Search

Spinal Cord Injury (SCI) presents a significant challenge in rehabilitation medicine, with recovery outcomes varying widely among individuals. Machine learning (ML) is a promising approach to enhance the prediction of recovery trajectories, but its integration into clinical practice requires a thorough understanding of its efficacy and applicability. We systematically reviewed the current literature on data-driven models of SCI recovery prediction. The included studies were evaluated based on a range of criteria assessing the approach, implementation, input data preferences, and the clinical outcomes aimed to forecast. We observe a tendency to utilize routinely acquired data, such as International Standards for Neurological Classification of SCI (ISNCSCI), imaging, and demographics, for the prediction of functional outcomes derived from the Spinal Cord Independence Measure (SCIM) III and Functional Independence Measure (FIM) scores with a focus on motor ability. Although there has been an increasing interest in data-driven studies over time, traditional machine learning architectures, such as linear regression and tree-based approaches, remained the overwhelmingly popular choices for implementation. This implies ample opportunities for exploring architectures addressing the challenges of predicting SCI recovery, including techniques for learning from limited longitudinal data, improving generalizability, and enhancing reproducibility. We conclude with a perspective, highlighting possible future directions for data-driven SCI recovery prediction and drawing parallels to other application fields in terms of diverse data types (imaging, tabular, sequential, multimodal), data challenges (limited, missing, longitudinal data), and algorithmic needs (causal inference, robustness)., Competing Interests: Declaration of competing interest None., (Copyright © 2024 The Authors. Published by Elsevier Inc. All rights reserved.)

Uncontrolled muscle spasms often develop after spinal cord injury. Structural and functional maladaptive changes in spinal neuronal circuits below the lesion site were postulated as an underlying mechanism but remain to be demonstrated in detail. To further explore the background of such secondary phenomena, rats received a complete sacral spinal cord transection at S(2) spinal level. Animals progressively developed signs of tail spasms starting 1 week after injury. Immunohistochemistry was performed on S(3/4) spinal cord sections from intact rats and animals were sacrificed 1, 4 and 12 weeks after injury. We found a progressive decrease of cholinergic input onto motoneuron somata starting 1 week post-lesion succeeded by shrinkage of the cholinergic interneuron cell bodies located around the central canal. The number of inhibitory GABAergic boutons in close contact with Ia afferent fibers was greatly reduced at 1 week after injury, potentially leading to a loss of inhibitory control of the Ia stretch reflex pathways. In addition, a gradual loss and shrinkage of GAD65 positive GABAergic cell bodies was detected in the medial portion of the spinal cord gray matter. These results show that major structural changes occur in the connectivity of the sacral spinal cord interneuronal circuits below the level of transection. They may contribute in an important way to the development of spastic symptoms after spinal cord injury, while reduced cholinergic input on motoneurons is assumed to result in the rapid exhaustion of the central drive required for the performance of locomotor movements in animals and humans., (Copyright © 2012 Elsevier Inc. All rights reserved.)

Central nervous system lesions, such as stroke or spinal cord injury (SCI), are followed by both cortical and spinal neuronal reorganization. In a severe chronic SCI a spinal neuronal dysfunction develops which is reflected in an exhaustion of leg muscle electromyographic (EMG) activity during assisted locomotion and a change in the dominance from an early to a late polysynaptic spinal reflex (SR) component. The aim of this study was to investigate the course of spinal neuronal function after a severe stroke, i.e., a unilateral deprivation of supraspinal input. In 30 hemiparetic stroke subjects locomotor and SR behavior were assessed. SR responses in the tibialis anterior muscle were evoked by non-noxious tibial nerve stimulation on both, the affected and the unaffected leg. In nine stroke subjects EMG activity of the leg muscles was recorded during assisted locomotion. In a similar way to SCI subjects, in severely affected chronic (>12 months post-incidence) stroke subjects a late SR component was prominent in the affected leg, while an early one dominated in the unaffected leg. The late SR component correlated with muscle paresis (rho=0.714) and walking ability (rho=0.493). In contrast to SCI subjects, no exhaustion of the EMG activity was observed in the affected leg muscles during prolonged assisted locomotion. It is concluded that spinal neuronal circuits undergo functional changes also after a stroke which have common as well as divergent features compared to SCI subjects. As a consequence, different rehabilitative strategies might be required., (Copyright © 2011 Elsevier Inc. All rights reserved.)