Background: Upper limb impairment is common after stroke. Standardised measures such as the Action Research Arm Test and Fugl Meyer Assessment are widely used but may show inter-rater variability and limited sensitivity to subtle motor changes. Objective: To develop and evaluate the Functional Upper Limb Movement Assessment (FULMA) system, a single-camera markerless motion capture tool for objective movement analysis of upper limb function with clinician facing outputs after stroke. Methods: A prospective observational study included 39 stroke participants and 19 healthy controls. Participants completed 9 functional tasks recorded with a LiDAR depth camera. Kinematic features were analysed using machine learning models to predict an ordinal task performance score anchored to Action Research Arm Test scoring descriptors. Predictions were compared with independent occupational therapist ratings, and automated kinematic commentary was generated. Results: The multilayer perceptron achieved a mean accuracy of 83.3%, with task level accuracies of 75.0% to 91.7% and weighted kappa values of 0.67 to 0.88. The support vector machine achieved a mean accuracy of 78.5%, with task level accuracies of 72.2% to 89.0% and weighted kappa values of 0.59 to 0.83. Performance varied across tasks, with the strongest results for cup to mouth and hair brushing. Commentary highlighted prolonged movement time, reduced smoothness and increased trunk displacement. Conclusion: This developmental study showed preliminary agreement between automated ordinal score predictions and therapist ratings within a controlled dataset. External validation and evaluation of measurement properties are required before clinical use. Kinematic commentary should be considered exploratory rather than a validated clinical interpretation.
Objective: To evaluate the efficacy of various noninvasive neuromodulation in restoring consciousness in patients with disorders of consciousness (DoC) through a network meta-analysis and identify the optimal noninvasive neuromodulation strategies. Design: Systematic review and network meta-analysis. Methods: A comprehensive and systematic literature search was conducted for this study, encompassing several authoritative databases, including PubMed, Web of Science, EMBASE, the Cochrane Library, and ClinicalTrials.gov. This study adhered to the PRISMA-Network Meta-Analysis guidelines and was registered with PROSPERO (CRD420251018090). Literature screening, data extraction, and bias assessment (using the PEDro scale) were performed independently by 2 reviewers. A Bayesian framework-based network meta-analysis was conducted using the GeMTC package in R. Treatment rankings were determined using the surface under the cumulative ranking curve. Results: A total of 41 studies were included, of which 19 were used for quantitative analysis. For Coma Recovery Scale-Revised (CRS-R), high frequencies-repetitive transcranial magnetic stimulation-primary motor cortex (HF-rTMS-M1) demonstrated the most pronounced effect (MD = 7.1; 95% CI = 2.6-11), followed by right median nerve electrical stimulation (RMNS) plus HF-rTMS-dorsolateral prefrontal cortex (DLPFC) (MD = 5.0; 95% CI = 2.6-7.5) and RMNS (MD = 3.0; 95% CI = 1.1-4.9). For Glasgow Coma Scale (GCS), subgroup analysis by etiology indicated that both HF-rTMS-DLPFC and HF-rTMS-M1 significantly improved CRS-R and GCS scores in patients with traumatic brain injury-related disorders of consciousness. The included studies generally demonstrated low risk of bias and the analysis model showed minimal heterogeneity ( I 2 < 5%), supporting the robustness of these findings. Conclusions: HF-rTMS-M1 and RMNS plus HF-rTMS-DLPFC, RMNS, HF-rTMS-DLPFC, and tDCS have shown positive signals in patients with DoC. The duration of the disorder and underlying etiology may influence the effectiveness of different noninvasive neuromodulation techniques in DoC. Given the marked heterogeneity of DoC and the limitations of the present study, these findings should be interpreted as hypothesis-generating observations rather than universally applicable conclusions. Further high-quality randomized controlled trials (RCTs) are warranted to provide robust evidence on the most suitable neuromodulation approaches for different DoC populations and to evaluate their long-term efficacy.
