IEEE Transactions on Neural Systems and Rehabilitation Engineering最新文献

{"title":"Cortical Plasticity Induced by Pairing Primary Motor Cortex Transcranial Magnetic Stimulation With Subthalamic Nucleus Magneto-Acoustic Coupling Stimulation","authors":"Ruixu Liu;Ren Ma;Xiaoqing Zhou;Xin Wang;Jiankang Wu;Fangxuan Chu;Mingpeng Wang;Xu Liu;Yuheng Wang;Kai Zhu;Shunqi Zhang;Tao Yin;Zhipeng Liu","doi":"10.1109/TNSRE.2025.3565258","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3565258","url":null,"abstract":"Paired cortical and deep stimulation has the potential to induce enhanced cortical plasticity. Ideally, such stimulation should be noninvasive and precisely controlled. A novel paired stimulation method, combining transcranial magnetic stimulation (TMS) with transcranial magneto-acoustic coupled stimulation (TMAS), named TMS–TMAS, was proposed to achieve such stimulations. Although the primary motor cortex (M1) is stimulated using TMS, the pulsed magnetic field is coupled with a focused ultrasound field to achieve TMAS-based focused electrical stimulation of the subthalamic nucleus (STN) via the magneto-acoustic coupling effect. Cortical plasticity is induced by precisely controlling the timing of magnetic pulse and ultrasound emissions based on spike timing-dependent plasticity (STDP). The experimental system achieved cortical-focused magnetic stimulation with a transverse resolution of 4.3 mm, a longitudinal resolution of 2.8 mm, and a magnetic field intensity of 1.6 T in the M1 region. Additionally, deep-focused electrical stimulation with a transverse resolution of 1.6 mm, a longitudinal resolution of 9.9 mm, and a coupled electric field intensity of 280 mV/m in the STN region was realized. In vivo animal experiments demonstrated that TMS–TMAS enhanced the amplitude of motor evoked potential (MEP) and reduced response latency. Simulation and experimental results confirmed that TMS–TMAS achieves high spatial resolution, noninvasive paired stimulation of the cortex and deep nuclei, and induces enhanced cortical plasticity when the stimulation sequence satisfies the STDP criteria. This method provides a promising approach for noninvasive paired stimulation and is expected to advance brain science research and the rehabilitation of neuropsychiatric disorders involving deep brain structures.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"1751-1762"},"PeriodicalIF":4.8,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10980113","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143925087","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":"Classification of Neuropsychiatric Disorders via Brain-Region-Selected Graph Convolutional Network","authors":"Zhenzhe Qin;Yongbo Li;Xiaoying Song;Li Chai","doi":"10.1109/TNSRE.2025.3565627","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3565627","url":null,"abstract":"For the classification of patients with neuropsychiatric disorders based on rs-fMRI data, this paper proposed a Brain-Region-Selected graph convolutional network (BRS-GCN). In order to effectively identify the most significant biomarkers associated with disease, we designed a novel ROI pooling score function. Additionally, we also designed a comprehensive loss function, including a group-level consistency loss function for preserving the same brain regions in subjects of the same category, and an anti-consistency function for maximizing brain region preservation differences between subjects of different categories. On the basis of the ROI graph, we directly incorporate the non-imaging information of the subjects in the network training. Experimental results on two public datasets, ABIDE and ADNI, validate the superiority of the model proposed in this paper, and the qualitative results of the biomarkers demonstrate the potential application of the model in medical diagnosis and treatment of neuropsychiatric disorders.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"1664-1672"},"PeriodicalIF":4.8,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10980138","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143925134","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":"Continuous Joint Kinematics Prediction Using GAT-LSTM Framework Based on Muscle Synergy and Sparse sEMG","authors":"Meiju Li;Zijun Wei;Zhi-Qiang Zhang;Shuhao Ma;Sheng Quan Xie","doi":"10.1109/TNSRE.2025.3565305","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3565305","url":null,"abstract":"sEMG signals hold significant potential for motion prediction, with promising applications in areas such as rehabilitation, sports training, and human-computer interaction. However, achieving robust prediction accuracy remains a critical challenge, as even minor inaccuracies in motion prediction can severely affect the reliability and practical utility of sEMG-based systems. In this study, we propose a novel framework, muscle synergy (MS)-based graph attention networks (MSGAT-LSTM), specifically designed to address the challenges of continuous motion prediction using sparse sEMG electrodes. By leveraging MS theory and graph-based learning, the framework effectively compensates for the limitations of sparse sEMG setups and achieves significant improvements in prediction accuracy compared to existing methods. Based on MS theory, the framework calculates cosine similarity between sEMG signal features from different muscles to assign edge weights, effectively capturing their coordinated contributions to motion. The proposed framework integrates GAT for relational feature learning with LSTM networks for temporal dependency modeling, leveraging the strengths of both architectures. Experimental results on the public dataset Ninapro DB2 and a self-collected dataset demonstrate that MSGAT-LSTM achieves superior performance compared to state-of-the-art methods, including the muscle anatomy and MS-based 3DCNN, GCN-LSTM, and classic models such as CNN-LSTM, CNN, and LSTM, in terms of RMSE and R2. Furthermore, experimental results reveal that incorporating MS into GCN reduces training time by 13% compared to GCN-LSTM, significantly enhancing computational efficiency and scalability. This study highlights the potential of integrating MS theory with graph-based deep learning methods for motion prediction based on sEMG.