Journal of NeuroEngineering and Rehabilitation最新文献

{"title":"Disruption of low-frequency narrowband EEG microstate networks in Parkinson's disease with mild cognitive impairment.","authors":"Guangying Pei, Mengxuan Hu, Yiliu He, Xiao Yang, Han Liu, Bo Jiang, Qi Xie, Qi Zhu, Boyan Fang, Tianyi Yan","doi":"10.1186/s12984-025-01747-0","DOIUrl":"https://doi.org/10.1186/s12984-025-01747-0","url":null,"abstract":"<p><strong>Background: </strong>Electroencephalogram (EEG) microstates provide insights into large-scale brain network coordination, revealing distinct neural dynamics within specific frequency bands associated with cognitive processes and neurological disorders. Critical gaps remain regarding the abnormalities of narrowband microstate networks in Parkinson's disease with mild cognitive impairment (PD-MCI), a key prodromal stage of the development of PD dementia. Given the importance of early detection and understanding of cognitive decline in PD-MCI, this study investigated whether alterations in narrowband EEG microstate networks could serve as early electrophysiological biomarkers for cognitive decline in PD-MCI.</p><p><strong>Method: </strong>Forty-seven individuals with PD (21 with MCI and 26 cognitively normal [PD-NC]) and 20 healthy controls were recruited. For both broadband and narrowband EEG microstates, the phase lag index was used to construct microstate brain networks, and their spatiotemporal variability was assessed.</p><p><strong>Results: </strong>Microstate analysis revealed significant divergence in narrowband parameters exclusively between the PD-MCI and PD-NC cohorts. PD-MCI showed a significant increase in low-frequency (delta/alpha-band) microstate class A, while delta-band microstate class D exhibited a significant reduction. The microstate network patterns of PD-MCI were characterized by diminished stability and disrupted synchronization in delta microstate class A within the frontal region, theta microstate class D within central region, and theta microstate class B within the occipital region. These neurophysiological markers specific to PD-MCI were significantly correlated with Montreal Cognitive Assessment scores, and machine learning-based analyses further validated their diagnostic efficacy, with accuracy ranging from 94 to 98%.</p><p><strong>Conclusions: </strong>This study identified unique abnormalities in narrowband microstate dynamics within neural networks of individuals with PD-MCI, revealing promising electrophysiological markers for the early detection and longitudinal monitoring of cognitive decline. Furthermore, these findings suggest potential applications in precision rehabilitation, whereby frequency-specific microstate biomarkers could guide individualized interventions and monitor therapeutic efficacy.</p>","PeriodicalId":16384,"journal":{"name":"Journal of NeuroEngineering and Rehabilitation","volume":"22 1","pages":"218"},"PeriodicalIF":5.2,"publicationDate":"2025-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145345666","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Re-examining the association between region-specific pain recurrence and muscle force strategies in patients with patellofemoral pain via OpenSim and artificial intelligence: a prospective cohort study toward targeted rehabilitation.","authors":"Zeyi Zhang, Ting Fan, Jin Wu, Youping Sun","doi":"10.1186/s12984-025-01762-1","DOIUrl":"https://doi.org/10.1186/s12984-025-01762-1","url":null,"abstract":"<p><strong>Background: </strong>This study utilized artificial intelligence (AI)-based machine learning algorithms, alongside the shapley additive explanations (SHAP) framework, to identify lower-limb muscle force patterns associated with recurrent patellofemoral pain (PFP) in the anterior and posterior patellar (APP), medial border of the patella (MBP), and lateral border of the patella (LBP) regions. The goal was to inform region-specific strength training strategies.</p><p><strong>Methods: </strong>A total of 299 patients with prior PFP underwent baseline biomechanical assessments, during which lower-limb and trunk muscle forces were estimated using OpenSim modeling. Participants were then prospectively followed for six months and categorized into pain-free, APP, MBP, or LBP groups according to PFP recurrence and pain location. Machine learning models were subsequently applied in conjunction with the SHAP framework to identify region-specific associations between muscle force patterns and PFP incidence.</p><p><strong>Results: </strong>APP recurrence was linked to gracilis force < 0.055 N/kg, adductor longus force > 0.110 N/kg, tibialis anterior force < 0.678 N/kg, tensor fasciae latae force > 0.144 N/kg, and internal oblique force < 0.699 N/kg. MBP recurrence was associated with rectus femoris force > 0.800 N/kg, gracilis force > 0.054 N/kg, gluteus maximus force > 0.379 N/kg, adductor longus force > 0.711 N/kg, and semitendinosus force < 0.037 N/kg. LBP recurrence corresponded to rectus femoris force < 0.530 N/kg, adductor longus force > 0.194 N/kg, tensor fasciae latae force < 0.082 N/kg, gracilis force > 0.040 N/kg, and gluteus maximus force < 0.151 N/kg.