged bridge-disease curriculum adapts a skeleton-based spatiotemporal graph model from large-scale action recognition through an intermediate Parkinson’s disease domain to the target NF2-SWN cohort (N = 19), decomposing one large domain shift into two more learnable transitions under leakage-proof, subject-independent evaluation. Three clinically motivated modules, bilateral asymmetry gating, temporal phase attention, and anatomical group saliency, yield interpretable, clinician-facing outputs aligned with balance assessment. Relative to direct transfer, bridge-disease transfer reduces patient-level prediction error by 40% on the Mini-BESTest total score, narrows the gap toward inter-rater agreement, and yields well-calibrated fall-risk stratification. A robustness analysis quantifies sensitivity to simulated acquisition variability, supporting a pragmatic smart-phone recording protocol. Together, these results support the feasibility of privacy-preserving video-based balance assessment in NF2-SWN under extreme data scarcity.
Integrating frequency-tuned, adaptive brain stimulation with brain-computer interfaces (BCIs) allows direct tests of the causal role of brain oscillations and advances BCIs toward bi-directional operation. A central challenge is that stimulation-induced artifacts overlap with endogenous brain rhythms, undermining robust real-time signal decoding and contingent BCI feedback. Here, we overcome this limitation by introducing an artifact-suppression approach that enables robust motor-imagery BCI control during frequency-tuned amplitude-modulated transcranial alternating current stimulation (AM-tACS). We developed a real-time spatial filtering pipeline that combines spatio-spectral decomposition (SSD) with beamforming and evaluated its performance against a standard Laplacian filter in 14 healthy participants. BCI control was assessed both in the absence of stimulation and during stimulation. We hypothesized that only the SSD-beamforming approach would preserve robust BCI control under stimulation. In the absence of stimulation, both pipelines supported robust BCI control (SSD-beamforming: 73 ± 9%; Laplacian: 72 ± 8%; p = .849). During AM-tACS, Laplacian filtering showed a marked performance decline to near chance level (58 ± 9%; p < .001). However, with SSD-beamforming, robust BCI control was preserved (76 ± 9%). These results demonstrate that robust BCI control during frequency-tuned AM-tACS is achievable. By enabling simultaneous stimulation and decoding, this approach establishes a new paradigm for testing the causal contributions of brain rhythms during ongoing BCI control and for advancing stimulation-informed, bi-directional BCI interventions. Future work will determine how AM-tACS can be leveraged to enhance BCI performance but also promote neuroplasticity during restorative BCI applications.
Restoring hand function is a top priority in spinal cord injury (SCI), yet current assistive technologies remain limited in usability and lack intuitive control. We developed a non-invasive neuromechatronic interface that translates spared motor neuron activity from individuals with tetraplegia into the motion of a supernumerary robotic sixth finger. Three individuals with chronic, motor complete cervical SCI (C5-C6 level, > 8 years post-injury), unable to voluntarily move their fingers, participated in the study. High-density surface electromyography (HDsEMG) signals were recorded from paralyzed forearm muscles during attempted hand opening and closing. These signals were decomposed in real time into individual motor unit activity, which was then used to proportionally control the robotic finger. Participants’ ability to use the robotic finger was evaluated through a series of functional grasping tasks involving objects of daily living. After only a few minutes of training, all participants were able to intuitively modulate the activity of their spared motor units and achieve proportional control of the robotic finger. Tasks successfully completed included those requiring force from the digits, such as removing a spray can lid. Additionally, participants were able to perform some tasks that, for them, would normally require both hands using only one hand with the robotic finger. These findings demonstrate that a non-invasive neural interface leveraging spared motor neurons can enable intuitive, functional grasping in individuals with SCI, without requiring the adoption of new movement strategies.
Peripheral magnetic stimulation (PMS) has emerged as a non-contact neuromodulation technique for rehabilitation and neuroprosthetic applications. However, its practical use remains limited by high power consumption. While coil geometry optimization has been explored, the influence of individual pulse waveform phases on EMG-based functional responses remains largely uncharacterized in PMS. In this study, we present a dual-coil PMS architecture designed to enhance the axial electric-field gradient along the nerve and systematically investigate how pulse waveform parameters influence evoked responses and energy efficiency. Using an in vivo rat common peroneal nerve model, we independently varied the rising phase (RP), maintaining phase (MP), and falling phase (FP) of rectangular current pulses and quantified electromyographic (EMG) responses and per-pulse energy consumption. Decreasing MP reduced EMG amplitude, whereas increasing MP enhanced recruitment until saturation. Under the fixed-current condition, an MP of 100-150 μs provided a practical low-energy range while maintaining a robust EMG-based response. Meanwhile, the energy-normalized response decreased monotonically as RP and FP increased, indicating that shorter transition phases are consistently advantageous from an energy-efficiency standpoint. The timing of the EMG-based functional response was most consistent with initiation by the first induced component, whereas the second component appeared to modulate the final response magnitude. Complementary electromagnetic simulations further showed that the nerve-axis electric-field component generated by the dual-coil configuration partially corresponds to that of a monopolar stimulation profile, providing a structural context for interpreting the observed waveform-dependent responses. Together, these results provide experimentally grounded pulse-design guidelines for energy-constrained PMS systems.
For blind or visually impaired (BVI), the acquisition of three-dimensional (3D) spatial relationships highly depends on touch, proprioception, and active movement experience. Existing training methods are mostly based on 2D tactile graphics or static models and therefore have difficulty providing continuous, controllable, and quantifiable 3D body-motion guidance. To address this issue, this study proposes a 3D spatial perception training method based on cable-driven parallel robot (CDPR) position guidance and virtual-constraint feedback. The CDPR serves as a force-feedback interaction platform, integrating visual pose measurement, a virtual-constraint force field, tension mapping, and hybrid force-position control to transform spatial information into continuous and perceivable bodymotion guidance. Device performance experiments showed that the 3D tracking root-mean-square errors (RMSEs) for a circular trajectory with a diameter of 100 mm and a square trajectory with a side length of 100 mm were 4.35 mm and 3.31 mm, respectively. When the desired constraint force was 20 N, the measured force-output RMSE was 1.13 N. Furthermore, 24 BVI subjects were recruited for a two-group parallel controlled experiment to compare the CDPR training group and the control group in direction perception, distance perception, 3D endpoint localization, and trajectory reproduction tasks. The results showed that the CDPR training group achieved significantly greater improvements in all four tasks and maintained lower errors in untrained but related transfer tasks. Trajectory-to-object matching results showed that subjects could use CDPR-demonstrated geometric trajectories to identify corresponding physical objects through haptic exploration.
