IEEE Transactions on Neural Systems and Rehabilitation Engineering最新文献

{"title":"Haptic Coupling to Negotiate Motion Plans","authors":"C. De Vicariis;E. Ivanova;V. Sanguineti;E. Burdet","doi":"10.1109/TNSRE.2026.3670954","DOIUrl":"10.1109/TNSRE.2026.3670954","url":null,"abstract":"Haptic coupling is integral to everyday life, enabling humans to collaborate on tasks without the need for verbal agreement of every detail. However, collaborative partners often have differing plans and use haptic coupling to negotiate a common strategy. While previous studies have focused on tasks where partners share the same plan, little is known about haptic negotiation when plans diverge. This study investigates how the motion plans of two mechanically connected partners evolve during repeating a via-points arm-reaching task when they start from differing initial plans. In one group, partners had plans requiring similar effort, while in another group, plans were unbalanced, requiring different levels of effort. The analysis of shape and movement metrics shows that all dyads coordinated their plans through practice, influencing subsequent movements even when disconnected. For symmetric plans, partners exhibited slight mutual adaptation toward each other. In contrast, for asymmetric plans, the partner with the simpler plan tended to lead the movement, while the partner with the more complex plan complied and relaxed their plan. These findings suggest that, during collaboration, partners leverage mechanical interaction to simplify tasks and minimize effort.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"34 ","pages":"1448-1456"},"PeriodicalIF":5.2,"publicationDate":"2026-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11421909","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147365121","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":"Retraining Gastrocnemius Muscle Coordination Reduces Late-Stance Knee Contact Force in Individuals With Knee Osteoarthritis","authors":"Michelle R. Joyce;Julie Muccini;Benjamin Randoing;Scott L. Delp;Scott D. Uhlrich","doi":"10.1109/TNSRE.2026.3669842","DOIUrl":"10.1109/TNSRE.2026.3669842","url":null,"abstract":"Musculoskeletal simulations and experiments in young adults without knee pain have demonstrated that reducing gastrocnemius muscle activity can reduce knee contact force, which may reduce pain and progression of knee osteoarthritis. This study investigated whether individuals with knee osteoarthritis could reduce gastrocnemius electromyography (EMG) when provided with haptic biofeedback and consequently reduce late-stance knee contact force. Individuals with tibiofemoral osteoarthritis walked on a treadmill with adaptive biofeedback instructing them to reduce gastrocnemius EMG. Thirteen of eighteen participants reduced their average gastrocnemius EMG by at least 10% during an initial 30-minute training session and thereby qualified for a second session. During the second session, participants received the same biofeedback, and we estimated knee contact force using musculoskeletal models and static optimization. With feedback, participants reduced gastrocnemius EMG by <inline-formula> <tex-math>$25pm 15$ </tex-math></inline-formula>% (p<0.001)> <tex-math>$0.38pm 0.47$ </tex-math></inline-formula> times body weight (p= 0.01). However, the average EMG of the vasti muscles increased by <inline-formula> <tex-math>$38pm 34$ </tex-math></inline-formula>% (p= 0.004), which contributed to an increase in early-stance knee contact force in some participants. Ten out of thirteen reduced their knee contact force impulse with the feedback. While additional work is needed to mitigate increases in vasti EMG, our data demonstrates that individuals with knee osteoarthritis can reduce gastrocnemius EMG and late-stance knee contact force in a brief period of training, suggesting the potential of muscle coordination retraining as a non-surgical intervention for knee osteoarthritis.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"34 ","pages":"1417-1425"},"PeriodicalIF":5.2,"publicationDate":"2026-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11419186","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147348250","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 System for Upper Limb Motor Assessment Using Inertial Sensors and Machine Learning for Telerehabilitation Therapies","authors":"David Martínez-Pascual;Yolanda Vales;Raúl Martín-Batanero;José M. Catalán;Andrea Blanco-Ivorra;Nicolás García-Aracil","doi":"10.1109/TNSRE.2026.3669220","DOIUrl":"10.1109/TNSRE.2026.3669220","url":null,"abstract":"Neurological injuries can lead to a significant disability, particularly in upper limb motor function, impairing patients’ ability to perform Activities of Daily Living (ADLs). Telerehabilitation has emerged as a promising solution for remote patient monitoring and rehabilitation. Hence, there is a need to develop technologies to facilitate the patient assessment process remotely. This study presents an intelligent evaluation system for assessing upper limb motor function using three Inertial Measurement Units (IMUs). The upper limb joint trajectories are used as inputs to a machine learning model to recognize twelve activities based on ADLs and functional movements. Furthermore, a trajectory assessment is conducted comparing the trajectories performed by patients and non-disabled users based on similarity indexes calculated using the Dynamic Time Warping (DTW) distance. Finally, the similarity indexes are leveraged to estimate the patients ’ degree of impairment, classifying their motor disabilities into mild or moderate. The system has been evaluated by 31 survivors of neurological injury with motor impairment and 21 individuals from a control group. The results demonstrate the feasibility of using the system to recognize different activities and to assess upper limb motor function. This approach has the potential to enhance the monitoring and rehabilitation of stroke patients in a home setting.