Neurorehabilitation and neural repair最新文献

{"title":"Safety of Early Rehabilitation Dose After Stroke on Composite Outcomes: Analysis of Nationwide Japanese Medical Claims Data.","authors":"Takuaki Tani, Upul Cooray, Daisuke Nishida, Kiyohide Fushimi, Takaaki Ikeda","doi":"10.1177/15459683261469074","DOIUrl":"https://doi.org/10.1177/15459683261469074","url":null,"abstract":"<p><strong>Introduction: </strong>Early rehabilitation guidelines lack a consensus on the optimal early rehabilitation regimen; hence, the impact of rehabilitation timing and dose on stroke recovery outcomes remains unclear. Using Japanese medical claims data within a target trial emulation framework, this study evaluated the safety of early in-hospital rehabilitation after stroke.</p><p><strong>Patients and methods: </strong>This study analyzed patients aged ≥ 18 years who were admitted to an acute hospital for acute stroke and received in-hospital rehabilitation within 2 days after admission, using the Japan Diagnosis Procedure Combination database (2018-2022). Rehabilitation exposures were defined as 6 predefined regimens (20-60 min/day initiated on days 1 or 2) and continued up to day 14. The outcome was the cumulative incidence of composite adverse events within 15 days after admission. A sequential, doubly robust estimator with a longitudinal modified treatment policy was applied, accounting for time-varying exposures and reducing potential time-related biases.</p><p><strong>Results: </strong>Using a target trial emulation framework with doubly robust estimation, the incidence under the reference regimen was 11.2% (95% CI: 9.75%-12.60%). The highest incidence was 26.20% (95% CI: 24.30%-28.20%), corresponding to a risk ratio (RR) of 2.35 (95% CI: 2.03-2.72) compared with the reference. In contrast, several higher-intensity regimens were associated with lower incidences, with the lowest incidence of .49% (95% CI: .28%-.71%), yielding an RR of .04 (95% CI: .03-.07) versus the reference. However, intermediate-dose regimens showed variable associations across scenarios.</p><p><strong>Discussion and conclusion: </strong>In this emulated trial, higher early rehabilitation doses were generally associated with a lower incidence of in-hospital adverse events. Regimens involving 60 min/day, particularly when initiated on day 1, showed the lowest estimated risk. However, the associations were not strictly linear, as intermediate-dose regimens demonstrated variable results across analyses. These findings suggest a potential benefit of adequately dosed early rehabilitation when clinically appropriate, while highlighting the importance of careful patient selection and monitoring.</p>","PeriodicalId":94158,"journal":{"name":"Neurorehabilitation and neural repair","volume":" ","pages":"15459683261469074"},"PeriodicalIF":3.7,"publicationDate":"2026-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148595273","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development and Content Validity of the Movement Compensatory Screening (MoCS): A Structured Framework for Identifying Compensatory Strategies After Stroke.","authors":"Pedro Henrique Sousa de Andrade, Rodrigo Bazan, Luciane Aparecida Pascucci Sande de Souza, Gustavo José Luvizutto","doi":"10.1177/15459683261464075","DOIUrl":"https://doi.org/10.1177/15459683261464075","url":null,"abstract":"<p><strong>Background: </strong>Compensatory movement strategies are common after stroke and vary across individuals and tasks. However, the lack of a structured framework to guide movement analysis during mobility and postural control tasks may limit consistent identification of these strategies across clinicians in clinical practice.</p><p><strong>Objective: </strong>To develop and examine the content validity of the Movement Compensatory Screening (MoCS) to identify compensatory movement strategies during mobility and postural control tasks after stroke.</p><p><strong>Methods: </strong>Following the Delphi method and COSMIN guidelines, the MoCS was developed through a multi-phase process. Item generation was based on a literature review, exploratory video analysis of individuals after stroke, and expert input. Item-level content validity was evaluated in 2 Delphi rounds using relevance and clarity ratings (Content Validity Coefficient ≥ 0.80). Instrument-level content comprehensiveness was subsequently assessed through a Delphi-based global evaluation by physiotherapists.</p><p><strong>Results: </strong>The final MoCS comprised 65 items across 7 domains: sit-to-stand and stand-to-sit transfer, gait, turn, climb up/down stairs, and dynamic standing balance. Initial mean CVC values were 0.89 for relevance and 0.86 for clarity, leading to item exclusion or refinement. Revised items achieved mean CVC values of 0.93 and 0.88 and were retained. An instrument-level evaluation indicated adequate content comprehensiveness, with expert agreement that the final item set sufficiently covered compensatory movement domains. A compensatory index (CI) was used to describe compensatory strategies by domain and anatomical plane.