</p><p><strong>Conclusions: </strong>Machine learning analyses revealed region-specific muscle force patterns predictive of PFP recurrence, offering a biomechanical foundation for targeted strength interventions in APP, MBP, and LBP cases.</p>","PeriodicalId":16384,"journal":{"name":"Journal of NeuroEngineering and Rehabilitation","volume":"22 1","pages":"217"},"PeriodicalIF":5.2,"publicationDate":"2025-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145345652","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Functional motor mapping of domestic pig lumbar spinal cord using penetrating microelectrodes.","authors":"Soroush Mirkiani, Amirali Toossi, Amin Arefadib, Carly O'Sullivan, Dirk G Everaert, Peter Seres, David Hu, Richard Uwiera, Kevin Robinson, Peter Konrad, Vivian K Mushahwar","doi":"10.1186/s12984-025-01754-1","DOIUrl":"https://doi.org/10.1186/s12984-025-01754-1","url":null,"abstract":"<p><p>The restoration of standing and walking after spinal cord injury (SCI) remains a top priority for individuals with paraplegia. Despite significant advancements in neuromodulation techniques, challenges such as limited selectivity and inconsistent outcomes highlight the need for innovative approaches. Intraspinal microstimulation (ISMS) has emerged as a promising method for restoring motor function as demonstrated in various preclinical models. This study aimed to investigate the functional neural networks within the ventral lumbar spinal cord of pigs. We explored 134 stimulation sites inside the spinal cord in 13 domestic pigs. Post-mortem magnetic resonance imaging (MRI) revealed the location of microelectrode tips inside the spinal cord. The recorded kinematics and electromyographical muscle activity associated with each microelectrode allowed the creation of a functional map of the neural networks activated with ISMS. In addition, we performed anatomical measurements of the lumbar spine and spinal column. Our results revealed a somatotopic organization of motor networks responsible for distinct movements and muscle activations. Differences in activation patterns were primarily observed along the rostrocaudal axis (P < 0.05), where specific stimulation sites were associated with unique movements and muscle responses. In contrast, no notable variations were seen along the mediolateral or dorsoventral directions. Knee extension (KE) was the most frequently observed movement, occurring in 78% of the stimulated sites in the lumbar enlargement, followed by extensor synergy (Ext Syn, 64%), hip flexion (HF, 50%), ankle flexion (AF, 50%), ankle extension (AE, 43%), and hip extension (HE, 43%). Stimulation along the rostrocaudal axis of the lumbar spinal cord elicited a sequence of movements, beginning with HF in the rostral region and transitioning to KE, AF, AE, and HE in the caudal region across animals. Stimulation in the rostral lumbar enlargement produced stronger normalized EMG signals exceeding 50% of the maximum in vastus lateralis (VL) compared to tibialis anterior (TA) gastrocnemius (GS), gluteus medius (GL), and biceps femoris (BF; P < 0.05). Co-activation, defined as simultaneous activity above 50% of normalized maximum EMG activity, occurred at 27.4% of stimulation sites, resulting in synergistic movements and joint stiffening. The resulting map of spinal cord motor networks is important for improving device design and the efficiency of neuroprosthetic interventions. While motor maps exist for other species, they are absent for domestic pigs, a critical model for preclinical testing of SCI treatments. The functional motor maps provided here serve as a foundation for designing and optimizing intraspinal interventions, advancing their translation to clinical application.</p>","PeriodicalId":16384,"journal":{"name":"Journal of NeuroEngineering and Rehabilitation","volume":"22 1","pages":"219"},"PeriodicalIF":5.2,"publicationDate":"2025-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145345734","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AI-based patient monitoring for fall prevention in stroke patients: a pilot study at a Malaysian acute stroke unit.","authors":"Monica Danial, Chee Toong Chow, Meng Hui Lim, Noor Azleen Ayop, Irene Looi, Alan Swee Hock Ch'ng","doi":"10.1186/s12984-025-01706-9","DOIUrl":"https://doi.org/10.1186/s12984-025-01706-9","url":null,"abstract":"<p><strong>Background: </strong>Falls are an important patient safety concern and stroke patient are at high risk. Artificial intelligence (AI) could be leveraged to reduce patient falls in the hospital but there is scarcity of data. Therefore, the aim of this study is to evaluate the effectiveness of the SMART AI Patient Sitter system-an AI-powered motion-sensing and alert system designed for fall detection and prevention in a real-world hospital setting.