Mixed matrix factorization: a novel algorithm for the extraction of kinematic-muscular synergies

Synergistic models have been employed to investigate motor coordination separately in the muscular and kinematic domains. However, the relationship between muscle synergies, constrained to be non-negative, and kinematic synergies, whose elements can be positive and negative, has received limited attention. Existing algorithms for extracting synergies from combined kinematic and muscular data either do not enforce non-negativity constraints or separate non-negative variables into positive and negative components. We propose a mixed matrix factorization (MMF) algorithm based on a gradient descent update rule which overcomes these limitations. It allows to directly assess the relationship between kinematic and muscle activity variables, by enforcing the non-negativity constrain on a subset of variables. We validated the algorithm on simulated kinematic-muscular data generated from known spatial synergies and temporal coefficients, by evaluating the similarity between extracted and ground truth synergies and temporal coefficients when the data are corrupted by different noise levels. We also compared the performance of MMF to that of non-negative matrix factorization applied to separate positive and negative components (NMFpn). Finally, we factorized kinematic and EMG data collected during upper-limb movements to demonstrate the potential of the algorithm. MMF achieved almost perfect reconstruction on noiseless simulated data. It performed better than NMFpn in recovering the correct spatial synergies and temporal coefficients with noisy simulated data. It also allowed to correctly select the original number of ground truth synergies. We showed meaningful applicability to real data; MMF can also be applied to any multivariate data that contains both non-negative and unconstrained variables.

Occupational Therapy Assessment for Upper Limb Rehabilitation: A Multisensor-Based Approach

Most post-stroke patients experience varying degrees of impairment in upper limb function and fine motor skills. Occupational therapy (OT) with other rehabilitation trainings is beneficial in improving the strength and dexterity of the impaired upper limb. An accurate upper limb assessment should be conducted before prescribing upper limb OT programs. In this paper, we present a novel multisensor method for the assessment of upper limb movements that uses kinematics and physiological sensors to capture the movement of the limbs and the surface electromyogram (sEMG). These sensors are Kinect, inertial measurement unit (IMU), Xsens, and sEMG. The key assessment features of the proposed model are as follows: (1) classification of OT exercises into four classes, (2) evaluation of the quality and completion of the OT exercises, and (3) evaluation of the relationship between upper limb mobility and muscle strength in patients. According to experimental results, the overall accuracy for OT-based motion classification is 82.2%. In addition, the fusing of Kinect and Xsens data reveals that muscle strength is highly correlated with the data with a correlation coefficient (CC) of 0.88. As a result of this research, occupational therapy specialists will be able to provide early support discharge, which could alleviate the problem of the great stress that the healthcare system is experiencing today.

Upper Limb Movement Measurement Systems for Cerebral Palsy: A Systematic Literature Review

Quantifying the quality of upper limb movements is fundamental to the therapeutic process of patients with cerebral palsy (CP). Several clinical methods are currently available to assess the upper limb range of motion (ROM) in children with CP. This paper focuses on identifying and describing available techniques for the quantitative assessment of the upper limb active range of motion (AROM) and kinematics in children with CP. Following the screening and exclusion of articles that did not meet the selection criteria, we analyzed 14 studies involving objective upper extremity assessments of the AROM and kinematics using optoelectronic devices, wearable sensors, and low-cost Kinect sensors in children with CP aged 4–18 years. An increase in the motor function of the upper extremity and an improvement in most of the daily tasks reviewed were reported. In the population of this study, the potential of wearable sensors and the Kinect sensor natural user interface as complementary devices for the quantitative evaluation of the upper extremity was evident. The Kinect sensor is a clinical assessment tool with a unique markerless motion capture system. Few authors had described the kinematic models and algorithms used to estimate their kinematic analysis in detail. However, the kinematic models in these studies varied from 4 to 10 segments. In addition, few authors had followed the joint assessment recommendations proposed by the International Society of Biomechanics (ISB). This review showed that three-dimensional analysis systems were used primarily for monitoring and evaluating spatiotemporal variables and kinematic parameters of upper limb movements. The results indicated that optoelectronic devices were the most commonly used systems. The joint assessment recommendations proposed by the ISB should be used because they are approved standards for human kinematic assessments. This review was registered in the PROSPERO database (CRD42021257211).

