IEEE Transactions on Neural Systems and Rehabilitation Engineering最新文献

{"title":"A Novel Adaptive Propulsion Enhancement eXperience (APEX) System: Development and Preliminary Validation for Enhancing Gait Propulsion in Stroke Survivors","authors":"Seoung Hoon Park;Hyunje Park;Jooeun Ahn;Beom-Chan Lee","doi":"10.1109/TNSRE.2025.3560324","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3560324","url":null,"abstract":"This study presents the development and preliminary validation of a novel system, called APEX (Adaptive Propulsion Enhancement eXperience), which aims to enhance gait propulsion in stroke survivors. The APEX system utilizes a dual-belt instrumented treadmill capable of measuring ground reaction forces and modulating belt speed in real time to provide visual biofeedback with dynamic propulsion promotion. We developed two propulsion promotion modes: the propulsion-facilitating mode, which extends ground contact time to elicit intrinsic propulsive effort and the propulsion-augmenting mode, which increases propulsive force by applying controlled external force. Ten chronic-stage stroke survivors (7 females and 3 males; age: <inline-formula> <tex-math>$61.40~pm ~6.96$ </tex-math></inline-formula> years) completed two experimental trials: one with the propulsion-facilitating mode, and the other with the propulsion-augmenting mode. Each trial included a baseline period without assistance (visual biofeedback and propulsion promotion) for 30 steps, a training period with assistance for 100 steps, and a post-training period without assistance for 30 steps. For each period, outcome measures (propulsive force, impulse, lower-limb kinematics, and muscle activity) were quantified. Statistical analysis revealed significant improvements in propulsive force, impulse, lower-limb kinematics, and muscle activity during both the training and post-training periods compared to the baseline period, with no significant differences between the training and post-training periods. These findings demonstrate the efficacy and reliability of the APEX system in delivering real-time, adaptive training to enhance gait propulsion. Integrating the APEX system into clinical practice has the potential to provide a scalable, patient-specific approach for post-stroke gait rehabilitation.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"1486-1496"},"PeriodicalIF":4.8,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10964362","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143888392","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":"Temporal Evolution of Frontal Plane Center-of-Mass Transfer Asymmetry in Post-Stroke Gait","authors":"Keng-Hung Shen;Robert Lee;Hao-Yuan Hsiao","doi":"10.1109/TNSRE.2025.3559857","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3559857","url":null,"abstract":"In typical human gait, the body center-of-mass (CoM) is cyclically transferred towards and supported by each lower extremity. The magnitude of this CoM transfer can be quantified by measuring the minimum mediolateral distance between the CoM and the stance foot during each step. Individuals with hemiparesis due to stroke often show a reduced and more variable CoM transfer magnitude in paretic versus non-paretic steps, which are linked to slower walking speeds and an increased risk of falling. While the commonly observed wider and more variable paretic foot placement at initial contact likely contributes to such frontal plane CoM transfer abnormalities, other factors could continue to adjust the CoM transfer magnitude after initial contact. To understand how the CoM transfer magnitude evolves throughout the transfer process, we derived an inverted-pendulum-based equation that projects the experimentally measured instantaneous mediolateral CoM position and velocity to the CoM transfer magnitude. We first validated our derived equation by demonstrating that CoM transfer magnitude can be predicted by the CoM position and velocity at the end of the double support phase with passive inverted pendulum dynamics. We then investigated how the asymmetry of this projected CoM transfer magnitude between the paretic and non-paretic steps evolves during the transfer process. Our findings revealed that about 54% of the transfer magnitude asymmetry was established at initial contact, predominantly influenced by foot placement, while another 38% was established during the double support phase, partly due to reduced work input from the non-paretic trailing limb. Additionally, the variability in transfer magnitude was augmented during the double support phase in paretic steps. Overall, the present study introduces a physics-based method capable of predicting CoM transfer magnitude in advance of its completion, and our findings highlight the significant contribution of the double support phase, which was previously less explored, to the asymmetries in CoM transfer magnitude and variability. Our results suggest that biomechanical factors during this phase, such as trailing limb work input, could be critical targets for future research and therapeutic interventions.