IEEE Transactions on Neural Systems and Rehabilitation Engineering最新文献

{"title":"AI-driven correction of video-derived gait kinematics in healthy older adults.","authors":"Shuaijie Wang, Tanvi Bhatt","doi":"10.1109/TNSRE.2026.3743712","DOIUrl":"https://doi.org/10.1109/TNSRE.2026.3743712","url":null,"abstract":"<p><p>Video-based gait analysis offers a cost-effective and scalable method for remotely assessing human walking patterns. However, issues such as noise and joint misidentification in the video-based gait analysis severely reduce its precision, particularly during perturbed walking (PW) in older adults. To address this challenge, this study developed and validated an automated correction method to enhance the accuracy of the video-based approach in gait analysis. Perturbed (slip) and unperturbed walking (UPW) trials were collected from 307 healthy older adults for model development, and another 126 healthy older adults were used for evaluation. Joint kinematics (segment angles) were calculated and compared across three methods: gold standard methods using data from motion capture system (Mocap), conventional video-based gait analysis (Video), and video-based gait analysis with proposed gait correction model (Model). Intra-class correlations (ICC) and RMSE were used to assess the agreement of Video-angle and Model-angle compared to Mocap-angle. Results indicated that Video-angle alone showed moderate reliability (ICC 0.66-0.77) during PW and good reliability (ICC 0.77-0.85) during UPW compared to Mocap-angle. The developed automated correction model could significantly improve the ICC by an average of 0.082 for both trial types, leading to good to excellent reliability (ICC 0.73-0.85 for PW and 0.87-0.92 for UPW). This study provides insights into optimizing video-based gait analysis protocols and proposes potential solutions to enhance accuracy and applicability for assessing mobility and fall risk in older populations.</p>","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"PP ","pages":""},"PeriodicalIF":6.6,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149193227","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":"EMG-Driven Phase-Locked Spinal Cord Stimulation Physiologically Modulates Essential Tremor.","authors":"M Sacristan-Moraleda, A Carrasco-Robledo, M Gonzalez-Garcia, A Latorre, L Rocchi, A Ortega, E Rocon, V Gimenez De Bejar, M Ruiz-Ortiz, J Lapena-Moltiva, J Benito-Leon, D Farina, J Lazaro, A Pascual-Valdunciel, J Ibanez","doi":"10.1109/TNSRE.2026.3742629","DOIUrl":"https://doi.org/10.1109/TNSRE.2026.3742629","url":null,"abstract":"<p><p>Essential tremor (ET) is the most prevalent movement disorder, yet existing pharmacological and surgical treatments often lack efficacy or involve significant risks. Phase-locked neuromodulation offers a targeted approach to disrupt pathological oscillations, but its implementation through non-invasive spinal cord stimulation (tSCS) has remained largely unexplored. In this study, we present a novel closed-loop tSCS framework for ET based on real-time tremor phase estimation from surface electromyography (EMG). The system implements a Fourier Linear Combiner (FLC) algorithm to track the demodulated EMG signal sample-by-sample, enabling short-latency stimulation delivery while mitigating the phase lag inherent in traditional filtering or decomposition methods. The framework was validated in ET patients performing an isometric precision pinching task, with stimulation delivered across eight equidistant phases of the tremor cycle. The results demonstrate the technical feasibility of the system, which achieved a peak-to-trough tremor amplitude modulation of approximately 20% relative to the trial mean. Furthermore, the observation of phase-dependent frequency modulation in a small subset of participants suggested that tSCS may interact with tremorgenic timing mechanisms via spinal afferent pathways without compromising voluntary motor control. These findings provide an initial demonstration that closed-loop tSCS can produce phase-dependent modulation of tremor in individual patients, where physiological modulation is driven by the precise temporal synchronization of stimuli with the patient's underlying neurophysiology.