Patients’ engagement plays a crucial role in the effectiveness of robot-assisted gait training (RAGT), particularly in paediatric neurorehabilitation, where motivation and active participation strongly influence functional outcomes. Despite its clinical relevance, engagement assessment is still largely based on subjective observation, limiting objectivity and scalability. Objective modelling of engagement in children with cerebral palsy remains underexplored, especially when relying on physiological signals acquired during therapy, due to logistical, ethical, and technological challenges that constrain multimodal data collection and cohort sizes. This study proposes a novel multimodal framework to automatically estimate engagement in a paediatric cerebral palsy population undergoing RAGT, capturing clinically relevant variability across patients. A cohort of 20 paediatric patients with cerebral palsy undergoing RAGT with the Hocoma Lokomat® system was monitored across multiple therapy sessions. Heart rate variability (HRV), facial infrared thermography (IRT), and exoskeleton-derived biomechanical features were acquired to capture complementary physiological and behavioural responses related to engagement. Signals were segmented into time windows and processed to extract statistical, spectral, and complexity features. Engagement was annotated by an expert clinician using a three-class scale (not engaged, neutral, engaged). A supervised multiclass machine-learning framework was then developed to estimate engagement from multimodal data, evaluating several ensemble-based classifiers under strict training–testing separation with repeated stratified splits and class-weighted learning to tackle class imbalance. The combination of multimodal features with the Extra Trees classifier achieved the best performance, with a macro-F1 score of 0.658 ± 0.027. Class-wise analysis showed higher performance for extreme engagement levels (not engaged and engaged), with most misclassifications occurring between adjacent classes, particularly involving the neutral state. Feature selection and explainability analyses identified exoskeleton-derived torque features as the most influential predictors, with thermal and HRV features providing complementary autonomic and emotional information. This study presents a novel multimodal machine learning approach for automatic engagement estimation during RAGT in children with cerebral palsy. Beyond classification performance, it demonstrates the feasibility of objective engagement modelling in a complex clinical population by integrating physiological and robotic interaction data. The results highlight the potential of multimodal sensing to support adaptive rehabilitation systems for continuous monitoring and personalized human–robot interaction.

BACKGROUND:Broad 6-month death-or-dependency outcomes after acute ischemic stroke can conceal opposing early benefit and harm pathways after antithrombotic treatment. We examined these pathways in the corrected public-use International Stroke Trial dataset. METHODS:We analyzed 19,285 randomized participants with assignable 6-month outcome classification; 150 with missing classification were excluded. The mediator was the first recorded selected event within 14 days or earlier death/discharge: early death, intracranial hemorrhage or hemorrhagic stroke, major extracranial bleeding, pulmonary embolism, recurrent stroke, or no selected event. Standardized risks, risk differences per 1000 patients, and risk ratios were estimated using robust Poisson regression and g-computation. Interventional direct and indirect effects were estimated with multinomial mediator and outcome models, marginalizing factorial co-allocation. RESULTS:Aspirin was associated with a small reduction in 6-month death or dependency (risk difference, -12.1 per 1000; risk ratio, 0.981). The interventional direct component was -9.8 per 1000 and the first-event-mediated component was -2.3 per 1000. Low-dose heparin had a near-null total effect (3.0 per 1000), with opposing direct (6.4) and indirect (-3.4) components. Higher-dose heparin also had a near-null composite effect (-1.9 per 1000), but mortality sensitivity analysis showed an unfavorable signal (15.6 per 1000). CONCLUSIONS:In this historical megatrial, small or near-null disability-inclusive effects were compatible with divergent early ischemic-prevention and bleeding-hazard pathways. Recorded first early events explained only part of the treatment-outcome contrasts. These estimates are methodological and interpretive, not contemporary prescribing guidance.

Background: Motivation is widely recognized as a key factor influencing learning and rehabilitation outcomes in children with cerebral palsy (CP). Despite its acknowledged relevance, motivation is rarely assessed systematically in pediatric neurorehabilitation, and there is limited consensus regarding appropriate outcome measures. Objectives: This systematic mapping review aimed to examine how motivation-related constructs are assessed in rehabilitation studies involving children with CP, identifying the instruments used and evaluating the extent to which motivation is explicitly measured across different rehabilitation contexts. Methods: The review was conducted in accordance with PRISMA guidelines and registered in PROSPERO (CRD420250651843). PubMed and Scopus were searched for studies published between 2013 and 2025. Eligible studies included rehabilitation interventions for children with CP that incorporated a clearly defined motivation-related outcome. Study quality and risk of bias were assessed using Joanna Briggs Institute tools and the RoB 2 tool. Results: Nine studies met the inclusion criteria, including 109 subjects, comprising randomized controlled trials and case series. Most studies involved children with mild to moderate motor impairment (GMFCS or MACS levels I-II). Motivation was assessed through heterogeneous approaches, including self-efficacy, mastery motivation, participation, adherence, and intrinsic motivation, with data collected from children, parents, therapists, or dyads. Conclusions: Although motivation is frequently cited as a critical component of effective rehabilitation in children with CP, its assessment remains inconsistent and methodologically fragmented. This mapping review, based on a limited and heterogeneous evidence base, highlights the need for standardized, validated, and developmentally appropriate tools to measure motivation-related constructs in pediatric CP rehabilitation.