</p><p><strong>Conclusion: </strong>The MoCS demonstrated content validity as an observational framework for identifying compensatory movement strategies during mobility and postural control tasks after stroke.</p>","PeriodicalId":94158,"journal":{"name":"Neurorehabilitation and neural repair","volume":" ","pages":"15459683261464075"},"PeriodicalIF":3.7,"publicationDate":"2026-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148595315","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Heterogeneous Recruitment Curve Responses to Anodal Transcranial Direct Current Stimulation in Children With Unilateral Spastic Cerebral Palsy.","authors":"Nicole Metelski, Andrew M Gordon, Shivakeshavan Ratnadurai-Giridharan, Claudio L Ferre, Maxime T Robert, Kathleen M Friel","doi":"10.1177/15459683261464051","DOIUrl":"10.1177/15459683261464051","url":null,"abstract":"<p><strong>Background: </strong>Children with unilateral spastic cerebral palsy (USCP) exhibit altered corticospinal organization that may influence responsiveness to treatment. Transcranial direct current stimulation (tDCS) may modulate corticospinal excitability, though responses vary widely. Recruitment curves derived from transcranial magnetic stimulation (TMS) can quantify excitability changes.</p><p><strong>Objective: </strong>To evaluate the feasibility, safety, and preliminary effects of combined TMS and anodal tDCS on recruitment curve-derived corticospinal excitability in children with USCP and explore predictors of responsiveness.</p><p><strong>Methods: </strong>In a single-group pre/post study, 20 children with USCP completed TMS-evoked recruitment curve testing before and after 20 minutes of 2mA anodal tDCS. Primary outcomes included changes in S50 (half-maximal motor-evoked potential [MEP] intensity) and slope at the curve inflection point. Secondary outcomes included MEP amplitude-based and model-derived recruitment curve metrics. Safety and tolerability were assessed using a standardized symptom screen.</p><p><strong>Results: </strong>The protocol was well-tolerated: no serious adverse events occurred, 80% reported no symptoms, and the most common symptom was mild scalp itching. No significant group-level pre/post differences were observed in this preliminary study. Responses were heterogeneous: 11/20 children met the responder definition (ΔS50 < 0). Exploratory analyses identified no consistent clinical or neurophysiologic predictors, although a potential responder pattern was observed in participants with bilateral corticospinal tract patterns.</p><p><strong>Conclusions: </strong>Although uniform group-level excitability changes were not observed following a single session of 2mA anodal tDCS, recruitment curve metrics were feasible, well-tolerated, and sensitive to interindividual differences. These findings support the use of recruitment curves as feasible tools to characterize variability and inform individualized neuromodulation strategies.<b>Trial registration number</b>: NCT03402854.</p>","PeriodicalId":94158,"journal":{"name":"Neurorehabilitation and neural repair","volume":" ","pages":"15459683261464051"},"PeriodicalIF":3.7,"publicationDate":"2026-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13384198/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148474938","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Neural Correlates of Balance in People With Parkinson's Disease, Older, and Younger Adults: An fNIRS Study.","authors":"Patrick Tait, Rodrigo Vitorio, Lisa Graham, Tamlyn Watermeyer, Richard Walker, Claire McDonald, Martina Mancini, Samuel Stuart, Rosie Morris","doi":"10.1177/15459683261454945","DOIUrl":"https://doi.org/10.1177/15459683261454945","url":null,"abstract":"<p><strong>Background: </strong>Postural instability is one of the most debilitating symptoms of Parkinson's disease (PD). Moreover, older adults (OA) often show issues with postural control leading to increased fall-risk. However, the current understanding of the neural underpinnings of standing postural control remains limited. This study aims to investigate cortical control of postural control in OA, younger adults (YA), and people with PD (PwPD), using functional near-infrared spectroscopy (fNIRS).