</p>","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"PP ","pages":""},"PeriodicalIF":6.6,"publicationDate":"2026-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149181616","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":"WPTNet-WPL: A Wave-Prior Transformer with Wasserstein Prior Learning for Interpretable Auditory Brainstem Response Assessment.","authors":"Ke Zhang, Haowen Pan, Zenan Li, Yongchao Chen, Shang Yan, Desheng Jia, Fei Chen, Juanjuan Li, Michael Chi Fai Tong, Mingxing Zhu, Xianhai Zeng, Shixiong Chen","doi":"10.1109/TNSRE.2026.3743175","DOIUrl":"https://doi.org/10.1109/TNSRE.2026.3743175","url":null,"abstract":"<p><p>Auditory brainstem response (ABR) testing typically relies on repeated recordings under multiple sound pressure level (dB) conditions and manual interpretation based on clinical experience. This approach suffers from significant subjectivity, time-consuming procedures, and poor consistency in results, thereby limiting its feasibility for conducting high-frequency, long-term, objective assessments within auditory rehabilitation settings. To address these limitations, this study proposes a deep neural network framework integrating clinical latency priors with adaptive optimal transport regularization, termed the Wave-Prior Transformer Network with Wasserstein Prior Learning (WPTNet-WPL). The framework performs binary normal/abnormal classification and five-class hearing-threshold classification from an ABR recording averaged over 1024 sweeps at a single stimulus intensity within the studied 10-100 dB nHL range. Its prediction target is the hearing-threshold category rather than the location of an individual ABR wave peak. The model first employs a one-dimensional convolutional network to extract local waveform features from ABR waveforms. The Dynamic Weighted Prior Attention (DWPA) mechanism then uses canonical Wave I, Wave III, and Wave V latency windows as soft physiological anchors. These anchors guide attention toward physiologically plausible ABR latency regions while preserving data-driven temporal features relevant to threshold classification. Furthermore, the proposed Wasserstein Prior Learning (WPL) module dynamically adjusts the Gaussian mixture prior distribution based on optimal transport theory, enabling adaptive alignment between the learned attention distribution and the physiological prior. This achieves synergistic optimization of prior knowledge and data-driven learning. Experimental results demonstrate that WPTNet-WPL achieves 90.29% accuracy in the binary classification task (normal/abnormal) and 82.26% accuracy in the five-class auditory threshold classification task, both significantly outperforming mainstream baseline models. The framework showed robust overall performance on single-intensity averaged ABR recordings acquired across the studied 10-100 dB nHL range. Auditory rehabilitation assessment and longitudinal functional monitoring remain potential future applications requiring prospective longitudinal validation across multiple centers.</p>","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"PP ","pages":""},"PeriodicalIF":6.6,"publicationDate":"2026-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149181588","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":"Effects of 4-Week Intervention Combining High-Definition Transcranial Direct Current Stimulation and Foot Core Exercise on Lower-Limb Joint Coordination Patterns and Variability.","authors":"Jiaxin Luo, Baofeng Wang, Bin Shen, Zhen Xu, Xuekai Zong, Xin Liang, Zhaohong Zeng, Weijie Fu","doi":"10.1109/TNSRE.2026.3742183","DOIUrl":"https://doi.org/10.1109/TNSRE.2026.3742183","url":null,"abstract":"<p><p>Coordination patterns and variability are key components of motor control. This study aimed to examine the effects of a 4-week high-definition transcranial direct current stimulation (HD-tDCS) combined with foot core exercise (FCE) on lower limb coordination patterns and variability during Y-balance test (YBT). Fifty-five healthy male participants were allocated to four groups by using randomization procedure (i.e., HD-tDCS + FCE, sham-tDCS + FCE, HD-tDCS, and FCE). Participants performed three YBT trials on the non-dominant (left) limb before and after a 4-week intervention (3 sessions/week, 20 min/session). The post-test reaching distance was matched to baseline performance to minimize the effect of variations in reaching distance on movement kinematics. A modified vector coding technique was used to characterize hip-ankle (H-A), hip-knee (H-K), and knee-ankle (K-A) coordination. In the posteromedial direction of YBT, the sagittal-plane H-K coupling demonstrated an increase in in-phase coordination (10.89%, p = 0.013) and a reduction in proximal-dominant coordination (13.86%, p = 0.015) following the HD-tDCS + FCE intervention relative to baseline and the FCE group. Sagittal-plane K-A coordination variability increased (p = 0.001) and frontal-plane K-A coordination variability (p = 0.021) and transverse-plane H-K coordination variability decreased (p = 0.004) following the combined intervention. These changes were significantly greater than those observed after sham stimulation and single interventions. A 4-week intervention combining HD-tDCS and FCE modulated coordination patterns and induced plane-related changes in coordination variability, suggesting a synergistic effect and a potential neuromechanical basis for enhanced postural stability.