Neurorehabilitation and neural repair最新文献

{"title":"Stage-Related Sensory Integration Deficits and Fall Risk in Parkinson's Disease.","authors":"Xiaoqing Luo, Jingxin Wang, Yuqin Shi, Yue Li, Shuangfang Li, Lu Wei, Meixiang Zhang, Lingjing Jin, Qing Zhao","doi":"10.1177/15459683261448478","DOIUrl":"https://doi.org/10.1177/15459683261448478","url":null,"abstract":"<p><strong>Introduction: </strong>Postural balance dysfunction in Parkinson's disease (PD) is associated with sensory integration deficits, yet stage-related changes and their relationship with falls remain incompletely understood. This study evaluated sensory integration across Hoehn-Yahr stages and prospectively monitored falls over 6 months.</p><p><strong>Methods: </strong>Seventy-five PD patients (26 early-stage and 49 advanced-stage) and 26 healthy controls (HCs) were assessed using the Sensory Organization Test. Demographic and motor assessments were performed, and falls were tracked for 6 months. Group comparisons used 1-way analysis of variance or Kruskal-Wallis tests, as appropriate. Associations with fall status were analyzed using χ² tests.</p><p><strong>Results: </strong>Advanced-stage PD patients were older and exhibited more severe motor symptoms than early-stage patients. Sensory integration deteriorated with disease progression. Compared with HCs and early-stage PD patients, advanced-stage PD patients demonstrated significantly reduced composite balance scores (<i>P</i> < .001). Significant overall group differences were observed for visual (<i>P</i> = .029), vestibular (<i>P</i> < .001), and preference ratios (<i>P</i> < .001), whereas somatosensory ratios remained preserved. Falls occurred in 33.3% of PD patients and were more frequent in advanced stages (44.9% vs 11.5%; <i>P</i> < .001). Vestibular dysfunction was significantly associated with fall occurrence (76.0% vs 38.0%; <i>P</i> = .002).</p><p><strong>Conclusion: </strong>Sensory integration deficits in PD progress with disease advancement and are primarily characterized by impairments in visual and vestibular domains. Vestibular dysfunction was significantly associated with fall risk. These findings suggest that vestibular assessment and targeted interventions may be beneficial for fall-risk management in PD.</p>","PeriodicalId":94158,"journal":{"name":"Neurorehabilitation and neural repair","volume":" ","pages":"15459683261448478"},"PeriodicalIF":3.7,"publicationDate":"2026-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148674914","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":"External Validation of a Machine Learning Model for the Early Prediction of Upper-Limb Recovery After Stroke.","authors":"G J van der Gun, R W Selles, I C Brunner, C Biering Lundquist","doi":"10.1177/15459683261469091","DOIUrl":"https://doi.org/10.1177/15459683261469091","url":null,"abstract":"<p><strong>Background: </strong>Reliable prediction of upper-limb recovery after stroke can support rehabilitation planning, yet few prognostic models have been tested beyond their development cohorts. External validation is essential to establish the clinical reliability of these methods.</p><p><strong>Objective: </strong>To externally validate a previously developed machine learning model for predicting 6-month upper-limb capacity after stroke, measured by the Action Research Arm Test (ARAT).</p><p><strong>Methods: </strong>The model was developed on a multicentre Dutch cohort of first-ever ischaemic stroke patients and validated in an independent Danish prospective cohort, including both ischaemic and haemorrhagic strokes. Predictions were generated from baseline assessments at 2 weeks post-stroke. Model performance was evaluated using the median absolute error (MedAE) and calibration analysis.</p><p><strong>Results: </strong>The validation cohort comprised 80 patients assessed at 14 ± 4 days post-stroke. Overall prediction error was comparable between the validation and development cohorts (MedAE = 5.7 [IQR 1.9-15.1] vs 3.9 [IQR 1.1-13.0]; P = 0.12). Calibration was close to ideal for predicted ARAT scores above 40. In contrast, lower predicted ranges showed systematic underprediction, reflecting variable outcomes in severely impaired patients, a pattern similar to that observed in the development cohort.</p><p><strong>Conclusions: </strong>In an independent validation cohort, the machine learning model performed similarly to its development cohort but showed clinically relevant miscalibration in patients with low predicted ARAT scores. Inclusion of additional predictors is required to improve reliability in severely impaired patients before subsequent steps toward clinical implementation can be considered.