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"34 ","pages":"1371-1381"},"PeriodicalIF":5.2,"publicationDate":"2026-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11418721","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147344161","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":"Simulating Muscle-Level Energetic Cost When Humans Walk With a Passive Biarticular Thigh Exosuit","authors":"Vahid Firouzi;Seungmoon Song;Oskar von Stryk;Andre Seyfarth;Maziar Ahmad Sharbafi","doi":"10.1109/TNSRE.2026.3668912","DOIUrl":"10.1109/TNSRE.2026.3668912","url":null,"abstract":"Passive exosuits offer potential for reducing the metabolic cost of walking, but evaluating their effectiveness is challenging due to difficulties in measuring internal biomechanics and muscle-level energetics. This study investigates the metabolic effects of the BATEX, a passive biarticular thigh exosuit assisting hip and knee flexion/extension. The exosuit features a spring parallel to the rectus femoris (RF) and a spring parallel to the hamstring (HAM). We combined experimental data from ten healthy adults walking on a treadmill under various exosuit conditions (different stiffness and configurations) with EMG-informed musculoskeletal simulations to estimate muscle-level behavior. The simulations aimed to replicate experimental metabolic measures, analyze cost fluctuations across the gait cycle, and elucidate muscle-tendon energetic responses, comparing individuals experiencing reductions (positive responders, PR) versus increases (negative responders, NR) in metabolic cost. Simulation results successfully replicated experimental whole-body metabolic cost trends for most participants (8/10, <inline-formula> <tex-math>${r} gt {0}.{7}$ </tex-math></inline-formula>, <inline-formula> <tex-math>${p}lt {0}.{05}$ </tex-math></inline-formula>), showing comparable overall net reductions primarily driven by significant savings during the swing phase. Combining RF and HAM springs resulted in complex, non-additive interactions. Muscle-level analysis identified both targeted effects on hip/knee flexors/extensors and non-targeted effects on ankle and hip ab/adductor muscles, with responses differing markedly between PR and NR groups. Distinct energy-saving mechanisms were associated with each spring type (RF: reduced activation; HAM: reduced fiber velocity). The differing responses of the PR and NR groups to the same device setup motivate personalization, and our muscle-level insights offer a foundation for future device refinement.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"34 ","pages":"1340-1351"},"PeriodicalIF":5.2,"publicationDate":"2026-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11417279","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147317234","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":"Edge-Aided Radar-Based Exercise Form Classification Using Lightweight Ensemble Learning for Personalized Healthcare","authors":"Jose Maria Sosa Gomez;Sajid Ahmed;Slim Souissi;Mohamed-Slim Alouini","doi":"10.1109/TNSRE.2026.3669061","DOIUrl":"10.1109/TNSRE.2026.3669061","url":null,"abstract":"Real-time, non-contact monitoring of exercise form is important for personalized rehabilitation, yet cameras and wearables raise privacy and robustness concerns. We present RehabRadar, an edge-aided system using a TI IWR1642 mmWave FMCW radar that trains personalized models to classify execution as correct or one of two common error types. The signal pipeline isolates the subject via range-gating and FIR high-pass filtering, then extracts complementary micro-Doppler spectrograms and range-Doppler sequences. A hybrid ensemble—MobileNetV3 for micro-Doppler images and CNN-LSTM for range-Doppler sequences—performs parallel inference with late fusion. The models are optimized for a Raspberry Pi 4B via magnitude-based pruning and post-training INT8 quantization. We evaluated the system in a proof-of-concept study with 10 healthy adults performing eight clinically curated exercises; ten-fold cross-validation per-participant yields 91.5% accuracy and 92.0% macro-F1 on average of all models, outperforming single-branch baselines. End-to-end latency averages 1.5 s, rep-level feedback while preserving data locally. The final model footprint is 21 MB, and all processing occurs on-device; raw radar is discarded after feedback, and only minimal encrypted metrics are transmitted externally. This work demonstrates the feasibility of personalized on-device error detection under edge constraints. Establishing clinical efficacy and generalizability beyond the studied cohort, broader exercise taxonomies, and patient populations is outside the present scope and motivates planned multi-site clinical validation. These results indicate that the mmWave radar, combined with compact neural models, can balance accuracy, latency, and footprint for private, contactless home rehabilitation analytics, and advance decentralized learning in IoT healthcare.