</p>","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"PP ","pages":""},"PeriodicalIF":6.6,"publicationDate":"2026-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149169461","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":"Using Digital Twins to Predict Recovery and Decline in Neurological Disorders.","authors":"Swathi Kiran, Risto Miikkulainen","doi":"10.1109/TNSRE.2026.3740549","DOIUrl":"https://doi.org/10.1109/TNSRE.2026.3740549","url":null,"abstract":"<p><p>In this viewpoint, we describe how digital twins, individually configured computational models of a person's unique language learning history and neurological status, can be used to predict recovery and decline in neurological disorders, with a particular focus on their potential for neurorehabilitation. We first situate digital twins within the broader evolution of computational modeling research in cognitive science and neurorehabilitation. We then introduce BiLex, a digital twin framework that uses self-organizing maps (SOMs) to model bilingual language processing through interconnected semantic and phonetic representations for two languages, and we explain why bilingualism serves as both a rigorous test case for the methodology and a clinically important application. We then describe the neurorehabilitation applications of BiLex including modeling stroke and aphasia that include individual impairment profiles, recovery, treatment-response prediction, and selection of the optimal treatment language, as well as simulating progressive decline in dementia. We summarize that the framework offers theory-driven model construction to improve our understanding of neurorehabilitation. Digital twins represent a paradigm shift enabling individualized assessment, treatment planning, and progress monitoring in neurological rehabilitation.</p>","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"PP ","pages":""},"PeriodicalIF":6.6,"publicationDate":"2026-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149109040","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":"Neuromuscular Adaptations in Degenerative Rotator Cuff Tears: Contributions of Aging and Pathology.","authors":"Jian-Ning Sun, Cai-Bin Dong, Miao-Qin Zhan, Liang Chen, De-Qing Hu, Nan Zheng, Han Li, Yun-Ru Ma, Yu-Rong Li, Peng Chen","doi":"10.1109/TNSRE.2026.3737618","DOIUrl":"10.1109/TNSRE.2026.3737618","url":null,"abstract":"<p><strong>Objective: </strong>Degenerative rotator cuff tear (RCT) is associated with impaired shoulder function; however, the extent to which altered neuromuscular coordination reflects aging-related changes or pathology-associated alterations remains unclear. This study aimed to characterize shoulder neuromuscular coordination patterns associated with aging and degenerative RCT using a multidimensional electromyographic approach.</p><p><strong>Methods: </strong>Surface electromyography was recorded from eight shoulder-related muscles during maximal shoulder abduction and flexion tasks in 106 participants, including young controls (YC, n=24), elderly controls (EC, n=24), and patients with degenerative RCT (n=58). Muscle synergy characteristics were quantified using non-negative matrix factorization (NMF). Intermuscular coordination was assessed using beta-band coherence analysis, and muscle interaction patterns were further evaluated using network topology metrics.</p><p><strong>Results: </strong>Compared with YC participants, both EC and RCT groups demonstrated reduced muscle synergy dimensionality, with no significant differences between EC and RCT groups. Synergy structure analyses revealed task-dependent differences among groups, and RCT participants exhibited coordination patterns partially similar to those observed in elderly controls. Intermuscular coherence and network analyses demonstrated group-specific alterations mainly during shoulder abduction, involving deltoid-related and deltoid-scapular muscle interactions. These findings suggest that degenerative RCT is associated with altered muscle coordination patterns superimposed on age-related neuromuscular changes.</p><p><strong>Conclusion: </strong>This study provides a comprehensive characterization of age- and pathology-associated alterations in shoulder neuromuscular coordination. The integration of muscle synergy, coherence, and network analyses may provide quantitative insights into functional impairment mechanisms in degenerative RCT and support future development of individualized rehabilitation strategies.