</p><p><strong>Methods: </strong>Conducted from January to December 2024 at the Acute Stroke Unit of Hospital Seberang Jaya (ASUHSJ), the study involved 30 stroke patients who consented to AI monitoring. The SMART AI patient sitter system comprised an optical sensor, alert panel, and control panel monitored by AI, which detected patient movement and triggered alerts to the observation counter. Blurred, non-identifiable images maintained patient privacy, and investigators were identified through uniform recognition. Data on mobility and fall events were recorded continuously.</p><p><strong>Results: </strong>The integration of this system led to an 83.33% reduction in fall incidents and the generation of 1,439 alerts with a 95.34% accuracy rate. Enrolled patients had a mean age of 61 years(SD ± 12.8) years; 63.3% were male; 56.7% were of Malay ethnicity and 83.3% were classified as high fall risk. The median duration of monitoring was 3 days (IQR: 1.0-6.0), with a median of 19 bed exits(IQR: 1.0-85.0) bed exits. The first bed exit attempt occurred at a median of 150 minutes (IQR: 20.0-2103.0) minutes post-admission. Response time to movement alerts was prompt, with a median of 21  seconds (IQR: 4.0-75.0). Only one fall (3.3%) was recorded during the study. The incident involved a moderate-risk patient who attempted to stand abruptly. Staff responded within 29 seconds, and the patient recovered without severe injury.</p><p><strong>Conclusion: </strong>These findings suggest the system's potential in early detection and timely intervention. Study data demonstrated wide variability in patient mobility patterns, highlighting the need for individualized monitoring. The SMART AI patient sitter system's ability to deliver real-time alerts, ensure patient privacy, and reduce fall incidence demonstrates its value in improving stroke patient safety. Overall, this study supports the integration of AI-based monitoring tools in clinical settings to enhance patient care and reduce preventable incidents like falls.</p>","PeriodicalId":16384,"journal":{"name":"Journal of NeuroEngineering and Rehabilitation","volume":"22 1","pages":"216"},"PeriodicalIF":5.2,"publicationDate":"2025-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145345718","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mapping the role of vagus nerve stimulation in post-stroke arm motor recovery.","authors":"Nicholas Aderinto, Israel Charles Abraham, Gbolahan Olatunji, Emmanuel Kokori, Ahmedyar Hasan, Olivier Uwishema","doi":"10.1186/s12984-025-01759-w","DOIUrl":"10.1186/s12984-025-01759-w","url":null,"abstract":"<p><strong>Objective: </strong>To map the scope, nature, and extent of evidence on using Vagus Nerve Stimulation (VNS) for post-stroke arm motor recovery in preclinical and clinical settings, identifying key findings, safety profiles, and evidence gaps to guide future research.</p><p><strong>Data sources: </strong>Following the Arksey and O'Malley framework and PRISMA-ScR guidelines, we searched PubMed, Embase, Scopus, Cochrane Library, Web of Science, and Google Scholar for studies published up to March 2025. Studies evaluated invasive or transcutaneous auricular VNS (taVNS) for arm or forelimb motor recovery in adult stroke survivors or animal models.</p><p><strong>Study selection: </strong>The titles and abstracts of selected studies were screened against the eligibility criteria using Covidence software to ensure rigor and transparency. Studies that met the inclusion criteria or required a full-text review were retained. Discrepancies were resolved through discussion or consultation with a third reviewer. A full-text review was done to arrive at a final list of studies.</p><p><strong>Data extraction: </strong>Data were extracted on study characteristics, intervention protocols, motor outcomes, safety profiles, and evidence gaps.</p><p><strong>Data synthesis: </strong>A scoping synthesis approach was employed, with scoping synthesis organized by preclinical and clinical findings.</p><p><strong>Conclusions: </strong>VNS is a promising adjunct to task-specific rehabilitation, enhancing arm motor recovery with a favorable safety profile. taVNS offers a scalable, non-invasive alternative but requires further optimization. Future research should focus on diverse stroke populations, standardize protocols, and investigate synergistic combinations with other rehabilitative strategies to optimize functional outcomes.</p>","PeriodicalId":16384,"journal":{"name":"Journal of NeuroEngineering and Rehabilitation","volume":"22 1","pages":"215"},"PeriodicalIF":5.2,"publicationDate":"2025-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12522968/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145301488","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effect of lower limb mirror visual feedback on cortical activation in healthy subjects: a self-controlled randomized trail.","authors":"Wei Cui, Yang Tian, Qian Yu, Lin Huang, Yan Yang, Huifang Liu, Li Xu","doi":"10.1186/s12984-025-01725-6","DOIUrl":"10.1186/s12984-025-01725-6","url":null,"abstract":"<p><strong>Background: </strong>Mirror visual feedback (MVF) has been widely applied in the recovery of upper limb motor dysfunction after stroke, but its application in the neurological rehabilitation of the lower limbs is relatively rare, and the neural mechanism of MVF on the lower limbs is not yet clear. This study aims to explore the impact of lower limb mirror visual feedback (LLMVF) on the cerebral cortex and its possible neural mechanisms.