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"1427-1438"},"PeriodicalIF":4.8,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10962267","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143848802","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":"The Footropter: A Passive Prosthetic Prescription Tool With Adjustable Forefoot and Hindfoot Stiffness","authors":"Harrison L. Bartlett;Brittany M. Moores;Brian E. Lawson;Max K. Shepherd","doi":"10.1109/TNSRE.2025.3559253","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3559253","url":null,"abstract":"Commercially available prosthetic feet are fabricated to have a fixed forefoot and hindfoot stiffness that cannot be changed in a clinical setting. This does not allow for patients to quickly compare multiple prosthetic foot stiffnesses to choose the stiffness they like the most while walking. In this paper, we present the Footropter, a passive prosthetic foot prescription tool that allows Certified Prosthetists (CPs) to rapidly change both the forefoot and hindfoot stiffnesses. The forefoot stiffness is changed by repositioning a spring clamp along a length of unbonded fiberglass layers and the hindfoot stiffness is changed by repositioning a single heel spring support. We introduce the design and working principles, characterize the ranges of available forefoot and hindfoot stiffnesses, and demonstrate the utility of the Footropter through two preference and perception studies with two unilateral transtibial prosthesis users. The Footropter, when paired with a preference optimization algorithm, can enable CPs to integrate patients’ experiential input into the clinical prescription process.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"1439-1448"},"PeriodicalIF":4.8,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10960312","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143860910","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":"Performance of Two Different Targeted Muscle Reinnervation Approaches for Improving Myoelectric Prosthetic Control","authors":"Jianping Huang;Xiangxin Li;Jingjing Wei;Chuanxin M. Niu;Guanglin Li","doi":"10.1109/TNSRE.2025.3558292","DOIUrl":"10.1109/TNSRE.2025.3558292","url":null,"abstract":"Targeted Muscle Reinnervation (TMR) is a surgical approach that can produce a neural-machine interface to provide additional electromyography (EMG) signals in intuitive control of myoelectric prostheses for high-level limb amputees. Clinically, TMR interface can be built by two types of surgical protocols. The first surgical protocol is to transfer a residual nerve to a denervated targeted muscle using a nerve-to-muscle suture and another is to anastomose a residual nerve to a targeted nerve via a nerve-to-nerve suture. Currently, it still remains unknown which surgical protocol would be more suitable for their clinical applications. In this study, a comparative investigation of the two TMR protocols was conducted by using animals and their performance in reconstructing EMG signals was evaluated. For nerve-to-muscle animal model, the proximal end of ulnar nerve was implanted onto denervated biceps brachii muscle and for nerve-to-nerve model, the proximal end of ulnar nerve was anastomosed to the distal end of musculocutaneous nerve. Post-surgery EMG signals were collected from all the TMR animals. Our results showed that the amplitudes of EMG signals gradually increased for the animals in the two TMR protocols over time, with an obvious difference between nerve-to-muscle and nerve-to-nerve animals. The signal-to-noise ratio and the centroid frequency of EMG signals in nerve-to-muscle animals were notably higher than those in nerve-to-muscle animals. These superior characteristics of the postoperative EMG signals demonstrated that nerve-to-nerve surgical protocol would be better than nerve-to-muscle in reconstructing EMG signals. The findings of this animal study suggest that both the TMR surgical protocols could be useful in providing additional EMG signals for myoelectric control, while the nerve-to-nerve suture would outperform the nerve-to-muscle suture in the quality and the appearance of the reconstructed extra EMG signals.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"1392-1399"},"PeriodicalIF":4.8,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10951106","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143811269","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":"Derivative-Guided Dual-Attention Mechanisms in Patch Transformer for Efficient Automated Recognition of Auditory Brainstem Response Latency","authors":"Yin Liu;Huanghong Sun;Qiang Li;Kangkang Li;Xinxing Fu;Hao Zhu;Tiecheng Song;Yue Zhao;Tiantian Wang;Chenqiang Gao","doi":"10.1109/TNSRE.2025.3558730","DOIUrl":"10.1109/TNSRE.2025.3558730","url":null,"abstract":"Accurate recognition of auditory brainstem response (ABR) wave latencies is essential for clinical practice but remains a subjective and time-consuming process. Existing AI approaches face challenges in generalization, complexity, and semantic sparsity due to single sampling-point analysis. This study introduces the Derivative-Guided Patch Dual-Attention Transformer (Patch-DAT), a novel, lightweight, and generalizable deep learning (DL) model for the automated recognition of latencies for waves I, III, and V. Patch-DAT divides the ABR time series into overlapping patches to aggregate semantic information, better capturing local temporal patterns. Meanwhile, leveraging the fact that ABR waves occur at the zero crossing of the first derivative, Patch-DAT incorporates a first derivative-guided dual-attention mechanism to model global dependencies. Trained and validated on large-scale, diverse datasets from two hospitals, Patch-DAT (with a size of 0.36 MB) achieves accuracies of 92.29% and 98.07% at 0.1 ms and 0.2 ms error scales, respectively, on a held-out test set. It also performs well on an independent dataset with accuracies of 88.50% and 95.14%, demonstrating strong generalization across clinical settings. Ablation studies highlight the contributions of the patching strategy and dual-attention mechanisms. Compared to previous state-of-the-art DL models, Patch-DAT shows superior accuracy and reduced complexity, making it a promising solution for object recognition of ABR latencies. Additionally, we systematically investigate how sample size and data heterogeneity affect model generalization, indicating the importance of large, diverse datasets in training robust DL models. Future work will focus on expanding dataset diversity and improving model interpretability to further improve clinical relevance.