</p><p><strong>Methods: </strong>A total of four 2-minute standing conditions were performed. Postural control and cortical activity were recorded in 80 PwPD, 33 OA, and 38 YA. A wireless fNIRS system recorded changes in relative oxygenated haemoglobin (∆HbO₂) across cortical regions including the prefrontal cortex (PFC), supplementary motor area (SMA), primary motor cortex (M1), primary somatosensory cortex (S1), and primary visual cortex (V1). Six wearable sensors provided sway outcome measures (area, jerkiness velocity, root mean square, and frequency).</p><p><strong>Results: </strong>Sway outcomes were greater across several conditions in PwPD. Significant group effects were found with increased ∆HbO² in the PFC in PD compared to OA. Moreover, YA had increased ∆HbO₂ in the S1 compared to OA and PD.</p><p><strong>Conclusions: </strong>PwPD showed greater PFC recruitment, indicating reliance on executive-attentional resources for balance. In contrast, YA engaged somatosensory regions more strongly, suggesting that ageing may affect the integration of sensory information for postural control. Findings support interventions that (a) reduce executive load during balance in PD and (b) bolster somatosensory integration in ageing.</p>","PeriodicalId":94158,"journal":{"name":"Neurorehabilitation and neural repair","volume":" ","pages":"15459683261454945"},"PeriodicalIF":3.7,"publicationDate":"2026-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148431799","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Levodopa-Based Therapy in Stroke Rehabilitation: A Systematic Review and Meta-Analysis of Randomized Controlled Trials.","authors":"Joseph Y Bena Nnang, Favour M L Foncha, Samuel G J Fodop, Dimitri S Tcheuko, Best C I Poudjoum, Tanyiche C Agelanu, Joel G Konlack Mekontso, Ignatius Esene","doi":"10.1177/15459683261432098","DOIUrl":"10.1177/15459683261432098","url":null,"abstract":"<p><p>BackgroundThe dopaminergic system plays a key role in neuroplasticity and motor learning, suggesting that levodopa can enhance recovery after stroke. However, the clinical evidence is inconsistent. This systematic review and meta-analysis aimed to provide a definitive synthesis of randomized controlled trials (RCTs) that evaluated levodopa-based therapy as an adjunct to stroke rehabilitation.MethodsFollowing PRISMA and Cochrane guidelines, we systematically searched PubMed, Embase, and CENTRAL from inception to October 2025 for RCTs comparing levodopa with placebo in adults who had experienced a stroke and were undergoing rehabilitation. The primary outcome was motor recovery, which was assessed using validated scales (eg, Fugl-Meyer Assessment). Secondary outcomes included mood and cognitive function. Pooled standardized mean differences (SMDs) were calculated using a random-effects model with the Hartung-Knapp-Sidik-Jonkman adjustment.ResultsSeven RCTs comprising 1257 participants (mean age, 62-73 years) met the inclusion criteria. Levodopa had no significant effect on motor function compared with placebo (SMD: 0.01; 95% CI: -0.10 to 0.13; <i>I</i>² = 0%), mood (SMD: -0.10; 95% CI: -0.30 to 0.10; <i>I</i>² = 3%), or cognition (SMD: -0.05; 95% CI: -0.29 to 0.19; <i>I</i>² = 0%). Sensitivity analyses confirmed the stability of the results.ConclusionsLevodopa-based therapy does not improve motor, cognitive, or mood outcomes during stroke rehabilitation. These findings close a long-standing question and indicate that dopaminergic augmentation should not be used routinely outside of mechanistic or biomarker-stratified trials.</p>","PeriodicalId":94158,"journal":{"name":"Neurorehabilitation and neural repair","volume":" ","pages":"553-565"},"PeriodicalIF":3.7,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147617034","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Looking Beyond Dose: Identifying Responders and Non-Responders to RehaCom Computerized Cognitive Rehabilitation in Progressive MS-The CogEx Study.","authors":"Cecilia Meza, Roberto S Hernandez, Silvana L Costa, Amber Salter, Nancy D Chiaravalloti, Maria Pia Amato, Giampaolo Brichetto, Jeremy Chataway, Gary Cutter, Ulrik Dalgas, John DeLuca, Rachel Farrell, Peter Feys, Massimo Filippi, Jennifer Freeman, Matilde Inglese, Robert W Motl, Maria A Rocca, Brian M Sandroff, Anthony Feinstein","doi":"10.1177/15459683261432556","DOIUrl":"10.1177/15459683261432556","url":null,"abstract":"<p><p>BackgroundRehaCom, a computerized cognitive rehabilitation program for people with multiple sclerosis (PwMS), has been studied primarily in relation to treatment \"dose\" (duration, frequency, and adherence), with less focus on which training modules drive improvement or which participant factors predict responsiveness. This secondary analysis of the CogEx trial investigated whether progression within specific RehaCom modules was associated with processing speed improvement, measured by the SDMT, and whether baseline characteristics predicted response in participants with progressive MS.MethodsA total of 153 