Deep learning networks have been successfully applied to transfer functions so that the models can be adapted from the source domain to different target domains. This study uses multiple convolutional neural networks to decode the electroencephalogram (EEG) of stroke patients to design effective motor imagery (MI) brain-computer interface (BCI) system. This study has introduced ‘fine-tune’ to transfer model parameters and reduced training time. The performance of the proposed framework is evaluated by the abilities of the models for two-class MI recognition. The results show that the best framework is the combination of the EEGNet and ‘fine-tune’ transferred model. The average classification accuracy of the proposed model for 11 subjects is 66.36%, and the algorithm complexity is much lower than other models.These good performance indicate that the EEGNet model has great potential for MI stroke rehabilitation based on BCI system. It also successfully demonstrated the efficiency of transfer learning for improving the performance of EEG-based stroke rehabilitation for the BCI system.

Background: Neuropathic pain is one of the most debilitating of all chronic pain syndromes. Intrathecal (i.t.) bone marrow stromal cell (BMSC) injections have a favorable safety profile; however, results have been inconsistent, and complete understanding of how BMSCs affect neuropathic pain remains elusive. Methods: We evaluated the analgesic effect of BMSCs on neuropathic pain in a chronic compression of the dorsal root ganglion (CCD) model. We analyzed the effect of BMSCs on microglia reactivity and expression of purinergic receptor P2X₄ (P2X₄R). Furthermore, we assessed the effect of BMSCs on the expression of transient receptor potential vanilloid 4 (TRPV4), a key molecule in the pathogenesis of neuropathic pain, in dorsal root ganglion (DRG) neurons. Results: I.t. BMSC transiently but significantly ameliorated neuropathic pain behavior (37.6% reduction for 2 days). We found no evidence of BMSC infiltration into the spinal cord parenchyma or DRGs, and we also demonstrated that intrathecal injection of BMSC-lysates provides similar relief. These findings suggest that the analgesic effects of i.t. BMSC were largely due to the release of BMSC-derived factors into the intrathecal space. Mechanistically, we found that while i.t. BMSCs did not change TRPV4 expression in DRG neurons, there was a significant reduction of P2X₄R expression in the spinal cord microglia. BMSC-lysate also reduced P2X₄R expression in activated microglia in vitro. Coadministration of additional pharmacological interventions targeting P2X₄R confirmed that modulation of P2X₄R might be a key mechanism for the analgesic effects of i.t. BMSC. Conclusion: Altogether, our results suggest that i.t. BMSC is an effective and safe treatment of neuropathic pain and provides novel evidence that BMSC’s analgesic effects are largely mediated by the release of BMSC-derived factors resulting in microglial P2X₄R downregulation.

The biomimetic materials that replicate the mechanical gradient transitions from muscle to tendon to bone remain a significant challenge in tissue engineering, particularly through simple and environmentally friendly approaches. This mechanical gradient is crucial for applications such as rotator cuff and Achilles tendon repair patches, which prevent stress shielding and ensure uniform stress distribution, addressing the stress concentration issues common in traditional repairs. Here, we present a strategy that achieves high strength even at high water content, enabling programmable modulus/structural gradients with broad applicability. Using rotator cuff tendon repair as a model system, we demonstrate successful in vivo tissue regeneration with integrated real-time sensing capabilities, providing quantitative data for rehabilitation protocols. The hydrogels exhibit precisely controlled regional mechanical properties and seamless interface transitions, mimicking the hierarchical structure of native tissue. This approach not only improves healing outcomes compared to conventional methods but also establishes a quantitative standard for rehabilitation training.

Hemiplegia is a common motor dysfunction caused by a stroke. However, the dynamic network mechanism of brain processing information in post-stroke hemiplegic patients has not been revealed when performing motor imagery (MI) tasks. We acquire electroencephalography (EEG) data from healthy subjects and post-stroke hemiplegic patients and use the Fugl-Meyer assessment (FMA) to assess the degree of motor function damage in stroke patients. Time-varying MI networks are constructed using the adaptive directed transfer function (ADTF) method to explore the dynamic network mechanism of MI in post-stroke hemiplegic patients. Finally, correlation analysis has been conducted to study potential relationships between global efficiency and FMA scores. The performance of our proposed method has shown that the brain network pattern of stroke patients does not significantly change from laterality to bilateral symmetry when performing MI recognition. The main change is that the contralateral motor areas of the brain damage and the effective connection between the frontal lobe and the non-motor areas are enhanced, to compensate for motor dysfunction in stroke patients. We also find that there is a correlation between FMA scores and global efficiency. These findings help us better understand the dynamic brain network of patients with post-stroke when processing MI information. The network properties may provide a reliable biomarker for the objective evaluation of the functional rehabilitation diagnosis of stroke patients.

Adaptor molecule downstream of kinase-3 (DOK3) is a vital regulator of innate immune responses in macrophages and B cells, and G-protein-coupled receptor 84 (GPR84) is significant in mediating the biosynthesis and maintenance of inflammatory mediators that are induced by neuropathic pain in microglia. In the present study, we determined the role of DOK3 in activating microglia-induced neuropathic pain and investigated the underlying mechanisms associated with GPR84. We found that knockdown of DOK3 in microglial cells dramatically reduced the levels of inflammatory factors, and we uncovered a physical association between DOK3 and GPR84 in the induction of inflammatory responses. We also observed that neuropathic pain and inflammatory responses induced by chronic constriction injury (CCI) of the sciatic nerve or intrathecal injection of a GPR84 agonist were compromised in DOK3-/- mice in vivo. Finally, enforced expression of DOK3 provoked inflammatory responses, and administration of pregabalin relieved neuropathic pain via inhibition of DOK3 expression. In conclusion, DOK3 induced neuropathic pain in mice by interacting with GPR84 in microglia. We hypothesize that targeting the adaptor protein DOK3 may open new avenues for pharmaceutical approaches to the alleviation of neuropathic pain in the spinal cord.