Objective To synthesize the available evidence on the effects of constraint-induced movement therapy (CIMT) in children with hemiplegic cerebral palsy (CP), focusing on upper limb functional outcomes and neuroplasticity-related changes assessed through direct or indirect measures. Methods This scoping review was conducted in accordance with PRISMA-ScR guidelines and was prospectively registered on the Open Science Framework (DOI: 10.17605/OSF.IO/DU8RE). A search of four databases (PubMed, Scopus, Embase, and Web of Science) was performed to identify studies involving children (0–18 years) with CP who received CIMT as the primary intervention. Eligible studies assessed neuroplasticity through neuroimaging or neurophysiological techniques. Results Eleven studies involving 221 children met the inclusion criteria. CIMT protocols varied in duration, intensity, and setting (e.g., clinical, home-based, camp-based). Across studies, CIMT was associated with improvements in upper limb function and spontaneous use. Neuroplastic changes included increased activation in the contralateral sensorimotor cortex, normalization of somatosensory responses, and structural brain adaptations. Adjunctive therapies such as repetitive transcranial magnetic stimulation, transcutaneous auricular vagus nerve stimulation, or occupational therapy further enhanced outcomes. Conclusion CIMT is an effective intervention that promotes cortical reorganization and improves motor function in children with hemiplegic CP. Customizing rehabilitation based on neurophysiological profiles may optimize clinical outcomes.

Background/Objectives: Traumatic brain injury (TBI) is increasingly understood as a chronic condition, but the role of early post-injury lifestyle behaviors in later cardiometabolic risk remains unclear. We examined whether lifestyle behaviors reported 1 year after injury were associated with the accumulation of common cardiometabolic risk factors by 5 years in the Traumatic Brain Injury Model Systems (TBIMS) National Database. Methods: This retrospective cohort secondary analysis included adults with followed 1-year and 5-year interviews, complete 1-year data on four behaviors, and the complete ascertainment of hypertension, diabetes or high blood sugar, and high cholesterol at both waves. The exposure was a favorable lifestyle count based on not smoking, non-heavy alcohol use, non-obese body mass index, and sports or exercise at least 10 times per month. The primary endpoint was the incident accumulation of at least two new common cardiometabolic conditions between years 1 and 5. The analytic cohort was an observed-data subset defined by follow-up retention, complete behavior data, paired outcome ascertainment, and baseline at-risk status rather than a random sample of all TBIMS participants. Results: Among 10,057 linked participants with followed interviews at both waves, 9593 were adults, 3182 had complete four-behavior exposure data, 689 had complete cardiometabolic ascertainment, and 581 formed the primary at-risk observed-data cohort. The primary endpoint occurred in 39 participants (6.7%). Each additional favorable behavior was associated with lower odds of the primary endpoint in the adjusted model (odds ratio [OR], 0.63; 95% confidence interval [CI], 0.41-0.98; p = 0.040). The results were similar after adjustment for the 1-year Functional Independence Measure cognitive score and in Firth logistic regression. Because the final cohort was selected and the number of primary events was small, the estimates should be interpreted as exploratory and may not generalize to the broader TBI population. Conclusions: More favorable 1-year lifestyle profiles were associated with lower 5-year cardiometabolic risk factor accumulation after TBI. These findings support prevention-oriented follow-up but do not establish causality or validate a prognostic score.

BackgroundComputerized cognitive training (CCT) is increasingly used in pediatric rehabilitation; however, its application across developmental disorders remains heterogeneous in terms of targets, delivery models, and outcomes. This scoping review aimed to map the currently available CCT tools used in children with developmental disorders and to summarize their main characteristics, clinical targets, and evidence gaps.MethodsWe conducted a scoping review in accordance with the PRISMA-ScR framework and registered the protocol on the Open Science Framework (OSF; DOI 10.17605/OSF.IO/9XQ5H). We searched peer-reviewed studies investigating CCT in children with developmental disorders and extracted data on device characteristics, target domains, training modalities, study design, and main findings.ResultsTwenty-two studies describing 21 devices were included. Evidence was heterogeneous across diagnoses, intervention architectures, comparators, and outcome measures. The most consistent signal emerged in ADHD, where some programs reported improvements in working memory and selected executive-function outcomes. Evidence in learning-related and intellectual developmental conditions was more variable and device-specific, while the only ASD study identified did not show superiority over mock training.DiscussionCCT appears clinically attractive because of its adaptability, gamified delivery, and potential for home-based use; however, the current evidence base is uneven and does not support broad efficacy claims across developmental disorders. More disorder-specific studies with stronger comparators and ecologically valid outcomes are needed.Systematic Review Registrationhttps://osf.io/9xq5h, doi: 10.17605/OSF.IO/9XQ5H.

