Marc Bolliger

The Integrated Neurological Change Score (INCS) combines changes in sensory and motor subscores from the International Standards for Spinal Cord Injury Classification (ISNCSCI) into a composite measure. We evaluated the INCS sensitivity to therapeutic outcomes, robustness against ceiling effects, and association to functional improvement in patients with acute cervical spinal cord injury (SCI). To this end, we conducted a retrospective analysis of data from the Nogo Inhibition in Spinal Cord Injury (NISCI) clinical trial alongside a matched cohort from the European Multicenter Study about Spinal Cord Injury (EMSCI). The NISCI trial assessed the safety and efficacy of the anti-Nogo-A antibody (NG-101) in acute cervical SCI, reporting a potential therapeutic effect in motor incomplete patients. Our findings show that the sensitivity of INCS to the effect of NG-101 is comparable to that obtained employing the changes in the Upper Extremity Motor Score (the primary outcome in the NISCI trial). Moreover, the INCS is less susceptible to ceiling effects compared to measures of upper and lower extremity or total motor scores, as observed in the NISCI trial and in the matched EMSCI cohort. This robustness may facilitate the design of more inclusive clinical trials without compromising statistical power. Finally, INCS correlates strongly with functional outcomes in self-care and walking ability, outperforming ISNCSCI motor scores. In conclusion, the INCS represents a sensitive measure of neurological change corroborating the value of ISNCSCI standards for use in SCI trials.

NG101 is a recombinant antibody that neutralizes the nerve growth inhibitor Nogo-A, promoting neural repair and improving upper extremity motor function in spinal cord injury (SCI). This study evaluated spinal cord MRI biomarkers to detect treatment-related structural changes and enhance patient stratification using data from 106 participants with acute cervical SCI in the phase 2b NISCI trial. We assessed lesion volume, tissue bridges, and remote changes in cross-sectional cord area (CSA), and tract-specific myelin-sensitive magnetization transfer saturation (MTsat) over six months. Compared to placebo, NG101-treated participants exhibited faster lesion volume reduction and a slower decline of CSA and MTsat in the corticospinal tracts and dorsal columns. Crucially, multimodal stratification incorporating MRI and electrophysiological measures substantially enhanced the detection of clinical treatment effects. These findings suggest NG101 slows trauma-induced progressive macro- and microstructural degeneration or promotes fiber sprouting. Combining MRI with electrophysiology enables sensitive detection of treatment effects and efficient trial designs. ClinicalTrials.gov identifier: NCT03935321.

Background: Spinal cord injury (SCI) causes long-term neurological deficits resulting in functional disabilities. While longitudinal recovery patterns of sensorimotor outcomes after SCI have been studied, few analyses have applied machine learning to systematically model the relationship between neurological impairments and functional independence at different post-injury phases. Methods: This study compared ordinal and nominal classification models predicting functional independence from sensorimotor status cross-sectionally. Inputs included motor and sensory scores from the International Standards for Neurological Classification of SCI, age, sex, and time since injury collected in the European Multicenter Study about SCI. Models were evaluated on a task from each domain of the Spinal Cord Independence Measure, namely grooming (self-care), bladder management (respiration and sphincter management), and indoor mobility (mobility). Analyses were stratified into early (≤ 40 days), intermediate (70–100 days), and late (> 182 days) post-injury phases. Models were ranked based on five evaluation metrics, and interpretability explored using Shapley Additive Explanations (SHAP). Results: Model accuracy improved over time (early phase: 46–71%, late phase: 50–85%), indicating that functional independence is more reliably determined from sensorimotor scores in later post-injury phases. Across all scenarios, random forest achieved the best overall performance (0.93 ± 0.03, averaged across different metrics). Ordinal models yielded fewer severe misclassifications compared to nominal models. Motor scores were stronger predictors than sensory scores, with lower limb function (L2–L4) strongly associated with mobility, voluntary anal contraction with bladder control, and upper limb function (C6, C8) with grooming ability, highlighting that models utilise known relationships. Conclusion: We show that both multiclass and ordinal models can accurately classify SCIM-based functional independence outcomes after SCI from neurological assessments at different time points post-injury. Ordinal approaches provide particular clinical value by minimizing severe misclassifications, a crucial advantage when distinguishing between functional independence classes that require fundamentally different care approaches. Interpretability analysis showed that the predictions are grounded in clinical knowledge. The developed models provide the basis for a modular prognostic framework, in which predicted ISNCSCI scores can be used to derive the most likely functional independence class, enabling a modular, computationally efficient and scalable approach to prediction in SCI care across a range of neurological and functional outcomes.

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).

Most established clinical walking tests assess specific aspects of movement function (velocity, endurance, etc.) but are generally unable to determine specific biomechanical or neurological deficits that limit an individual’s ability to walk. Recently, inertial measurement units (IMU) have been used to collect objective kinematic data for gait analysis and could be a valuable extension for clinical assessments (e.g., functional walking measures). This study assesses the reliability of an IMU-based overground gait analysis during the 2-min walk test (2mWT) in individuals with spinal cord injury (SCI). Furthermore, the study elaborates on the capability of IMUs to distinguish between different gait characteristics in individuals with SCI. Twenty-six individuals (aged 22–79) with acute or chronic SCI (AIS: C and D) completed the 2mWT with IMUs attached above each ankle on 2 test days, separated by 1 to 7 days. The IMU-based gait analysis showed good to excellent test–retest reliability (ICC: 0.77–0.99) for all gait parameters. Gait profiles remained stable between two measurements. Sensor-based gait profiling was able to reveal patient-specific gait impairments even in individuals with the same walking performance in the 2mWT. IMUs are a valuable add-on to clinical gait assessments and deliver reliable information on detailed gait pathologies in individuals with SCI.Trial registration: NCT04555759.