participants completed 12 weeks of RehaCom training across 5 attention-based modules. Cognition was assessed at baseline, 12 weeks, and 6 months using the SDMT. Correlation and regression analyses evaluated associations between module progression and cognitive outcomes.ResultsProgression correlated significantly with SDMT improvement in 4 modules, with the strongest effects for Attention/Concentration (<i>r</i> = .37, <i>P</i> < .001) and Divided Attention-2 (<i>r</i> = .36, <i>P</i> < .001). Higher baseline SDMT, higher premorbid IQ, older age, and greater module progression independently predicted better SDMT performance at12-weeks (adjusted <i>R</i>² = .73). At 6 months, higher baseline SDMT, greater progression in Attention/Concentration and Divided Attention-2, older age, and female sex predicted better SDMT performance (adjusted <i>R</i>² = .71).ConclusionProcessing speed gains in progressive MS were related to both module-specific progression and participant characteristics, supporting a precision approach to cognitive rehabilitation that tailors training content to individual cognitive profiles. This study is a secondary analysis of the CogEx trial (ClinicalTrials.gov Identifier: NCT03679468; https://clinicaltrials.gov/ct2/show/NCT03679468).</p>","PeriodicalId":94158,"journal":{"name":"Neurorehabilitation and neural repair","volume":" ","pages":"575-586"},"PeriodicalIF":3.7,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13291402/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147793426","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mapping Brain Function After Stroke: From Early Disorganization to Late Compensation.","authors":"Célia Delcamp, Zhibin Zhou, Ramesh Srinivasan, Steven C Cramer","doi":"10.1177/15459683261426352","DOIUrl":"10.1177/15459683261426352","url":null,"abstract":"<p><p>IntroductionElectroencephalography (EEG) is useful to capture changes in brain function after stroke. How these relate to time after stroke and deficit severity remains unclear. We examined these issues by testing specific hypotheses using cortical power and functional connectivity.MethodsThis cross-sectional study included 100 stroke patients and 45 healthy controls. Cortical power and connectivity (coherence) were extracted from a 3-minute resting-state dense-array (256-lead) EEG. Analysis included subgroups based on time post-stroke (<or≥ 90 days) and motor status (Fugl-Meyer score ≤or> 40) using robust permutation tests and partial Spearman's correlations.ResultsEarly after stroke, power was supranormal in low frequency bands and subnormal in high frequency bands, while brain connectivity was widely subnormal. With greater time post-stroke, beta and gamma connectivity were higher bilaterally, and brain connectivity was supranormal in the late phase across all frequency bands. Motor status was related to cortical power only in cortico-subcortical patients and was related to connectivity in a manner that varied according to severity of motor deficit and lesion location.ConclusionsResults support use of EEG measures as biomarkers of brain reorganization after stroke and emphasize the need for a nuanced understanding according to individual details. Current findings indicate that motor deficits are best understood using a network connectivity approach and highlight the need to interpret EEG measures post-stroke within the specific context (time post-stroke, deficit severity, and lesion location) in which they are acquired to maximize their utility as biomarkers to guide personalized rehabilitation.</p>","PeriodicalId":94158,"journal":{"name":"Neurorehabilitation and neural repair","volume":" ","pages":"537-552"},"PeriodicalIF":3.7,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13055745/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147625072","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Postural Control Determinants of Gait Dysfunction in Huntington's Disease.","authors":"Franchino Porciuncula, Paula Wasserman, Karen S Marder, Ashwini K Rao","doi":"10.1177/15459683261445976","DOIUrl":"10.1177/15459683261445976","url":null,"abstract":"<p><strong>Background: </strong>Gait dysfunction is an important concern in Huntington's disease (HD). The influence of HD-specific postural control impairments on gait dysfunction, from pre-manifest HD (pHD) to manifest HD (mHD), is poorly understood.</p><p><strong>Objectives: </strong>To explore the interplay of posture and gait in HD, we first (Aim 1) quantified the extent of deficits in postural control and gait across the spectrum of HD. Subsequently (Aim 2), we examined the contributions of postural control impairments to gait dysfunction.