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"34 ","pages":"1405-1416"},"PeriodicalIF":5.2,"publicationDate":"2026-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11417293","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147317174","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":"PDXNet: An eXplainable Hybrid Attention Convolutional Neural Network for Parkinson’s Disease Monitoring and Evaluation","authors":"Lei Zhang;Wen Liu;Qin Ni;Zhenyu Gao;Yuanjun Wang","doi":"10.1109/TNSRE.2026.3668313","DOIUrl":"10.1109/TNSRE.2026.3668313","url":null,"abstract":"Parkinson’s disease (PD), the second most common neurodegenerative disorder, affects patients and caregivers worldwide. There is a growing need for technologies that use portable wearable sensors to monitor and assess patients using artificial intelligence (AI). Nevertheless, many state-of-the-art AI recognition systems are “black-box” models, making it difficult to understand their internal logic and leading to mistrust in medical applications. In this paper, we propose an eXplainable hybrid attention convolutional neural network for Parkinson’s disease monitoring and evaluation (PDXNet) based on real-world PD data from the University of Rochester. Specifically, we automatically extract resting tremor segments and use a hybrid-attention CNN to evaluate tremor presence (AUC > 0.93). Moreover, saliency maps and SHapley Additive exPlanations (SHAP) are used to interpret the model by visualizing feature contributions for human experts to assess the model’s internal logic. Ultimately, the feature contributions obtained align with human intuition. PDXNet demonstrates high accuracy in assessing resting tremors in PD and provides interpretability to users. It offers a trustworthy technical solution for PD monitoring using wearable sensors and AI.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"34 ","pages":"1426-1437"},"PeriodicalIF":5.2,"publicationDate":"2026-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11414184","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147305479","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":"Test-Retest Reliability and Preliminary Reference Data for the Virtual Eggs Test in Healthy Adults","authors":"Lucia Angelini;Michele Piazzini;Marco Baccini;Tommaso Ciappetti;Francesca Cecchi;Marco Controzzi","doi":"10.1109/TNSRE.2026.3667416","DOIUrl":"10.1109/TNSRE.2026.3667416","url":null,"abstract":"Rehabilitation professionals rely on hand assessment to select the proper therapy and monitor the recovery process over time. The Virtual Eggs Test (VET) is a unique assessment tool that evaluates both fine and gross hand dexterity, taking into account not only the speed in performing an action but also the accuracy in regulating the grip force. The VET was preliminary validated with amputees and healthy individuals, demonstrating construct validity, but also highlighting some weaknesses that required a protocol revision. Here, we present the update version of the protocol and of the outcomes measure (Fine Dexterity Index–FDI - and Gross Dexterity Index - GDI). We carried on a clinical trial involving 79 healthy participants, stratified by age groups, to collect normative data and evaluate test-retest reliability. The FDI and the GDI demonstrate no significant difference between test and retest. FDI showed excellent reliability (ICC was 0.90 and 0.91 for the dominant and non-dominant hand, respectively). While GDI demonstrated moderate reliability (ICC was equal to 0.63 and 0.64 for the dominant and non-dominant hand, respectively). The findings indicate that the VET is reliable over time for the evaluation of hand function in tasks involving fragile objects.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"34 ","pages":"1363-1370"},"PeriodicalIF":5.2,"publicationDate":"2026-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11409409","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147283740","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":"Enhanced Identification of Chronic Ankle Instability Under Different Conditions: A New Evaluation Framework Based on Feature Fusion and Machine Learning","authors":"Zhifeng Zhou;Datao Xu;Tianle Jie;Meizi Wang;Zanni Zhang;Huiyu Zhou;Yi Yuan;Julien S. Baker;Yaodong Gu","doi":"10.1109/TNSRE.2026.3667526","DOIUrl":"10.1109/TNSRE.2026.3667526","url":null,"abstract":"This study proposed a synergy-informed evaluation framework that integrates muscle synergy features derived from non-negative matrix factorization (NNMF) of surface EMG signals with deep feature fusion and machine learning techniques. EMG data were collected from nine lower-limb muscles during both anticipated and unanticipated landing tasks in 30 CAI patients and 30 healthy controls. Synergy-derived features were embedded into multidimensional representations and processed through a convolutional neural network (CNN) to achieve hierarchical feature integration, followed by classification using a random forest algorithm. The results revealed that individuals with CAI demonstrated altered synergy structures and a compensatory shift toward proximal muscle recruitment, particularly under unanticipated tasks. Among the four evaluated models, the CNN-RF-Unant configuration yielded the highest classification accuracy (0.96) and F1-score (0.95), outperforming models based on anticipated tasks or without CNN-based fusion. The feature importance analysis further highlighted the superior informativeness of unanticipated-task-derived features. These findings demonstrate that combining NNMF-based synergy analysis with CNN-driven fusion substantially enhances the detection of neuromuscular deficits in CAI, particularly when assessments involve unanticipated perturbations. This approach offers a clinically valuable and ecologically valid framework for identifying latent functional impairments and tailoring individualized rehabilitation strategies.