Background: Walking ability is the priority for spinal cord injury (SCI) patients. Nontraumatic SCI (NTSCI) is increasing with aging populations, yet its prognosis remains understudied. Early predictionF using admission clinical indicators could facilitate decision-making and rehabilitation planning. Objective: To preliminarily develop and validate a machine learning model using early admission clinical indicators for predicting post-rehabilitation walking ability probability (with a classification threshold of 0.5) in patients with NTSCI. Methods: This retrospective study included model development and temporal external validation. We enrolled 148 NTSCI patients, randomly allocating them into training (80%) and internal test (20%) sets. Four feature sets were constructed from objective clinical measures. Nine algorithms were compared; Gradient Boosting Decision Tree (GBDT) was selected based on AUC, recall, and F2-score, followed by hyperparameter tuning. The final model was validated independently on a cohort of 37 NTSCI patients (July 2025 to May 2026). Ethical approval (M202616) and consent waiver obtained; retrospectively registered (MR-11-26-021748); no patient involvement. Results: The GBDT-based model outperformed all others. On internal testing, it achieved an AUC of 0.91 (95% CI: 0.77-1.00), recall 0.92 (95% CI: 0.71-1.00), and accuracy 0.90 (95% CI: 0.77-1.00). Key predictors included total lower limb muscle strength, age, and others. On temporal external validation, it showed encouraging performance with accuracy 0.81 (95% CI: 0.68-0.92) and recall 0.70 (95% CI: 0.40-1.00). Conclusion: This preliminary model may have potential for predicting walking ability in patients with NTSCI; however, these findings are exploratory and require confirmation in larger, multicenter cohorts before any clinical application can be considered.
Background: Walking performance is worse in Black than White adults with multiple sclerosis (MS), and that difference might extend into real-world, device-based measurements. Objective: The current study examined peak 30-minute cadence (Peak-30 CAD ) and peak 1-minute cadence (Peak-1 CAD ) in Black and White adults with MS. Methods: Participants with MS who self-identified as Black (n = 43) or White (n = 96) completed the Timed 25-Foot Walk (T25FW) and 6-Minute Walk (6MW), and wore an accelerometer on a belt around the waist during the waking hours of the day for a 7-day period. Results: Peak-30 CAD and Peak-1 CAD along with T25FW and 6MW were significantly lower in Black than White participants when controlling for imbalances in age, sex, education, and disease duration, with the differences approaching a moderate magnitude. The differences in Peak-30 CAD and Peak-1 CAD were smaller and non-significant in additional sensitivity analyses further controlling for number of days of valid accelerometer data. Peak-30 CAD and Peak-1 CAD had strong correlations with T25FW and 6MW in Black and White participants. Conclusion: Peak-30 CAD and Peak-1 CAD were associated with laboratory-based walking performance in both Black and White adults with MS and may provide complementary real-world mobility metrics.
Background: Recent studies have identified the right cerebellar Crus I (rCrus I) as a promising target for rTMS in improving language rehabilitation. However, it remains unclear whether continuous theta burst stimulation (cTBS) over the rCrus I improves language outcomes in patients with subacute post-stroke aphasia (PSA).Objective: To determine whether inhibitory cTBS over rCrus I improves language recovery in PSA and to explore underlying functional connectivity (FC) mechanisms.Methods: Fifty-one PSA patients were randomized to receive either real cTBS (n = 25) or sham stimulation (n = 26) over rCrus I (10 sessions, 2 weeks) combined with speech-language therapy (SLT). Language assessments (WAB-AQ, BNT, BDAE) and resting-state fMRI were conducted before and after the intervention.Results: Both groups showed significant language improvement post-intervention. No significant interaction was found for WAB-AQ (P = .058), but a significant interaction was observed for repetition (P = .034), favoring cTBS. Resting-state fMRI showed altered connectivity between rCrus I and right temporo-occipital regions, with FC changes negatively correlated with language gains in the cTBS group. Exploratory subgroup analyses identified 2 distinct FC response patterns (FC-increase and FC-decrease), indicating heterogeneous cerebello-cortical and intra-cerebellar connectivity modulation across participants.Conclusions: Cerebellar cTBS did not confer a significant overall benefit on language recovery in PSA, but selectively improved repetition performance, suggesting domain-specific effects. Functional imaging indicated that rCrus I-centered connectivity changes were associated with behavioral outcomes, with marked inter-individual variability. These findings support a modulatory role of cerebellar cTBS on language networks, warranting further validation in larger, well-powered studies.Trial registration: This trial was registered under the China Clinical Trial Registry (Registration No. ChiCTR2100049828).
