Predicting upper limb compensation during prehension tasks in tetraplegic spinal cord injured patients using a single wearable sensor

Trends and Innovations in Wearable Technology for Motor Rehabilitation, Prediction, and Monitoring: A Comprehensive Review

(1) Background: Continuous health promotion systems are increasingly important, enabling decentralized patient care, providing comfort, and reducing congestion in healthcare facilities. These systems allow for treatment beyond clinical settings and support preventive monitoring. Wearable systems have become essential tools for health monitoring, but they focus mainly on physiological data, overlooking motor data evaluation. The World Health Organization reports that 1.71 billion people globally suffer from musculoskeletal conditions, marked by pain and limited mobility. (2) Methods: To gain a deeper understanding of wearables for the motor rehabilitation, monitoring, and prediction of the progression and/or degradation of symptoms directly associated with upper-limb pathologies, this study was conducted. Thus, all articles indexed in the Web of Science database containing the terms "wearable", "upper limb", and ("rehabilitation" or "monitor" or "predict") between 2019 and 2023 were flagged for analysis. (3) Results: Out of 391 papers identified, 148 were included and analyzed, exploring pathologies, technologies, and their interrelationships. Technologies were categorized by typology and primary purpose. (4) Conclusions: The study identified essential sensory units and actuators in wearable systems for upper-limb physiotherapy and analyzed them based on treatment methods and targeted pathologies.

Hand Grasp Classification in Egocentric Video After Cervical Spinal Cord Injury

OBJECTIVE

The hand function of individuals with spinal cord injury (SCI) plays a crucial role in their independence and quality of life. Wearable cameras provide an opportunity to analyze hand function in non-clinical environments. Summarizing the video data and documenting dominant hand grasps and their usage frequency would allow clinicians to quickly and precisely analyze hand function.

METHOD

We introduce a new hierarchical model to summarize the grasping strategies of individuals with SCI at home. The first level classifies hand-object interaction using hand-object contact estimation. We developed a new deep model in the second level by incorporating hand postures and hand-object contact points using contextual information.

RESULTS

In the first hierarchical level, a mean of 86% ±1.0% was achieved among 17 participants. At the grasp classification level, the mean average accuracy was 66.2 ±12.9%. The grasp classifier's performance was highly dependent on the participants, with accuracy varying from 41% to 78%. The highest grasp classification accuracy was obtained for the model with smoothed grasp classification, using a ResNet50 backbone architecture for the contextual head and a temporal pose head.

DISCUSSION

We introduce a novel algorithm that, for the first time, enables clinicians to analyze the quantity and type of hand movements in individuals with spinal cord injury at home. The algorithm can find applications in other research fields, including robotics, and most neurological diseases that affect hand function, notably, stroke and Parkinson's.

Plasticity in Cervical Motor Circuits following Spinal Cord Injury and Rehabilitation

Simple Summary

Spinal cord injury results in a decreased quality of life and impacts hundreds of thousands of people in the US alone. This review discusses the underlying cellular mechanisms of injury and the concurrent therapeutic hurdles that impede recovery. It then describes the phenomena of neural plasticity—the nervous system’s ability to change. The primary focus of the review is on the impact of cervical spinal cord injury on control of the upper limbs. The neural plasticity that occurs without intervention is discussed, which shows new connections growing around the injury site and the involvement of compensatory movements. Rehabilitation-driven neural plasticity is shown to have the ability to guide connections to create more normal functions. Various novel stimulation and recording technologies are outlined for their role in further improving rehabilitative outcomes and gains in independence. Finally, the importance of sensory input, an often-overlooked aspect of motor control, is shown in driving neural plasticity. Overall, this review seeks to delineate the historical and contemporary research into neural plasticity following injury and rehabilitation to guide future studies.

Abstract

Neuroplasticity is a robust mechanism by which the central nervous system attempts to adapt to a structural or chemical disruption of functional connections between neurons. Mechanical damage from spinal cord injury potentiates via neuroinflammation and can cause aberrant changes in neural circuitry known as maladaptive plasticity. Together, these alterations greatly diminish function and quality of life. This review discusses contemporary efforts to harness neuroplasticity through rehabilitation and neuromodulation to restore function with a focus on motor recovery following cervical spinal cord injury. Background information on the general mechanisms of plasticity and long-term potentiation of the nervous system, most well studied in the learning and memory fields, will be reviewed. Spontaneous plasticity of the nervous system, both maladaptive and during natural recovery following spinal cord injury is outlined to provide a baseline from which rehabilitation builds. Previous research has focused on the impact of descending motor commands in driving spinal plasticity. However, this review focuses on the influence of physical therapy and primary afferent input and interneuron modulation in driving plasticity within the spinal cord. Finally, future directions into previously untargeted primary afferent populations are presented.

Tenodesis Grasp Detection in Egocentric Video

OBJECTIVE

Cervical spinal cord injury (cSCI) can impair motor function in the upper limbs. Video from wearable cameras (egocentric video) has the potential to provide monitoring of rehabilitation outcomes at home, but methods for automated analysis of this data are needed. Wrist flexion and extension are essential elements to track grasping strategies after cSCI, as they may reflect the use of the tenodesis grasp, a common compensatory strategy. However, there is no established method to evaluate wrist flexion and extension from egocentric video.

METHODS

We propose a machine-learning-based approach comprising three steps-hand detection, pose estimation, and arm orientation estimation-to estimate wrist angle data, leading to the detection of tenodesis grasp.

RESULTS

The hand detection in conjunction with the pose estimation algorithm correctly located wrist and index finger metacarpophalangeal coordinates in 63% and 76% of 15,319 annotated frames, respectively, extracted from egocentric videos of individuals with cSCI performing activities of daily living in a home simulation laboratory. The arm orientation algorithm had a mean absolute error of 2.76 +/- 0.39 degrees in 12,863 labeled frames. Using these estimates, the presence of a tenodesis grasp was correctly detected in 72% +/- 11% of frames in videos of 6 activities.

CONCLUSION

The results provided a clear indication of which participants relied on tenodesis grasp and which did not.

SIGNIFICANCE

This paradigm provides the first method that can enable clinicians and researchers to monitor the use of the tenodesis grasp by individuals with cSCI at home, with implications for remote therapeutic guidance.