</p><p><strong>Methods: </strong>Participants (N = 38) included healthy controls (n = 10), pHD (n = 17), and mHD (n = 11). We quantified postural control using wearable sensors during sensory-challenging conditions using Jerk and Total Sway Area, and gait at self-selected pace, using outcomes of gait quality (peak swing velocity, stride length, cadence, %stance, and %swing) and stride-to-stride variability. We examined between-group differences (Aim 1) and conducted multiple regression analyses (Aim 2).</p><p><strong>Results: </strong>Impairments in postural control (Jerk and Total Sway Area) and gait (primarily variability) were evident in pHD and substantially increased in mHD (<i>P</i> < .05). Postural control deficits explained 14% to 39% of variance of gait dysfunction based on quality and variability, and gait items of the Unified Huntington's Disease Rating Scale (<i>P</i> < .05).</p><p><strong>Conclusions: </strong>Deficits in postural control and gait begin in the pre-manifest stage, and worsen in manifest HD, highlighting the need for earlier intervention. Our results highlight that postural control deficits contribute substantially to gait deficits in HD, rather than merely co-occurring. Further investigation is required to understand how posture-gait link can be applied to clinical gait rehabilitation programs.</p>","PeriodicalId":94158,"journal":{"name":"Neurorehabilitation and neural repair","volume":" ","pages":"587-597"},"PeriodicalIF":3.7,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147793435","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Corrigendum to \"Exploring the Evolution of Cortical Excitability Following Acute Stroke\".","authors":"","doi":"10.1177/15459683261447055","DOIUrl":"10.1177/15459683261447055","url":null,"abstract":"","PeriodicalId":94158,"journal":{"name":"Neurorehabilitation and neural repair","volume":" ","pages":"598"},"PeriodicalIF":3.7,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147793431","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Unsupervised Data Driven Clustering of the Neurological Assessments of People With Traumatic SCI Focusing on Sensorimotor Complete Injuries.","authors":"Olga Taran, Rüdiger Rupp, Louis P Lukas, Adrian Kaufmann, Norbert Weidner, Martin Schubert, Björn Zörner, Frank Röhrich, Josina Waldmann, Yorck B Kalke, Rainer Abel, Doris Maier, Fred H Geisler, Armin Curt, Catherine R Jutzeler, Sarah C Brüningk","doi":"10.1177/15459683261454947","DOIUrl":"https://doi.org/10.1177/15459683261454947","url":null,"abstract":"<p><strong>Background: </strong>Spinal cord injury (SCI) leads to lifelong disability with highly variable neurological recovery, complicating prognostication and conceptualization of clinical trials. The American Spinal Injury Association Impairment Scale (AIS) is widely used to classify injury severity. Although AIS A injuries are considered sensorimotor complete, they show substantial heterogeneity in residual function and recovery. Data-driven approaches offer an opportunity to uncover latent subgroups beyond conventional classifications. We evaluate whether unsupervised, data-driven clustering can identify distinct subgroups within patients with traumatic SCI and characterize neurological patterns in sensorimotor complete SCI.</p><p><strong>Methods: </strong>We applied an unsupervised clustering model to International Standards of Neurological Classification of Spinal Cord Injury (ISNCSCI) examination scores from the European Multicenter Study about Spinal Cord Injury dataset (3165 patients), to derive neurological groupings independent of predefined ISNCSCI classifications. Clusters were derived from the full cohort, followed by focused analyses of individuals classified as AIS A at their first documented assessment. External reproducibility was evaluated using data from the Sygen clinical trial.</p><p><strong>Results: </strong>Six distinct clusters were identified. Patients graded as AIS A were represented in 5 clusters, which differed markedly in injury level (paraplegic vs tetraplegic) and indicators of recovery potential, including neurological sparing, upper and lower extremity motor scores, and AIS conversion rates. These patterns were consistently reproduced in the Sygen cohort.</p><p><strong>Conclusions: </strong>Proposed framework complements conventional AIS grading by revealing distinct neurological conditions related to the variability among patients with baseline sensorimotor complete injuries. Proposed data-driven framework enables more comprehensive prognostic assessments and improves patient stratification in clinical trials.</p>","PeriodicalId":94158,"journal":{"name":"Neurorehabilitation and neural repair","volume":" ","pages":"15459683261454947"},"PeriodicalIF":3.7,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148371495","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}