</p>","PeriodicalId":94158,"journal":{"name":"Neurorehabilitation and neural repair","volume":" ","pages":"15459683261469091"},"PeriodicalIF":3.7,"publicationDate":"2026-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148665339","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":"Atypical Dual-Task Cost and Reduced Attentional Neural Modulation in Parkinson's Disease With Freezing of Gait.","authors":"Ing-Shiou Hwang, Yu-An Chen, Ruey-Meei Wu, Cheng-Ya Huang","doi":"10.1177/15459683261448466","DOIUrl":"10.1177/15459683261448466","url":null,"abstract":"<p><strong>Background: </strong>Dual-task walking poses substantial challenges for individuals with Parkinson's disease (PD), particularly those with freezing of gait (FOG), as dual-task interference increases fall risk and limits functional mobility.</p><p><strong>Objective: </strong>To investigate dual-task interference at both the behavioral and neural levels in PD individuals with FOG (PDFOG+) and those without FOG (PDFOG-) during dual-task walking involving a demanding manual task.</p><p><strong>Methods: </strong>Seventeen PDFOG- and 17 PDFOG+ participated in this study. Gait performance, manual-task performance, and scalp electroencephalograph (EEG) were recorded in single-task condition and dual-task walking while performing a high attentional-load manual task (an interlocking ring task). The primary behavioral outcomes were dual-task costs (DTC) of gait velocity and ring performance, representing locomotor interference and manual-task interference, respectively. The primary neural outcomes focused on theta-band EEG measures, including regional theta power and inter-regional theta connectivity, given their established role in attentional control during dual-task walking in PDFOG+.</p><p><strong>Results: </strong>Compared with PDFOG-, PDFOG+ exhibited significantly less DTC of gait velocity and greater DTC of ring performance. At the neural level, PDFOG+ demonstrated attenuated task-dependent modulations of increased theta-band power and decreased theta-band connectivity relative to PDFOG-.</p><p><strong>Conclusions: </strong>PDFOG+ exhibited an atypical pattern of dual-task interference characterized by preserved gait velocity at the expense of concurrent manual-task performance, together with diminished theta-band attentional modulation. These findings suggest limited flexibility in attentional resource allocation in PDFOG+ and highlight theta-band neural dynamics as a key mechanism underlying maladaptive task-task regulation during walking.</p><p><strong>Trial registration: </strong>National Taiwan University Hospital Research Ethics Committee: No. NCT03298503.</p>","PeriodicalId":94158,"journal":{"name":"Neurorehabilitation and neural repair","volume":" ","pages":"631-642"},"PeriodicalIF":3.7,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147848337","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":"Minimal Impact of Low Vision on Explicit Sensorimotor Adaptation.","authors":"Mihai Cipleu, Sritej Padmanabhan, Emily A Cooper, Jonathan S Tsay","doi":"10.1177/15459683261445439","DOIUrl":"10.1177/15459683261445439","url":null,"abstract":"<p><strong>Objective: </strong>Rehabilitation from motor system dysfunction relies on learning deliberate motor corrections through practice and feedback. This is called explicit motor adaptation. One key source of feedback for this adaptation is the visual error signal between the intended movement and the achieved movement. As people age, both motor dysfunction and visual impairment become more common, potentially compromising the visual feedback signal. Previous work has shown that visual impairment can disrupt the implicit, automatic adjustments made by the sensorimotor system. But how visual impairment influences explicit motor adaptation, a cornerstone of rehabilitation, remains unknown.</p><p><strong>Methods: </strong>To address this gap, we recruited individuals with low vision (LV), defined as uncorrectable visual impairment resulting in functional vision loss, and age-matched controls to complete a visuomotor task designed to isolate 2 components of explicit motor adaptation: discovering a new deliberate sensorimotor strategy and recalling a previously learned one.</p><p><strong>Results: </strong>Surprisingly, LV was not associated with a measurable impact on either component. Individuals with LV were as effective as controls in both discovering and retrieving successful explicit sensorimotor strategies.