</p><p><strong>Method: </strong>23 healthy subjects were selected to conduct a self-controlled randomized study using a block design, and functional near-infrared spectroscopy (fNIRS) was used to monitor the activation of brain regions in real LLMVF and sham LLMVF. The left lower limb of the subject was set as the active leg to perform active knee flexion and extension movements, and the right lower limb was set as the observation leg (shielded behind the mirror without any movement).</p><p><strong>Results: </strong>The mean HbO changes of LLMVF was significantly higher in the bilateral premotor and supplementary motor cortex (PM + SMA) (right: p = 0.010, left: p = 0.049), the bilateral dorsolateral prefrontal cortex (DLPF) (right: p = 0.030, left: p = 0.003), the left S1 (p = 0.011), and the right FP (p = 0.033) compared to the sham LLMVF.</p><p><strong>Conclusion: </strong>LLMVF increases neural activity in the sensory and motor related areas, indicating that LLMVF can promote more activation of brain functional areas, which verifies the top-down positive effect of LLMVF.</p>","PeriodicalId":16384,"journal":{"name":"Journal of NeuroEngineering and Rehabilitation","volume":"22 1","pages":"214"},"PeriodicalIF":5.2,"publicationDate":"2025-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12522634/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145301539","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Generalizability of neuromuscular coordination in the human upper extremity after stroke and its implications in neurorehabilitation.","authors":"Manuel Portilla-Jiménez, Yoon No Gregory Hong, Komal K Kukkar, Hyung-Soon Park, Sheng Li, Jinsook Roh","doi":"10.1186/s12984-025-01755-0","DOIUrl":"10.1186/s12984-025-01755-0","url":null,"abstract":"<p><strong>Background: </strong>Previous studies have shown that stroke often impairs neuromuscular coordination (i.e., muscle synergies) across various biomechanical conditions. In our previous study, we investigated the generalizability of muscle synergies between isometric and free dynamic reaching in healthy individuals. However, the extent to which muscle synergy characteristics after stroke are generalized across these conditions remains unclear.</p><p><strong>Methods: </strong>Electromyographic signals from eight upper extremity muscles were recorded from 14 chronic stroke survivors with mild-to-severe motor impairment and eight age-range matched controls while performing isometric force generation and point-to-point dynamic reaching tasks. Non-negative matrix factorization was applied to identify muscle synergy characteristics underlying each task.</p><p><strong>Results: </strong>In both groups, muscle activation patterns were effectively reconstructed using a small set of muscle synergies. The neurologically intact participants recruited four and five muscle synergies during the static and dynamic tasks, respectively. However, stroke survivors typically recruited four muscle synergies to perform both tasks. In addition, the composition of muscle synergies within each participant in both groups was largely conserved across the two tasks, though alterations in intermuscular coordination patterns were observed in post-stroke individuals, particularly in moderate and severe impairment cases. The majority of the altered, stroke-induced synergy patterns were explained by merging synergies underlying dynamic reaching of healthy individuals. The characteristics of muscle synergy activation profiles differed between the isometric and dynamic motor tasks in both groups. Stroke-induced alterations in correlation of pairs of synergy activation profiles were observed in dynamic reaching, but not in isometric conditions.</p><p><strong>Conclusion: </strong>This study provides several implications to stroke neurorehabilitation. First, accessible isometric conditions, especially for severely impaired stroke survivors, can be adopted as biomechanical conditions of therapeutic exercises expecting potential transferability of motor learning effects to dynamic conditions. Second, fractionation of merged synergies after stroke can be a potential rehabilitation target to enhance motor control. Finally, dynamic tasks can be effective in assessing and intervening in potential motor abnormalities that may not be prominent during isometric conditions. These results highlight the importance of developing novel stroke rehabilitation strategies that aim at improving intermuscular coordination characteristics to enhance motor function across varying biomechanical conditions after stroke.