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"34 ","pages":"1318-1328"},"PeriodicalIF":5.2,"publicationDate":"2026-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11409385","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147283801","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 Lightweight Hybrid Encoder-Decoder Framework for Multiple Degree of Freedom Muscle Force Estimation","authors":"Yang Zheng;Yixin Li;Haixiong Zhang;Guanghua Xu","doi":"10.1109/TNSRE.2026.3667588","DOIUrl":"10.1109/TNSRE.2026.3667588","url":null,"abstract":"Goal: Motor unit (MU) discharge information extracted via real-time electromyogram (EMG) decomposition shows superiority in dexterous finger motion decoding. However, some critical constraints might limit the performance of multi-degree-of-freedom (DoF) muscle force estimation, including the neglect of the temporal cumulative effects of MU discharges and the rigid MU pool allocation across fingers. Methods: A hybrid encoder-decoder framework integrating EMG decomposition with TFR (Temporal Firing Rate)-Net was proposed for multi-DoF force estimation. The initial encoder involved decomposing EMG into MU spike trains and firing rates, which are subsequently processed through TFR-Net for hierarchical encoding and decoding. This framework uses temporal firing rate to model force accumulation instead of a twitch model, and allocates MU weights dynamically and flexibly in multi-fingers and multi-force level tasks instead of rigid MU pool allocation. Results: Two baselines (firing rate-based regression method and twitch force model method) were evaluated on 15-min EMG from 10 subjects performing alternating multi-finger isometric extensions. The results showed the proposed method demonstrated superior comprehensive performance with a higher correlation (R<inline-formula> <tex-math>${}^{mathbf {{2}}}$ </tex-math></inline-formula>: <inline-formula> <tex-math>$0.80~pm ~0.12$ </tex-math></inline-formula> vs. <inline-formula> <tex-math>$0.75~pm ~0.14$ </tex-math></inline-formula> vs. <inline-formula> <tex-math>$0.62~pm ~0.19$ </tex-math></inline-formula>) and a lower prediction error (root-mean-square error: 6.32% <inline-formula> <tex-math>$pm ~1.89$ </tex-math></inline-formula>% vs. 7.24% <inline-formula> <tex-math>$pm ~1.82$ </tex-math></inline-formula>% vs. 9.96% <inline-formula> <tex-math>$pm ~2.54$ </tex-math></inline-formula> % maximum voluntary contraction) compared with the two comparison methods, and an improved computational efficiency (Flops: 1.350k vs. 408.093k vs. 0.016k) compared with the twitch force model method. Significance: Further development of the proposed method could potentially provide a robust human machine interface for dexterous finger force prediction in realistic applications.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"34 ","pages":"1329-1339"},"PeriodicalIF":5.2,"publicationDate":"2026-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11409383","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147283743","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":"Evaluating Variable Transmissions in Body-Powered Prosthetic Grasping","authors":"Michael E. Abbott;Andrew I. W. McPherson;Franklin D.-K. Ho;Hannah S. Stuart","doi":"10.1109/TNSRE.2026.3667407","DOIUrl":"10.1109/TNSRE.2026.3667407","url":null,"abstract":"Body-powered prostheses remain popular for those with upper limb absence in part due to their inherent haptic feedback, but they still face low adoption rates due to the high forces required from the user and associated discomfort. Recent work on a desktop haptics testbed demonstrates potential benefits from including variable transmissions in simulated body-powered devices, reducing physical demands on the user and improving grasp success for a wide variety of object types. However, real-world grasping tests have yet to be performed with an embodied wearable system. In this work, we evaluate five different transmission modes, including fixed and multiple variable modes, on a body-powered wearable prosthetic device in a grasp and lift task. We demonstrate how variable transmissions can reduce actuation loads on the user with negligible changes to required motion inputs and find that abrupt, autonomous changes in transmission state can increase the risk of overgrasping and crushing fragile objects.","PeriodicalId":13419,"journal":{"name":"IEEE Transactions on Neural Systems and Rehabilitation Engineering","volume":"34 ","pages":"1284-1293"},"PeriodicalIF":5.2,"publicationDate":"2026-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11408914","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147283749","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}