Current Status and Challenge for Implementation in Clinical Application of Augmented Reality in Orthopedics Department at a Medical Center

With technical development, artificial intelligence (AI) has been actively involving in the healthcare industry. Augmented reality (AR) is an interactive experience with the combination of virtual objects and a real-world environment, and the objects reside in the environment of the real world through computer-generated images for the purpose to enhance perceptual effects, which can be applied in the fields of medical education and clinical practice. Researchers have found that learning motives and interests may be raised by AR. At a medical center, the inter-specialty team from the Teaching Department and Rehabilitation Department jointly developed an AR Medical Education App, which involves 44 muscle strength and walking exercises, including 6 upper limb movements, 28 lower limb exercises, and 10 cardiorespiratory exercises. Various exercise packages can be designed by health caregivers based on patient’s needs in exercise. The Orthopedics Ward applied it in the respiration training for patients who underwent spinal surgery, preventing respiratory comorbidities. The improved postoperative pulmonary function has been found when compared with that before surgery, with statistical significance. Respiration, upper and lower limbs exercises were persistently performed in patients who underwent spinal surgery, which also has been incorporated in routine nursing care to add diverse options of patient education materials for nursing personnel. In the future, aspects that required further efforts include: expanded software equipment, simplified operation mode, increased user-friendly features for equipment, and expended plentifulness of contents.

Skin Strain Analysis of the Scapular Region and Wearables Design

Monitoring scapular movements is of relevance in the contexts of rehabilitation and clinical research. Among many technologies, wearable systems instrumented by strain sensors are emerging in these applications. An open challenge for the design of these systems is the optimal positioning of the sensing elements, since their response is related to the strain of the underlying substrates. This study aimed to provide a method to analyze the human skin strain of the scapular region. Experiments were conducted on five healthy volunteers to assess the skin strain during upper limb movements in the frontal, sagittal, and scapular planes at different degrees of elevation. A 6 × 5 grid of passive markers was placed posteriorly to cover the entire anatomic region of interest. Results showed that the maximum strain values, in percentage, were 28.26%, and 52.95%, 60.12% and 60.87%, 40.89%, and 48.20%, for elevation up to 90° and maximum elevation in the frontal, sagittal, and scapular planes, respectively. In all cases, the maximum extension is referred to the pair of markers placed horizontally near the axillary fold. Accordingly, this study suggests interesting insights for designing and positioning textile-based strain sensors in wearable systems for scapular movements monitoring.

Mixed matrix factorization: a novel algorithm for the extraction of kinematic-muscular synergies

Synergistic models have been employed to investigate motor coordination separately in the muscular and kinematic domains. However, the relationship between muscle synergies, constrained to be non-negative, and kinematic synergies, whose elements can be positive and negative, has received limited attention. Existing algorithms for extracting synergies from combined kinematic and muscular data either do not enforce non-negativity constraints or separate non-negative variables into positive and negative components. We propose a mixed matrix factorization (MMF) algorithm based on a gradient descent update rule which overcomes these limitations. It directly assesses the relationship between kinematic and muscle activity variables, by enforcing the non-negativity constrain on a subset of variables. We validated the algorithm on simulated kinematic-muscular data generated from known spatial synergies and temporal coefficients, by assessing the similarity between extracted and ground truth synergies and temporal coefficients when the data are corrupted by different noise levels. We also compared the performance of MMF to that of non-negative matrix factorization applied to separate positive and negative components (NMFpn). Finally, we factorized kinematic and EMG data collected during upper-limb movements to demonstrate the potential of the algorithm. MMF achieved almost perfect reconstruction on noiseless simulated data. It performed better than NMFpn in recovering the correct spatial synergies and temporal coefficients with noisy simulated data. It allowed to correctly select the original number of ground truth synergies. We showed meaningful applicability to real data. MMF can also be applied to any multivariate data that contains both non-negative and unconstrained variables.

U-Limb: A multi-modal, multi-center database on arm motion control in healthy and post-stroke conditions

Background Shedding light on the neuroscientific mechanisms of human upper limb motor control, in both healthy and disease conditions (e.g., after a stroke), can help to devise effective tools for a quantitative evaluation of the impaired conditions, and to properly inform the rehabilitative process. Furthermore, the design and control of mechatronic devices can also benefit from such neuroscientific outcomes, with important implications for assistive and rehabilitation robotics and advanced human-machine interaction. To reach these goals, we believe that an exhaustive data collection on human behavior is a mandatory step. For this reason, we release U-Limb, a large, multi-modal, multi-center data collection on human upper limb movements, with the aim of fostering trans-disciplinary cross-fertilization. Contribution This collection of signals consists of data from 91 able-bodied and 65 post-stroke participants and is organized at 3 levels: (i) upper limb daily living activities, during which kinematic and physiological signals (electromyography, electro-encephalography, and electrocardiography) were recorded; (ii) force-kinematic behavior during precise manipulation tasks with a haptic device; and (iii) brain activity during hand control using functional magnetic resonance imaging.