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"1763-1773"},"PeriodicalIF":4.8,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10980137","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143924960","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":"A Wearable Research System for Combined Cochleo-Vestibular Stimulation","authors":"David Lanthaler;Patrick P. Huebner;Matthew D. Parker;Andreas Griessner;Viktor Steixner;Clemens M. Zierhofer","doi":"10.1109/TNSRE.2025.3565136","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3565136","url":null,"abstract":"Cochlear implants (CI) are a well-established treatment option for patients with severe to profound hearing loss, while vestibular implant (VI) trials give a promising outlook for patients with severely impaired vestibular function. In a number of subjects these two conditions may also present together, necessitating treatment with a cochleo-vestibular implant (CVI). While the feasibility of CVIs has been demonstrated, no wearable processor has existed to provide target-specific, modulated stimulation for both systems over extended periods. We introduce a first wearable audio-motion processor (AMP) system designed to be used in conjunction with a CVI. We first present the architecture of the AMP, along with the possible modes of operation. We then use a testbench to show the functionality and limits of the presented device. Important performance characteristics of such a system are the latency between head movements and resulting vestibular stimulation pulses, and the deviations of stimulation amplitudes and pulse rates from a programmed transfer function (TF). The device was tested using amplitude- and rate-modulated vestibular pulses in response to predefined single-axis rotations performed on a rotary platform, while providing simultaneous auditory stimulation to cochlear electrodes. We were able to achieve a recorded latency comparable to the physiological response time of normal vestibular organs. The results for the TF showed that the measured values for the pulse rates and the amplitudes followed the reference values very accurately. This audio-motion processor is the world’s first wearable processor capable of delivering combined, specifically modulated cochlear and vestibular stimulation.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"1740-1750"},"PeriodicalIF":4.8,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10979432","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143925086","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 Neurodegenerative Disease Diagnosis Through Confidence-Driven Dynamic Spatio-Temporal Convolutional Network","authors":"Ning Yuan;Donghai Guan;Shengrong Li;Li Zhang;Qi Zhu","doi":"10.1109/TNSRE.2025.3564983","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3564983","url":null,"abstract":"Dynamic brain networks are more effective than static networks in characterizing the evolving patterns of brain functional connectivity, making them a more promising tool for diagnosing neurodegenerative diseases. However, existing classification methods for dynamic brain networks often rely on sliding windows to extract multi-window features, leading to suboptimal performance due to the spatio-temporal coupling on these windows and limited ability to effectively integrate complex topological features. To address these limitations, we propose a novel method called Confidence-Driven Dynamic Spatio-Temporal Convolutional Network (CD-DSTCN). First, our proposed method employs a spatio-temporal convolutional network integrated with a temporal attention mechanism to extract spatio-temporal features within each window. By propagating information across temporal windows during spatial convolution, the method effectively captures and integrates complex temporal and spatial dependencies. Second, each window generates an output probability, which quantifies prediction confidence based on the true class probability (TCP). This confidence score serves as a weight to assess the relative importance of different time windows. Finally, the confidence-weighted fused features are passed through a multilayer perceptron (MLP) for final classification. Extensive experiments on Alzheimer’s and Parkinson’s datasets show that the proposed method outperforms the state-of-the-art algorithms and can provide valuable biomarkers for brain disease diagnosis. Our code is publicly available at: <uri>https://github.com/YNingCode/CD-DSTCN</uri>","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"1715-1728"},"PeriodicalIF":4.8,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10979475","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143925270","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":"Fully