</p>","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"PP ","pages":""},"PeriodicalIF":6.6,"publicationDate":"2026-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149060701","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":"A Case Study Characterizing Healthy & Post-Stroke Neuromotor Behavior During 6D Upper-Limb Isometric Gaming: Implications for Design of End-Effector Rehabilitation Robot Interfaces.","authors":"Ajay Anand, Gabriel Parra, Chad A Berghoff, Laura A Hallock","doi":"10.1109/TNSRE.2026.3737040","DOIUrl":"10.1109/TNSRE.2026.3737040","url":null,"abstract":"<p><p>Successful robot-mediated rehabilitation requires designing games and robot interventions that pro- mote healthy motor practice. However, the interplay between a given user's neuromotor behavior, the gaming interface, and the physical robot makes designing system elements - and even characterizing what behaviors are \"healthy\" or pathological - challenging. We leverage our OpenRobotRehab 1.0 open access data set to explore the characteristics of 13 healthy and 2 post-stroke users' force output, muscle activations, and game performance while executing isometric trajectory tracking tasks using an end-effector rehabilitation robot. We present an assessment of how subtle aspects of interface design impact user behavior; an exploratory analysis of how pathological neuromo- tor behaviors are reflected in end-effector force dynamics; and a novel hidden Markov model (HMM)-based neuro-motor behavior classification method based on surface electromyography (sEMG) signals during cyclic motions. We demonstrate that task specification (including which axes are constrained and how users interpret tracking instructions) shapes user behavior; that pathology-related features are detectable in 6D end-effector force data during isometric task execution, but that healthy neuromotor strategies are heterogeneous and inherently difficult to characterize; and that our HMM-based models discriminate healthy and post-stroke neuromotor dynamics where synergy-based decompositions reflect no such differentiation. Lastly, we discuss these results' implications for the design of adaptive end-effector rehabilitation robots capable of promoting healthier movement strategies across diverse user populations.</p>","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"PP ","pages":""},"PeriodicalIF":6.6,"publicationDate":"2026-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149030380","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":"Edge-Based Vision-Language Assistive System for the Visually Impaired: A Quantized VLM Approach.","authors":"Batyr Arystanbekov, Huseyin Atakan Varol, Adnan Yazici","doi":"10.1109/TNSRE.2026.3696447","DOIUrl":"https://doi.org/10.1109/TNSRE.2026.3696447","url":null,"abstract":"<p><p>This paper presents a novel edge-deployable assistive system for visually impaired individuals, powered by vision-language models (VLMs). Existing cloud-based solutions for image captioning suffer from latency, dependency on internet connectivity, and overly simplistic scene descriptions that fail to convey the rich contextual information needed for meaningful real-world navigation. To address these challenges, we propose a self-contained, wearable system that performs real-time scene interpretation on-device without cloud reliance. The system integrates a quantized version of the LLaVA-NeXT-13B VLM with speech recognition (Whisper) and speech synthesis (PIPER), running on an NVIDIA Jetson Orin NX and Raspberry Pi-based input module. Our framework emphasizes intuitive user interaction through a button-based interface and Bluetooth audio output, minimizing cognitive load. We validate the quantization approach through large-scale benchmarks, such as VizWiz-VQA and VQAv2, demonstrating minimal accuracy degradation (2.6% and 0.9%, respectively) compared to the original model. User evaluations involving 28 participants compared the system to a baseline image captioning model. Objective results demonstrated a 25% increase in image identification accuracy. The system achieved high usability scores and maintained practical latency (4-5 seconds per query), supporting real-world feasibility. This work advances the development of scalable, interpretable, and accessible AI-driven assistive technologies, enabling greater independence and interaction for the visually impaired.