</p>","PeriodicalId":16384,"journal":{"name":"Journal of NeuroEngineering and Rehabilitation","volume":"22 1","pages":"213"},"PeriodicalIF":5.2,"publicationDate":"2025-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12522652/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145292475","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Divided attention and manual visuomotor control in stroke: a combined dual-task and eye movement study.","authors":"Elisa Dziezuk, Quentin Le Boterff, Coralie Van Ravestyn, Solène Mairesse, Sonia Hamdoun, David Calvet, Lina Daghsen, Loïc Carment, Charlotte Rosso, Marc A Maier, Guillaume Turc, Jean-Louis Mas, Påvel G Lindberg","doi":"10.1186/s12984-025-01735-4","DOIUrl":"10.1186/s12984-025-01735-4","url":null,"abstract":"<p><strong>Background: </strong>Daily manual tasks require cognitive-motor interactions. There is limited research on cognitive-motor dual-tasks involving the upper extremity. In this study we used a manual visuomotor dual-task to measure post-stroke cognitive-motor impairments. Given previous evidence of impaired cognitive-motor interaction in stroke we hypothesized that the presence of enhanced dual-task cognitive load will impact motor performance in stroke patients. We also hypothesized that this dual-task effect would be greater in stroke patients compared to healthy controls. We also explored whether cognitive-motor impairments observed in these single- and dual-task conditions would relate to deficits in manual dexterity.</p><p><strong>Methods: </strong>30 chronic stroke participants (29.77 ± 35.39 months post-stroke) with mild-to-moderate hemiparesis without cognitive impairment (global screening test) and 30 age-matched healthy subjects performed a visuomotor grip force-tracking task in single- and dual-task conditions, requiring divided attention (resisting visual distraction) and working memory (mental addition of transiently displayed numbers). Gaze was simultaneously recorded to probe cognitive performance through saccades. Dexterity impairments were separately quantified using a kinetic device.</p><p><strong>Results: </strong>Stroke patients had increased visuomotor tracking error but did not show significantly increased change in visuomotor tracking error during the dual-task, with no significant difference between single task condition vs. divided attention or vs. working memory dual-task conditions. In contrast, age-matched healthy controls did show the expected difference with significantly higher dual-task force-tracking error. The between-group analysis only revealed a significant group difference (Stroke vs. Control) with stroke patients producing twice as much tracking error in both single and dual-task conditions. Stroke participants showed significantly reduced dual-task saccade modulation, with a reduced difference in saccades to displayed numbers (similar in both groups) vs. to distractors (higher in stroke) (median ± IQR: stroke 14.6 ± 18.75%; controls: 26.4 ± 32.41%). Non-inhibited saccades to distractors explained certain dexterity group differences (force control and timing of finger movements).</p><p><strong>Conclusion: </strong>The visuomotor force-tracking error, although increased, did not show enhanced cognitive-motor interaction in stroke. However, the task-related saccade analysis did detect impaired divided attention post-stroke, that may contribute to impaired dexterity, particularly in tasks requiring on-line sensorimotor integration. Upper limb dual-tasking practice may be relevant for engaging attention and enhancing post-stroke activities in daily life. Trial registration ClinicalTrials.gov ID NCT05454748.</p>","PeriodicalId":16384,"journal":{"name":"Journal of NeuroEngineering and Rehabilitation","volume":"22 1","pages":"212"},"PeriodicalIF":5.2,"publicationDate":"2025-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12512275/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145274568","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Differentiating post-stroke patients from healthy individuals via vision-based skeleton-optical fusion.","authors":"Xiao Han, Ziyan Wang, Liping Li, Kongfa Hu","doi":"10.1186/s12984-025-01726-5","DOIUrl":"10.1186/s12984-025-01726-5","url":null,"abstract":"<p><strong>Background: </strong>At present, the analysis of abnormal gait in post-stroke patients predominantly relies on wearable devices. However, with the advancements in computer vision technology, the integration of deep learning algorithms has introduced new possibilities for research. In particular, multi-modal fusion technology can effectively combine various modalities obtained through vision-based approaches, enabling more comprehensive and accurate representation of abnormal gait information in post-stroke patients.