Wireless Implantable Device Capable of Multichannel Neural Spike Recording and Stimulation for Long-Term Freely Moving Rodent Study","authors":"Minh Duc Hoang;Wonok Kang;Matthew Koh;Sung-Min Park","doi":"10.1109/TNSRE.2025.3564625","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3564625","url":null,"abstract":"Neural spike recordings provide detailed insights into the neuronal activity and serve as powerful feedback signals for closed-loop neuromodulation, which is gaining significant attention as a medical technology of the future. However, chronic preclinical evaluations of such innovations have been hindered by the tethering effects of traditional systems on naturalistic movements. Numerous untethered systems have currently promoted experiments in ambulatory animals but robust spike recording remains challenging. This study presents a fully wireless implantable device with a compact volume of 4.8 cm3, offering six-channel spike recording at 20 kHz which matches the performance of commercial benchtop systems and four-channel stimulation with <0.1% error for long-term freely moving rodent studies. Together with a 6.78-MHz magnetic resonance wireless power transfer technology, the device enables 2.4 GHz bidirectional wireless communication, ensuring stable data transmission up to 1.5 m with <0.1% data loss. The alumina ceramic-kovar hermetic sealing protects the electronics with minimal radiowave efficiency losses of 10% at 6.78 MHz and 0.1% at 2.4 GHz. Successful implantations in rats (n =5) demonstrate sustained spike recordings from the hippocampus over 60 days. Successful closed-loop seizure detection based on neural activity recording and suppression through an acute status epilepticus model highlight the potential of this device in chronic disease management applications.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"1621-1632"},"PeriodicalIF":4.8,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10978891","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143925269","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":"EEGUnity: Open-Source Tool in Facilitating Unified EEG Datasets Toward Large-Scale EEG Model","authors":"Chengxuan Qin;Rui Yang;Wenlong You;Zhige Chen;Longsheng Zhu;Mengjie Huang;Zidong Wang","doi":"10.1109/TNSRE.2025.3565158","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3565158","url":null,"abstract":"The increasing number of dispersed EEG dataset publications and the advancement of large-scale Electroencephalogram (EEG) models have increased the demand for practical tools to manage diverse EEG datasets. However, the inherent complexity of EEG data, characterized by variability in content data, metadata, and data formats, poses challenges for integrating multiple datasets and conducting large-scale EEG model research. To tackle the challenges, this paper introduces EEGUnity, an open-source tool that incorporates modules of \"EEG Parser\", \"Correction\", \"Batch Processing\", and \"Large Language Model Boost\". Leveraging the functionality of such modules, EEGUnity facilitates the efficient management of multiple EEG datasets, such as intelligent data structure inference, data cleaning, and data unification. In addition, the capabilities of EEGUnity ensure high data quality and consistency, providing a reliable foundation for large-scale EEG data research. EEGUnity is evaluated across 25 EEG datasets from different sources, offering several typical batch processing workflows. The results demonstrate the high performance and flexibility of EEGUnity in parsing and data processing. The project code is publicly available at github.com/Baizhige/EEGUnity.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"1653-1663"},"PeriodicalIF":4.8,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10979503","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143924962","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":"High-Order Graphical Topology Analysis of Brain Functional Connectivity Networks Using fMRI","authors":"Qinrui Ling;Aiping Liu;Yu Li;Taomian Mi;Piu Chan;B. T. Thomas Yeo;Xun Chen","doi":"10.1109/TNSRE.2025.3564293","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3564293","url":null,"abstract":"The brain connectivity network can be represented as a graph to reveal its intrinsic topological properties. While classical graph theory provides a powerful framework for examining brain connectivity patterns, it often focuses on low-order graphical indicators and pays less attention to high-order topological metrics, which are crucial to the comprehensive understanding of brain topology. In this paper, we capture high-order topological features via a graphical topology analysis framework for brain connectivity networks derived from functional Magnetic Resonance Imaging (fMRI). Several high-order metrics are examined across varying sparsity levels of binary graphs to trace the evolution of brain networks. Topological phase transitions are primarily investigated that reflect brain criticality, and a novel indicator called “redundant energy” is proposed to measure the chaos level of the brain. Extensive experiments on diverse datasets from healthy controls validate the reproducibility and generalizability of our framework. The results demonstrate that around critical points, classical graph theoretical indicators change sharply, driven by crucial brain regions that have high node curvatures. Further investigations on fMRI of subjects with and without Parkinson’s disease uncover significant alterations in high-order topological features which are further associated with the severity of the disease. This study provides a fresh perspective on studying topological architectures of the brain, with the potential to expand our comprehension on brain function in both healthy and diseased states.