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"1865-1877"},"PeriodicalIF":4.8,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10955482","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143811268","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":"Enhancing and Optimizing User-Machine Closed-Loop Co-Adaptation in Dynamic Myoelectric Interface","authors":"Wei Li;Ping Shi;Sujiao Li;Hongliu Yu","doi":"10.1109/TNSRE.2025.3558687","DOIUrl":"10.1109/TNSRE.2025.3558687","url":null,"abstract":"Co-adaptation interfaces, developed through user-machine collaboration, have the capacity to transform surface electromyography (sEMG) into control signals, thereby enabling external devices to facilitate or augment the sensory-motor capabilities of individuals with physical disabilities. However, the efficacy and reliability of myoelectric interfaces in untrained environments over extensive spatial range have not been thoroughly explored. We propose a user-machine closed-loop co-adaptation strategy, which consists of a multimodal progressive domain adversarial neural network (MPDANN), an augmented reality (AR) system and a scenario-based dynamic asymmetric training scheme. MPDANN employs both sEMG and Inertial Measurement Unit (IMU) data using dual-domain adversarial training, with the aim of facilitating knowledge transfer and enabling multi-source domain adaptation. The AR system allows users to perform 10 holographic object repositioning tasks in a stereoscopic mixed reality environment using a virtual prosthesis represented as an extension of the residual limb. The scenario-based dynamic asymmetric training scheme, which employs incremental learning in MPDANN and incremental training in the AR system, enables the continuous updating and optimization of the system parameters. A group of non-disable participants and two amputees performed a five-day offline data collection in multiple limb position conditions and a five-day real-time holographic object manipulation task. The average completion rate for subjects utilizing MPDANN reached <inline-formula> <tex-math>${83}.{37}% pm {2}.{50}%$ </tex-math></inline-formula> on the final day, marking a significant improvement compared to the other groups. These findings provide a novel approach to designing myoelectric interfaces with cross-scene recognition through user-machine closed-loop co-adaptation.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"1673-1684"},"PeriodicalIF":4.8,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10955275","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143803130","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":"Optimized Temporal Interference Stimulation Based on Convex Optimization: A Computational Study","authors":"Chao Geng;Yang Li;Long Li;Xiaoqi Zhu;Xiaohan Hou;Tian Liu","doi":"10.1109/TNSRE.2025.3558306","DOIUrl":"10.1109/TNSRE.2025.3558306","url":null,"abstract":"Temporal interference (TI) stimulation is a non-invasive method targeting deep brain regions by applying two pairs of high-frequency currents with a slight frequency difference to the scalp. However, optimizing electrode configurations for TI via computational modeling is challenging and time-consuming due to the non-convex nature of the optimization. We propose a convex optimization-based method (CVXTI) for optimizing TI electrode configurations. We decompose the TI optimization into two convex steps, enabling rapid determination of electrode pair configurations. CVXTI accommodates various optimization objectives by incorporating different objective functions, thereby enhancing the focality of the stimulation field. Performance analysis of CVXTI shows superior results compared to other methods, particularly in deep brain regions. Subject variability analysis on four individuals highlights the necessity of customized stimulus optimization. CVXTI leverages the distribution characteristics of the TI envelope electric field to optimize electrode configurations, enhancing the optimization efficiency.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"1400-1410"},"PeriodicalIF":4.8,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10951111","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143803132","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":"Neuro-Modulation Analysis Based on Muscle Synergy Graph Neural Network in Human Locomotion","authors":"Ningjia Yang;Xuesi Li;Qi An;Jingsong Li;Shingo Shimoda","doi":"10.1109/TNSRE.2025.3557777","DOIUrl":"10.1109/TNSRE.2025.3557777","url":null,"abstract":"The coordination of muscles in human locomotion is commonly understood as the integration of motor modules known as muscle synergies. Recent research has delved into the adaptation of muscle synergies during the acquisition of new motor skills. However, the precise interplay between modulated muscle synergies during movement according to motion requirements remains unclear. Here, we aim to elucidate the alterations in locomotor synergies across various lower-limb motion strategies and motor tasks. Our findings reveal consistent weights of muscles in muscle synergies alongside varying timing activation aligned with specific motion requirements. It shows that spatial muscle synergies remain stable across different motor tasks, but humans adjusted the timing activation of these modules (temporal muscle synergies) to meet the motor requirements. To classify temporal muscle synergies and quantify connection weights for both self-connections and connections between muscle synergies, we employed a graph neural network. Our results demonstrate that muscle synergy 4, responsible for elevating the thigh