</p><p><strong>Methods: </strong>The study recruited 70 post-stroke patients and 70 healthy individuals to capture video recordings of their gait. We used Human Pose Estimation (HPE) to extract skeleton points from each frame and computed the optical flow information of these points and the corresponding angular variations of the lower limbs. Additionally, depth space features were extracted using ResNet-50 and subsequently integrated. For classification, a Long Short-Term Memory (LSTM) network was employed to analyze the fused features.</p><p><strong>Results: </strong>To evaluate the effectiveness of the feature extraction method, we tested it on both an open dataset and a self-collected clinical dataset, comparing it with CNN-RNN and Vision Transformer (ViT). The results from the LSTM network, after inputting the fused features, demonstrated optimal performance with 2 layers and 128 hidden units, achieving accuracies of 0.8794±0.0447 and 0.8778±0.0347, respectively.</p><p><strong>Conclusion: </strong>It was found that optical flow information calculated based on skeleton points, combined with variations in knee flexion and ankle dorsiflexion angles, improved the interpretability of the analytical framework. This improvement enables clinicians to gain a clearer understanding of the model's decision-making process, thereby increasing their confidence in its outputs. By employing a multi-modal fusion approach, information from different modalities is integrated, which not only broadens the analytical perspectives but also facilitates clinicians' deeper insights into the patient's gait characteristics.</p>","PeriodicalId":16384,"journal":{"name":"Journal of NeuroEngineering and Rehabilitation","volume":"22 1","pages":"209"},"PeriodicalIF":5.2,"publicationDate":"2025-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12509394/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145258439","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Superior efficacy of 100-Hz transcutaneous electrical nerve stimulation in reducing post-stroke spasticity: a systematic review and meta-analysis.","authors":"Yingxiu Diao, Xiaomin Niu, Jiahao Huang, Chong You, Xiaoying Lin, Jiaxin Pan, Jianghua Cheng","doi":"10.1186/s12984-025-01744-3","DOIUrl":"10.1186/s12984-025-01744-3","url":null,"abstract":"<p><strong>Background: </strong>Post-stroke spasticity is a prevalent complication of upper motor neuron injury, hindering motor recovery, independence, and quality of life. Transcutaneous electrical nerve stimulation (TENS) has been proposed as a non-invasive strategy to modulate neural excitability and reduce spasticity. However, its clinical efficacy remains uncertain due to heterogeneity in stimulation protocols and patient characteristics. This systematic review and meta-analysis aimed to assess the overall effectiveness of TENS in managing post-stroke spasticity and to examine potential differences in outcomes across stimulation frequencies and stroke phases.</p><p><strong>Methods: </strong>Databases searched included PubMed, Embase, Web of Science, Scopus, PEDro, and the Cochrane Library up to March 2025. The primary outcome was spasticity severity, assessed using the Modified Ashworth Scale (MAS) or Composite Spasticity Score (CSS). Subgroup analyses were conducted by stimulation frequency and stroke stage. Standardized mean differences (SMDs) were calculated using a random-effects model. Risk of bias was assessed using the Cochrane RoB 2.0 tool.</p><p><strong>Results: </strong>Seventeen randomized controlled trials (RCTs) involving 913 participants were included. TENS significantly reduced post-stroke spasticity compared to controls (SMD = - 0.64; 95% CI: - 0.91 to - 0.37; P < 0.001; I² = 69%). Subgroup analysis revealed the greatest effect in the acute phase (SMD = - 1.77), followed by subacute (SMD = - 0.61) and chronic phases (SMD = - 0.44) (p for subgroup difference < 0.001). TENS at 100 Hz yielded significant improvement (SMD = - 0.69), whereas lower frequencies (< 100 Hz) did not reach statistical significance. However, between-frequency group differences were not statistically significant (P = 0.67). Sensitivity analyses confirmed the robustness of the findings. Egger's test suggested potential publication bias (P = 0.008).</p><p><strong>Conclusions: </strong>TENS is a safe and effective intervention for reducing post-stroke spasticity, especially when applied during the acute phase. High-frequency stimulation at 100 Hz may confer greater benefits, though further standardized studies are needed to validate optimal parameters and timing. These results support the early incorporation of 100 Hz TENS into comprehensive stroke rehabilitation protocols. PROSPERO registration number: CRD 420251029133.</p>","PeriodicalId":16384,"journal":{"name":"Journal of NeuroEngineering and Rehabilitation","volume":"22 1","pages":"210"},"PeriodicalIF":5.2,"publicationDate":"2025-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12512259/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145258444","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}