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"1611-1620"},"PeriodicalIF":4.8,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10977007","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143924954","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":"Probing Vestibular Function With Frequency- Modulated Electrical Vestibular Stimulation","authors":"Janita Nissi;Otto Kangasmaa;Ilkka Laakso","doi":"10.1109/TNSRE.2025.3564388","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3564388","url":null,"abstract":"Electrical vestibular stimulation (EVS) is a non-invasive technique used to affect the vestibular system. It disturbs the sense of balance and evokes false sensations of movement by modulating the firing rate of vestibular afferents. This study used frequency-modulated EVS (FM-EVS) combined with center-of pressure (CoP) measurements to investigate the strength-frequency relationship of the stimulation and the evoked responses. CoP responses to FM-EVS were measured for ten subjects. Stimulus waveforms composed of linear chirps were compared to the evoked CoP responses, producing estimates of the highest frequencies at which EVS affected the CoP for stimulation currents of 0.75, 1.0 and 1.5 mA. Latency was calculated as the delay between the CoP response and stimulus. In situ electric field in the vestibular system was determined using fifteen high-resolution anatomical head models using the finite element method. CoP responses were evoked at up to <inline-formula> <tex-math>$5.5~pm ~1.1$ </tex-math></inline-formula> Hz with 0.75 mA, <inline-formula> <tex-math>$8.2~pm ~1.1$ </tex-math></inline-formula> Hz with 1.0 mA, and <inline-formula> <tex-math>$10.5~pm ~1.2$ </tex-math></inline-formula> Hz with 1.5 mA. The vestibular electric field was <inline-formula> <tex-math>$175~pm ~23$ </tex-math></inline-formula> mVm<inline-formula> <tex-math>${}^{-{1}}$ </tex-math></inline-formula> per 1 mA current. The average latency of the response was <inline-formula> <tex-math>$86~pm ~17$ </tex-math></inline-formula> ms. The results provide insight into the strength-frequency dependency for EVS-evoked motion responses with estimates for the in situ electric field strength, which can be used for the future development of human electromagnetic field exposure guidelines or the design of both EVS and transcranial electrical brain stimulation studies.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"33 ","pages":"1707-1714"},"PeriodicalIF":4.8,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10976990","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143924955","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":"Intelligent Diagnosis and Predictive Rehabilitation Assessment of Chronic Ankle Instability Using Shoe-integrated Sensor System.","authors":"Zhonghe Guo, Yanzhang Li, Yuchen Wang, Haoxuan Liu, Rui Guo, Jingzhong Ma, Xiaoming Wu, Dong Jiang, Tianling Ren","doi":"10.1109/TNSRE.2025.3563924","DOIUrl":"https://doi.org/10.1109/TNSRE.2025.3563924","url":null,"abstract":"<p><p>Ankle sprains, the leading injuries in the emergency department that affect people worldwide, often leading to chronic ankle instability (CAI) characterized by recurring pain and weakness. However, challenges are presented in accurately identifying CAI-related abnormal gait patterns and assessing rehabilitation effects. Traditional plantar pressure systems lack portability and can only be used in limited specific actions, while a few early proposed portable systems have demonstrated insufficient accuracy. Besides, no previous studies have yet focused on assessing rehabilitation effects, which is crucial to providing the treatment selection and rehabilitation evaluation of CAI. Considering this, we propose a novel approach to improve the diagnostic process for CAI. A Shoe-Integrated Sensor System (SISS) which can accurately capture gait data during various activities was implemented. We collected and processed level walking data from 80 CAI patients diagnosed by professional experts and 42 healthy individuals using the system, including feature extraction and filtering algorithms. An artificial intelligence diagnosis was applied to the data, achieving a classification accuracy of 93.39% and an area under the curve (AUC) of 0.959, satisfying the clinical requirements for accuracy. Furthermore, a novel methodology was proposed to assess the level of patient rehabilitation. The validation results of rehabilitation status prediction demonstrated highly consistent results with doctors' diagnoses. Due to the significant impact of gait data in assisting the diagnosis of various neurological and musculoskeletal diseases that result in gait abnormalities, the proposed system can also be extended and utilized in other similar medical fields for diagnosing and real-time monitoring, promoting the development of smart healthcare.</p>","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.8,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143977890","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}