IEEE Transactions on Neural Systems and Rehabilitation Engineering最新文献

Musculoskeletal modeling and simulations enable accurate description and analysis of the movement of biological systems with applications such as rehabilitation assessment, prosthesis, and exoskeleton design. However, the widespread usage of these techniques is limited by costly sensors, laboratory-based setups, computationally demanding processes, and the use of diverse software tools that often lack seamless integration. In this work, we address these limitations by proposing an integrated, real-time framework for musculoskeletal modeling and simulations that leverages OpenSimRT, the robotics operating system (ROS), and wearable sensors. As a proof-of-concept, we demonstrate that this framework can reasonably well describe inverse kinematics of both lower and upper body using either inertial measurement units or fiducial markers. Additionally, when combined with pressure insoles, it effectively estimates inverse dynamics of the ankle joint and muscle activations of major lower limb muscles during daily activities, including walking, squatting and sit to stand, stand to sit. Based on the preliminary data, the proposed pipeline showed strong agreement (r>0.70) with motion capture measurements across tasks for joint angles and torques, except for knee torque during walking. RMSE values for joint angles were within 9° for all joints except the knee during squat. Overall, lower RMSE were observed for squat and sit-to-stand compared with walking, particularly at the knee and hip joints. We believe this work lays the groundwork for further studies with more complex real-time and wearable sensor-based human movement analysis systems and holds potential to advance technologies in rehabilitation, robotics and exoskeleton designs.

Anterior cruciate ligament (ACL) injury often leads to lasting deficits in joint stability and neuromuscular control, even after reconstruction. Understanding how these deficits manifest during functional tasks is essential for improving rehabilitation strategies. This study recruited 25 male participants who had undergone ACL reconstruction, with assessments conducted at 3, 6, 9, and 12 months postoperatively. Surface electromyography (sEMG) signals from ten lower-limb muscles were collected during a standardized stair-descent task, and non-negative matrix factorization (NNMF) was applied to extract the corresponding muscle synergy patterns. Paired-samples t-tests and Wilcoxon rank-sum tests were performed to evaluate differences in muscle synergies between the ACL-reconstructed and contralateral limbs. Motor modules analysis revealed a preserved four-synergy structure in both limbs, with VAF exceeding 90%. At 3-6 months postoperatively, the reconstructed limb exhibited significantly elevated activation of the medial gastrocnemius (MG), biceps femoris (BF), and rectus femoris (RF) (p < 0.005). This was accompanied by reduced contributions from the semitendinosus (ST) and lateral gastrocnemius (LG) in Synergy 4, indicative of a compensatory, quadriceps-dominant control strategy. By 9 months, partial normalization of neuromuscular coordination was observed, with interlimb symmetry across all four synergies largely restored by 12 months. These findings demonstrate that recovery of physiological neuromuscular control following ACL reconstruction is a prolonged and staged process. Longitudinal motor module analysis captures the dynamic reorganization of modular control from early compensatory patterns to restored interlimb coordination and may provide a mechanism-based indicator to guide personalized neuromuscular rehabilitation.

Parkinson's Disease (PD) is a progressive neurodegenerative disorder marked by motor and non-motor symptoms, which complicate both diagnosis and disease monitoring. Traditional subjective assessments, such as the Unified Parkinson's Disease Rating Scale (MDS-UPDRS) and Hoehn and Yahr scale, often fall short of capturing subtle motor variations across PD stages as well as require expertise and thus the accessibility is limited in daily life. In this study, we evaluated the feasibility of using in-phase (IP) and anti-phase (AP) heel- and toe-tapping as biomarkers to monitor PD progression objectively. Motion data were collected from 40 participants (28 patients with PD, 12 age-matched healthy controls) using a pair of smart insoles with embedded accelerometers. Our results show that the heel IP yielded the largest number of stage-discriminative features, with 96 out of 112 extracted features showing significant differences across PD stages and achieved up to 92% classification accuracy using supervised machine learning classifiers, particularly Random Forest and Neural Network. Clustering analyses (KMeans and Gaussian Mixture Model) further supported stage-specific grouping patterns, with chi-square significance p < 0.0001. These findings suggest that heel IP can serve as a sensitive and practical assessment for PD stage classification. Paired with smart insoles and a tapping game, this can be used as an assistive tool to monitor PD disease progression for at home monitoring in daily life.

Neural interfaces offer a pathway to intuitive, high-bandwidth interaction, but the sensitive nature of neural data creates significant privacy hurdles for large-scale model training. Federated learning (FL) has emerged as a promising privacy-preserving solution, yet its efficacy in real-time, online neural interfaces remains unexplored. In this study, we 1) propose a conceptual framework for applying FL to the distinct constraints of neural interface applications and 2) provide a systematic evaluation of FL-based neural decoding using high-dimensional surface electromyography across both an offline simulation and a real-time, online user study. While offline results suggest that FL can simultaneously enhance performance and privacy, our online experiments reveal a more complex landscape. We found that standard FL assumptions struggle to translate to real-time, sequential interactions with user-decoder co-adaptation. Our results show that while FL retains privacy advantages, it introduces performance tensions not predicted by offline simulations. These findings identify a critical gap in current FL methodologies and highlight the need for specialized algorithms designed to navigate the unique co-adaptive dynamics of online neural decoding.

Objective: In complex networks, researching the relationships between nodes and edges has been a hot topic in recent years. However, to date, no studies have explored the multiscale node-edge interaction (MNEI) information within complex networks.

Method: As an illustrative example, the study employs brain networks of individuals diagnosed with Alzheimer's disease, mild cognitive impairment, and healthy controls. Our approach begins by decomposing the node and edge attributes from the vertex domain into nine MNEI components within the graph frequency domain. Each component encapsulates joint information, integrating either high, middle, or low graph frequency bands for node attributes, along with any band from the edge attributes. Following this, we transform each MNEI component back into the vertex domain to enable further analysis. Ultimately, the MNEI features derived from both domains are employed to classify subjects into three distinct groups.

Results: A majority of MNEI features display significant differences among the groups, resulting in classification performance that surpasses traditional brain network analysis methods.

Conclusion: Importantly, this study is the first to demonstrate the capability of capturing MNEI in complex networks. Additionally, this research can be regarded as a novel information fusion technique for integrating node and edge attributes under non-Euclidean network topological constraints. Furthermore, this approach can also be considered a new type of multi-scale complex network decomposition.

Significance: Overall, these advancements have expanded the scope of complex network analysis and provided brand-new scientific insights, with the potential for widespread application in numerous fields in the future.