Background: Accurate prediction of walking function after a traumatic spinal cord injury (SCI) is crucial for an appropriate tailoring and application of therapeutical interventions. Long-term outcome of ambulation is strongly related to residual muscle function acutely after injury and its recovery potential. The identification of the underlying determinants of ambulation, however, remains a challenging task in SCI, a neurological disorder presented with heterogeneous clinical manifestations and recovery trajectories. Objectives: Stratification of walking function and determination of its most relevant underlying muscle functions based on stratified homogeneous patient subgroups. Methods: Data from individuals with paraplegic SCI were used to develop a prediction-based stratification model, applying unbiased recursive partitioning conditional inference tree (URP–CTREE). The primary outcome was the 6-minute walk test at 6 months after injury. Standardized neurological assessments ≤15 days after injury were chosen as predictors. Resulting subgroups were incorporated into a subsequent node-specific analysis to attribute the role of individual lower extremity myotomes for the prognosis of walking function. Results: Using URP–CTREE, the study group of 361 SCI patients was divided into 8 homogeneous subgroups. The node specific analysis uncovered that proximal myotomes L2 and L3 were driving factors for the differentiation between walkers and non-walkers. Distal myotomes L4–S1 were revealed to be responsible for the prognostic distinction of indoor and outdoor walkers (with and without aids). Conclusion: Stratification of a heterogeneous population with paraplegic SCI into more homogeneous subgroups, combined with the identification of underlying muscle functions prospectively determining the walking outcome, enable potential benefit for application in clinical trials and practice.

Study design: Multicentre-observational study. Objectives: The 6-minute walk test (6mWT) is an established assessment of walking function in individuals with spinal cord injury (SCI). However, walking 6 min can be demanding for severely impaired individuals. The 2-minute walk test (2mWT) could be an appropriate alternative that has already been validated in other neurological disorders. The aim of this study was to assess construct validity and test-rest reliability of the 2mWT in individuals with SCI. In addition, the influence of walking performance on sensitivity to change of the 2mWT was assessed. Setting: Swiss Paraplegic Center Nottwil, Switzerland; Balgrist University Hospital, Zürich, Switzerland. Methods: Fifty individuals (aged 18–79) with SCI (neurological level of injury: C1-L3, AIS: A-D) were assessed on two test days separated by 1 to 7 days. The first assessment consisted of a 2mWT familiarization, followed by a 2mWT and 10-meter walk test (10MWT) (including the Walking Index for Spinal Cord Injury (WISCI II)) in randomized order. The second assessment consisted of 2mWT and 6mWT in randomized order. Tests were separated by at least 30 min of rest. Results: The interclass correlation coefficient between the 2mWT assessed on the first and second test day was excellent (r = 0.980, p < 0.001). The 2mWT correlated very strongly with the 6mWT (r = 0.992, p < 0.001) and the 10MWT (r = 0.964, p < 0.001), and moderately with the WISCI II (r = 0.571, p < 0.001). Sensitivity to change was slightly affected by walking performance. Conclusion: The 2mWT is a valid and reliable alternative to the 6mWT to measure walking function in individuals with SCI. Trial registration: NCT04555759.

Background: New therapeutic approaches in neurological disorders are progressing into clinical development. Past failures in translational research have underlined the critical importance of selecting appropriate inclusion criteria and primary outcomes. Narrow inclusion criteria provide sensitivity, but increase trial duration and cost to the point of infeasibility, while broader requirements amplify confounding, increasing the risk of trial failure. This dilemma is perhaps most pronounced in spinal cord injury (SCI), but applies to all neurological disorders with low frequency and/or heterogeneous clinical manifestations. Objective: Stratification of homogeneous patient cohorts to enable the design of clinical trials with broad inclusion criteria. Methods: Prospectively–gathered data from patients with acute cervical SCI were analysed using an unbiased recursive partitioning conditional inference tree (URP–CTREE) approach. Performance in the 6-minute walk test at 6 months after injury was classified based on standardized neurological assessments within the first 15 days of injury. Functional and neurological outcomes were tracked throughout rehabilitation up to 6 months after injury. Results: URP–CTREE identified homogeneous outcome cohorts in a study group of 309 SCI patients. These cohorts were validated by an internal, yet independent, validation group of 172 patients. The study group cohorts identified demonstrated distinct recovery profiles throughout rehabilitation. The baseline characteristics of the analysed groups were compared to a reference group of 477 patients. Conclusion: URP–CTREE enables inclusive trial design by revealing the distribution of outcome cohorts, discerning distinct recovery profiles and projecting potential patient enrolment by providing estimates of the relative frequencies of cohorts to improve the design of clinical trials in SCI and beyond.