</p><p><strong>Conclusion: </strong>Together, these findings identify explicit strategies as a resilient learning mechanism that can be potentially leveraged in motor rehabilitation, even when visual input is degraded.</p>","PeriodicalId":94158,"journal":{"name":"Neurorehabilitation and neural repair","volume":" ","pages":"643-652"},"PeriodicalIF":3.7,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147864532","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":"Neuromechanics of Nonuse and Compensation: Implications for Rehabilitation After Stroke.","authors":"Germain Faity, Denis Mottet, Jérôme Froger, Marion Delorme","doi":"10.1177/15459683261445442","DOIUrl":"10.1177/15459683261445442","url":null,"abstract":"<p><strong>Background: </strong>Stroke often results in compensatory movement strategies that combine use of trunk movements with nonuse of the affected upper extremity, which is considered detrimental to recovery.</p><p><strong>Objective: </strong>In this study, we investigate whether compensation and nonuse can be more than a suboptimal counterpart to recovery. We explore the influence of neuromechanics on nonuse and compensation in 22 individuals with stroke and 22 controls.</p><p><strong>Methods: </strong>We asked seated participants to reach a target under 2 nonuse conditions (spontaneous or with minimized trunk compensation) and under 3 arm weight conditions (control, lightened, and weighted).</p><p><strong>Results: </strong>We replicated the findings that stroke induces more trunk compensation, more anterior deltoid activation and greater effort. We found that, in stroke patients, reduced arm weight decreased nonuse, while in controls, increased arm weight induced trunk compensation similar to what is observed after stroke. Furthermore, reaching with nonuse after stroke required less effort and preserved a force reserve at the shoulder.</p><p><strong>Conclusion: </strong>Our results show that both poststroke and healthy individuals engage in similar nonuse and compensation in the face of their neuromechanical limitations, as predicted by an optimal control policy aiming to succeed at the task while keeping a force reserve at each joint. We derive 2 theoretical predictions for future clinical research. First, patients whose nonuse yields few functional gains should benefit most from interventions to reduce compensation. Second, improving shoulder strength after stroke should reduce relative muscle activation, thereby decreasing trunk compensation and upper extremity nonuse.<i>Clinical Trial</i>. NCT04747587.</p>","PeriodicalId":94158,"journal":{"name":"Neurorehabilitation and neural repair","volume":" ","pages":"615-630"},"PeriodicalIF":3.7,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13392161/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147825305","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":"Clinical Efficacy and Preliminary Cost-Utility of Low-Frequency Repetitive Transcranial Magnetic Stimulation Versus Sham Stimulation for Neurogenic Overactive Bladder in Stroke Survivors: A Randomized Controlled Trial.","authors":"Mohammed Usman Ali, Kenneth N K Fong, Georg S Kranz, Jingjing Li, Crystal Kwan, Priya Kannan","doi":"10.1177/15459683261432087","DOIUrl":"10.1177/15459683261432087","url":null,"abstract":"<p><strong>Background: </strong>Neurogenic overactive bladder (OAB) among survivors is burdensome. Low-frequency repetitive transcranial magnetic stimulation (rTMS) is a promising non-invasive intervention requiring comprehensive evaluation of its clinical and economic impact.ObjectivesTo evaluate the efficacy, cost-utility, and stroke survivors' experiences of rTMS for neurogenic OAB.MethodsIn this randomized, assessor-blinded, sham-controlled trial, 60 stroke survivors with neurogenic OAB received active rTMS (1200 pulses 80% resting motor threshold [RMT]) or sham (20% RMT) thrice weekly for 4 weeks at contralateral primary motor cortex. The OAB Symptom Score (OABSS), Incontinence Quality of Life (I-QOL), and Brief Resilience Scale (BRS)-were measured at baseline, week 4, and week 8. Repeated measures analysis of covariance evaluated effects. Cost-utility analysis used societal costs and quality-adjusted life years (QALYs). Focus groups involved 12 active-group participants.ResultsActive rTMS (n = 30; 60% male; mean age = 62.1 ± 9.5 years) significantly improved OABSS (mean difference [MD] = 1.81 points, 95% confidence interval [CI] [1.42-2.20], <i>P</i> < .001), I-QOL (MD = 17.48 points, 95% CI [14.18-20.79], <i>P</i> < .001), and