to propel forward during the swing phase, experiences pronounced enhancement with changes in motion strategies. Furthermore, we observed a reduction in the self-connection of muscle synergy 2, implicated in stabilizing body posture, during motion tasks other than normal walking. Additionally, the connections between muscle synergy 2 and other synergies diminished, indicating more adaptation in muscle synergy 2 to achieve stabilization in more challenging motor tasks. The validity of these findings was verified through five-fold cross-validation, affirming the efficacy of our approach in elucidating neuro-modulation mechanisms in human locomotion. Our proposed methodology holds promising implications for the development of personalized training strategies, offering insights into the intricate interactions among different muscle synergies in accomplishing motor tasks.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"1381-1391"},"PeriodicalIF":4.8,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10949291","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143784465","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":"Explainable Depression Classification Based on EEG Feature Selection From Audio Stimuli","authors":"Lixian Zhu;Rui Wang;Xiaokun Jin;Yuwen Li;Fuze Tian;Ran Cai;Kun Qian;Xiping Hu;Bin Hu;Yoshiharu Yamamoto;Björn W. Schuller","doi":"10.1109/TNSRE.2025.3557275","DOIUrl":"10.1109/TNSRE.2025.3557275","url":null,"abstract":"With the development of affective computing and Artificial Intelligence (AI) technologies, Electroencephalogram (EEG)-based depression detection methods have been widely proposed. However, existing studies have mostly focused on the accuracy of depression recognition, ignoring the association between features and models. Additionally, there is a lack of research on the contribution of different features to depression recognition. To this end, this study introduces an innovative approach to depression detection using EEG data, integrating Ant-Lion Optimization (ALO) and Multi-Agent Reinforcement Learning (MARL) for feature fusion analysis. The inclusion of Explainable Artificial Intelligence (XAI) methods enhances the explainability of the model’s features. The Time-Delay Embedded Hidden Markov Model (TDE-HMM) is employed to infer internal brain states during depression, triggered by audio stimulation. The ALO-MARL algorithm, combined with hyper-parameter optimization of the XGBoost classifier, achieves high accuracy (93.69%), sensitivity (88.60%), specificity (97.08%), and F1-score (91.82%) on a auditory stimulus-evoked three-channel EEG dataset. The results suggest that this approach outperforms state-of-the-art feature selection methods for depression recognition on this dataset, and XAI elucidates the critical impact of the minimum value of Power Spectral Density (PSD), Sample Entropy (SampEn), and Rényi Entropy (Ren) on depression recognition. The study also explores dynamic brain state transitions revealed by audio stimuli, providing insights for the clinical application of AI algorithms in depression recognition.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"1411-1426"},"PeriodicalIF":4.8,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10947765","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143772235","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":"Spike-Based Neuromorphic Model of Spasticity for Generation of Affected Neural Activity","authors":"Jin Yan;Qi Luo;Zhi Chen;Zeyu Wang;Xinliang Guo;Qing Xie;Denny Oetomo;Ying Tan;Chuanxin M. Niu","doi":"10.1109/TNSRE.2025.3557044","DOIUrl":"10.1109/TNSRE.2025.3557044","url":null,"abstract":"Spasticity is a common motor symptom that disrupt muscle contraction and hence movements. Proper management of spasticity requires identification of its origins and reasoning of the therapeutic plans. Challenges arise because spasticity might originate from elevated activity in both the cortical and sub-cortical pathways. No existing models (animal or computational) could cover all possibilities leading to spasticity, especially the peripheral causes such as hyperreflexia. To bridge this gap, this work develops a novel computational, spike-based neuromorphic model of spasticity, named NEUSPA. Rather than relying solely on a monosynaptic spinal loop comprising alpha motoneurons, sensory afferents, synapses, skeletal muscles, and muscle spindles, the NEUSPA model introduces two additional inputs: additive (ADD) and multiplicative (MUL). These inputs generate velocity-dependent EMG responses. The effectiveness of the NEUSPA model is validated using classic experiments from the literature and data collected from two post-stroke patients with affected upper-limb movements. The model is also applied to simulate two real-world scenarios that patients may encounter. Simulation results suggest that hyperreflexia due to extra inputs was sufficient to produce spastic EMG responses. However, EMG onsets were more sensitive to ADD inputs (slope =0.628, p <0.0001,> <tex-math>${}^{{2}} =0.96$ </tex-math></inline-formula>) compared to MUL inputs (slope =0.471, p <0.0001,> <tex-math>${}^{{2}} =0.92$ </tex-math></inline-formula>). Additionally, simulation of finger-pressing on a deformable object indicated that spasticity could increase the duration from 1.03s to 1.20s compared to a non-impaired condition. These results demonstrate that NEUSPA effectively synthesizes abnormal physiological data, facilitating decision-making and machine learning in neurorehabilitation.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"1360-1371"},"PeriodicalIF":4.8,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10947710","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143772237","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}