</p>","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"PP ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148015396","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":"Simulation-Driven Exoskeleton Control: Predicting Soft Pneumatic Gel Muscle Actuator Assistance to Reduce Metabolic Cost at Different Walking Speeds","authors":"Gunarajulu Renganathan;Israel Luis;Elena M. Gutierrez-Farewik;Mitsunori Tada;Yuichi Kurita","doi":"10.1109/TNSRE.2026.3671348","DOIUrl":"10.1109/TNSRE.2026.3671348","url":null,"abstract":"Wearable exoskeletons have emerged as a solution to enhance locomotion in individuals with impairments and/or weakness. Assistive devices with pneumatic gel muscle actuators (PGMs) are promising for daily use due to their high power-to-weight ratio and compliant structure, enabling potentially easy integration into smart garments. The intrinsic properties of PGMs have been studied over the past decade; however, little is known about how to leverage their dynamics to effectively and optimally assist motion. In this study, we modeled hip joint assistance via two PGMs at each user’s leg and employed musculoskeletal simulations to predict optimal assistive strategies that reduce metabolic costs during walking at various speeds. Specifically, we implemented a bilevel optimization framework to identify optimal control parameters: stiffness, onset time, and duration, under two control modes: coupled and independent, at three actuator placements: medial, neutral, and lateral, relative to the user’s hip joint center. Our results showed that, across walking speeds, PGM actuators with coupled control mode reduced estimated metabolic cost by 5.3–16.0% and with independent control mode by 10.5–17.5%. We also identified that PGM assistance with medial placement with coupled control mode offered the best trade-off between control simplicity and potential metabolic savings at slow walking speeds, which might be particularly useful for enhancing mobility in older adults and in rehabilitation settings. Also, our simulation suggested that neutral placement tended to outperform other actuator placements across speeds in terms of metabolic savings. Future experimental studies may benefit from guiding exoskeleton control as per the predicted assistive strategies in this work.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"34 ","pages":"1457-1469"},"PeriodicalIF":5.2,"publicationDate":"2026-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11423896","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147369219","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":"Effects of Mechanical Perturbation Magnitude on Human Gait Entrainment","authors":"Omik M. Save;Sidhant Das;Evan Carlson;Anna Kruse;Jooeun Ahn;Hyunglae Lee","doi":"10.1109/TNSRE.2026.3670885","DOIUrl":"10.1109/TNSRE.2026.3670885","url":null,"abstract":"Gait entrainment is a relatively new robot-aided rehabilitation approach, and its underlying mechanisms remain underexplored. Investigating how different periodic perturbation parameters influence entrainment characteristics could help bridge this knowledge gap and improve gait rehabilitation protocol designs. This study examines the effect of varying magnitudes of periodic mechanical perturbations on gait entrainment characteristics in lower extremity joints during walking, such as success rate, phase variability, and onset latency. Two distinct soft robotic devices were utilized to perturb the ankle and hip joints, with perturbation magnitudes controlled by adjusting the actuator pressure. Fifteen healthy participants performed walking tasks in separate studies for each joint, with each device perturbing the respective joint at predetermined magnitudes. In the ankle study, a perturbation magnitude corresponding to 3.4% of the peak ankle torque achieved a consistently high entrainment success rate (75.6%). Similarly, in the hip study, a perturbation magnitude equivalent to 7.8% of the peak hip torque yielded a high entrainment success rate (80.0%). Both studies exhibited plateauing trends in entrainment success rate, phase variability, and onset latency, indicating that increases beyond their respective critical magnitude thresholds did not lead to further improvements. These results may be attributed to the recruitment of somatosensory feedback networks as well as mechanisms for optimizing mechanical assistance, which are not necessarily mutually exclusive. Identifying these magnitude thresholds provides a foundation for developing personalized rehabilitation protocols aimed at enhancing neuromotor learning through consistent gait entrainment.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"34 ","pages":"1438-1447"},"PeriodicalIF":5.2,"publicationDate":"2026-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11422280","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147365175","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}