BRS (MD = 0.25 points, 95% CI [0.09-0.41], <i>P</i> = .002), at weeks 4 and 8 compared to sham (n = 30; 47% male; mean age = 61.7 ± 8.3 years). Active rTMS was associated with lower societal costs (HK$1267.3 vs HK$1839.0) and higher QALYs (0.691 vs 0.571) than sham. Qualitative data indicated excellent tolerability, symptom relief, and acceptability.ConclusionsLow-frequency rTMS is clinically effective, safe, acceptable, and potentially cost-saving for post-stroke neurogenic OAB. Larger trials with active comparators and extended follow-up are warranted.Trial RegistrationThis trial was registered at http://ClinicalTrials.gov (reference number: NCT05557175) before the recruitment of the first participant.</p>","PeriodicalId":94158,"journal":{"name":"Neurorehabilitation and neural repair","volume":" ","pages":"603-614"},"PeriodicalIF":3.7,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13392219/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147793362","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":"TDCS Modulates Inflammatory Markers to Improve Post-Stroke Cognitive Impairment and Depression: An Exploratory Randomized Trial.","authors":"Jingjing Liu, Wenyan Li, Wei Li, Yiheng Ma, Yinghua Wen, Junying Wu","doi":"10.1177/15459683261442186","DOIUrl":"10.1177/15459683261442186","url":null,"abstract":"<p><p>BackgroundPeripheral inflammatory markers may serve as indicators of cognitive impairment and depression after ischemic stroke. Post-stroke cognitive impairment hinders rehabilitation and quality of life. Transcranial direct current stimulation (tDCS) is a promising non-invasive intervention, but its link to inflammatory changes and clinical improvement remains unclear.ObjectiveTo evaluate tDCS effects on cognition and depression in stroke patients, and to examine if inflammatory marker changes underlie these effects.MethodsSixty patients were randomized to an experimental group (EG, n = 30) receiving active tDCS (2 mA, 20 minutes/day over affected dorsolateral prefrontal cortex) or a control group (CG, n = 30) receiving sham stimulation, alongside standard rehabilitation for 4 weeks. Serum interleukin-1β ( IL-1β), interleukin-6 (IL-6), interleukin-10 (IL-10), and tumor necrosis factor-α (TNF-α) levels were measured by enzyme-linked immunosorbent assay (ELISA) pre- and post-intervention. Cognition and depression were assessed using Montreal Cognitive Assessment (MoCA) and Hamilton Depression Scale (HAMD).ResultsPost-intervention, only the EG showed significant reductions in IL-6 and TNF-α (both <i>P</i> < .01), with no change in IL-1β or IL-10 (<i>P</i> > .05). The EG demonstrated greater improvement in MoCA and HAMD scores than the CG (<i>P</i> = .01 and .04). Changes in IL-6 (ΔIL-6) and TNF-α (ΔTNF-α) predicted improvements in MoCA scores (ΔMoCA, <i>R</i>² = .607, <i>P</i> < .01). ΔIL-6 and disease duration predicted improvements in HAMD scores (ΔHAMD, <i>R</i>² = .501, <i>P</i> < .01).ConclusiontDCS combined with conventional rehabilitation therapies may reduce pro-inflammatory cytokine levels and improve cognitive and depressive symptoms, supporting its potential application as an anti-inflammatory neurorehabilitation therapy.Clinical Trial registrationStudy on the mechanism of transcranial direct current stimulation in the intervention of working memory decline after stroke, https://www.chictr.org.cn/showproj.html?proj=208836, ChiCTR2300077242.</p>","PeriodicalId":94158,"journal":{"name":"Neurorehabilitation and neural repair","volume":" ","pages":"653-664"},"PeriodicalIF":3.7,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147944241","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":"In Memorium: Dr. Michelle Ploughman.","authors":"Dale Corbett","doi":"10.1177/15459683261454843","DOIUrl":"10.1177/15459683261454843","url":null,"abstract":"","PeriodicalId":94158,"journal":{"name":"Neurorehabilitation and neural repair","volume":" ","pages":"693-694"},"PeriodicalIF":3.7,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148195239","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":"Augmented Reality and Artificial Intelligence for the Assessment and Rehabilitation of Spatial Neglect: A Systematic Review.","authors":"Shaojun Li, Benjamin Chong, Ghazal Mehri-Kakavand, Catherine Shi, Denise Taylor, Allan Fowler, Mark Billinghurst, Monika Harvey, Alan Wang","doi":"10.1177/15459683261445440","DOIUrl":"10.1177/15459683261445440","url":null,"abstract":"<p><strong>Background and purpose: </strong>Augmented reality (AR) and artificial intelligence (AI) have been applied to the assessment and rehabilitation of post-stroke spatial neglect (SN). This study aims to evaluate the feasibility, effectiveness, degree of personalization, and ecological validity of AR, AI, and hybrid methods for SN assessment and rehabilitation.</p><p><strong>Methods: </strong>PubMed, Scopus, Web of Science, Embase, CINAHL, IEEE Xplore, and the ACM Digital Library were searched up to August 2025. Two reviewers independently screened articles, extracted data, and assessed risk of bias and outcome-level certainty.</p><p><strong>Results: </strong>Of 268 screened studies published between 2000 and 2025, 15 met the inclusion criteria, including 11 assessment studies (8 AI, 1 AR, and 2 hybrid) and 4 AR rehabilitation studies, involving 567 participants. AI assessment methods demonstrated high diagnostic accuracy (area under the curve (AUC) up to 0.95), and 1 AR assessment showed strong diagnostic accuracy (AUC = 0.89). Four AR rehabilitation studies reported acceptable feasibility, with 1 randomized controlled trial (RCT) showing improvements in several neglect outcomes. Ecological validity and personalization were generally very low, and the overall certainty of evidence ranged from low to very low.</p><p><strong>Conclusion: </strong>Current evidence for AR and AI SN assessment and rehabilitation methods remains insufficient to determine their feasibility, effectiveness, ecological validity, and degree of personalization, largely due to small sample sizes, methodological heterogeneity, and the limited number of RCTs. Future research should focus on developing standardized, scalable frameworks that integrate AR with adaptive AI models, and multicenter RCTs are required to confirm clinical efficacy and long-term functional outcomes.</p>","PeriodicalId":94158,"journal":{"name":"Neurorehabilitation and neural repair","volume":" ","pages":"678-692"},"PeriodicalIF":3.7,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13392187/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147825205","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":"External Validation of the EPOS Prediction Model for Independent Gait After Stroke.","authors":"Livia Vinzens, Martina Betschart, Janne Marieke Veerbeek","doi":"10.1177/15459683261425934","DOIUrl":"10.1177/15459683261425934","url":null,"abstract":"<p><strong>Background: </strong>Accurate gait recovery prognosis is crucial for guiding stroke rehabilitation. The Early Prediction of functional Outcome after Stroke (EPOS) model predicting independent gait 6 months poststroke, was previously validated in 2 small, homogenous samples of first-ever stroke patients without prestroke disability. This study aimed to externally validate the EPOS model in a heterogeneous stroke sample.</p><p><strong>Methods: </strong>A prospective longitudinal cohort study conducted in 2 Swiss acute stroke units. Eligible patients could not walk independently within 72 hours poststroke, regardless of stroke characteristics or prestroke disability. Sitting balance and paretic leg strength were assessed within 72 hours. Independent gait was evaluated at 3 months. The model's predictive performance was assessed using multiple metrics.</p><p><strong>Results: </strong>Two hundred eighty patients were analyzed (median age 76 years; 42% female). The model showed acceptable fit (Brier score 0.14, 95% confidence interval [CI] 0.11-0.18) and acceptable discrimination (area under the receiver operating characteristic curve 0.74, 95% CI 0.67-0.81). At the 0.5 threshold, sensitivity was 0.98 (95% CI 0.95-0.99) and specificity 0.32 (95% CI 0.21-0.45). Decision curve analysis indicated clinical usefulness across thresholds from 0.28 to 0.90.</p><p><strong>Conclusions: </strong>The EPOS model demonstrated moderate predictive performance for regaining independent gait at 3 months when applied within 72 hours poststroke in a heterogeneous cohort. A high-sensitivity threshold is recommended, classifying only patients lacking sitting balance and hemiplegic leg strength as unlikely to regain gait independence, preventing missing recovery potential. As a next step, the model's impact on decision-making, patient outcomes, and healthcare resources should be evaluated in comparable settings.</p><p><strong>Trial registration: </strong>NCT06438770, NCT05039047.</p>","PeriodicalId":94158,"journal":{"name":"Neurorehabilitation and neural repair","volume":" ","pages":"665-677"},"PeriodicalIF":3.7,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147944275","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}