BACKGROUND:Pain is a critical yet frequently underestimated component in the care of patients with acquired brain injury (ABI) and disorders of consciousness (DoC). Because these individuals often lack the ability to communicate verbally or purposefully, clinicians face substantial challenges in recognizing and managing pain, despite its profound influence on autonomic stability, behavioural responsiveness, rehabilitation engagement and overall prognosis. CONTENT:This position paper synthesizes current knowledge on the multidimensional nature of pain and reviews the main behavioural, autonomic and neurophysiological tools available to assess nociception and pain-related processing in non-communicative patients. By integrating evidence from standard clinical scales with advanced physiological markers and neuroimaging findings, we highlight how preserved activity within the so-called pain matrix challenges traditional assumptions about pain absence in DoC populations. CLINICAL IMPLICATIONS:The paper argues for a shift toward multimodal, patient-centred approaches that combine behavioural observation with objective physiological indicators to improve diagnostic accuracy and ensure ethically responsible care. Practical guidance is provided on selecting appropriate assessment tools, interpreting behavioural and physiological signs of nociception, and implementing more effective pain management strategies. CONCLUSIONS:Accurate pain assessment is essential not only to promote recovery and facilitate rehabilitation but also to uphold the central ethical principle of safeguarding the dignity of patients with disorders of consciousness. SIGNIFICANCE STATEMENT:Understanding pain in Disorders of Consciousness (DoC) is a major clinical and ethical challenge, as residual nociceptive processing may be underestimated. This study advances a multidimensional framework integrating behavioural and neurophysiological evidence, moving beyond simple detection toward interpretation of pain meaning. It has direct implications for improving pain assessment, guiding personalized management and supporting more accurate and ethically grounded care in non-communicative patients.

Background and Objectives: Children with Developmental Coordination Disorder (DCD) show substantial motor and balance difficulties that affect daily activities. Although action observation (AO) and motor imagery (MI) are effective in other neurological conditions, their impact in DCD remains underinvestigated. This review explores the preliminary evidence of AO- and MI-based interventions for improving motor and functional outcomes in children with DCD. Methods: A systematic search of PubMed, Scopus, and Web of Science identified randomized controlled trials and controlled trials published in the last 15 years evaluating AO and MI interventions in children with DCD. Two independent reviewers conducted the screening of the studies, data extraction, and the risk-of-bias assessment using RoB2 and ROBINS-I. The review followed PRISMA reporting guidelines and was pre-registered on the PROSPERO database (CRD420251084196). Results: Of 320 records initially identified, seven studies, involving 199 children with DCD (aged 5–12 years), were included. Interventions varied from single-session to multi-session protocols (1–16 sessions) and included AO, MI, or a combination of both (AO + MI), with heterogeneous control conditions. Within these studies, the outcomes were primarily assessed using standardized motor coordination measures (MABC/MABC-2, DCDQ), planning tasks, and performance-based activities of daily living (ADLs) measures. Improvements were reported in motor imagery tasks, planning, and functional task performance. However, RCTs and CTs were identified to have a moderate and high risk of bias, respectively. Conclusions: The present review suggests that AO and MI, either alone or in combination, may enhance motor planning, coordination, and daily functional skills in children with DCD, supporting internal motor representations and predictive motor control, reflecting functional gain in motor skills and ADL performance. Interestingly, these mental training approaches can be applied in clinical and everyday settings and are suitable for supporting these processes, with VR-based combinations representing a promising, but exploratory, approach. Although critical heterogeneity and a moderate risk of bias remain, the findings need to be interpreted with caution and require further investigation.

Cerebral palsy (CP) is a permanent neurological disorder that frequently causes motor impairments, balance dysfunction, and reduced mobility in children. Robotic-assisted gait training (RAGT) has shown promise for improving gait and motor function, but little is known about how neuroplasticity adaptation influence outcomes. This study evaluated the individualized effects of a four-week RAGT program in two pediatric CP patients (GMFCS level 2 and level 5) using multimodal monitoring. Functional near-infrared spectroscopy (fNIRS) signal was recorded at the first RAGT session (T0), sixth session (T1), and twelfth session (T2), to assess cerebral plasticity as well as robotic torque outputs to assess leg (hip and knee) muscle force improvements. Clinical assessments (Modified Ashworth Scale, GMFM-88, WeeFIM®, PedsQL™ CP Module) complemented these measures. The GMFCS level 5 patient, despite severe initial limitations, demonstrated greater improvements, with enhanced prefrontal cortical activation, reduced robotic assistance torque, and decreased spasticity, alongside modest functional gains. In contrast, the GMFCS level 2 patient showed subtler fNIRS variation and torque reduction, reflecting a more stable neuromotor profile. These preliminary findings underscore the value of integrating neurovascular metrics to personalize pediatric neurorehabilitation. Real-time monitoring of brain responses, beyond motor performance alone, may help optimizing RAGT by ensuring interventions are functionally effective.

Robot-assisted arm training (RAAT) has demonstrated promising potential in improving rehabilitation outcomes for individuals with neurological conditions, particularly stroke. Despite 20 years of their use in clinical and research settings, there are still significant needs to be made concerning clinical indications. In the present perspective manuscript, we provide some hypotheses of the suitability of different RAAT according to the features of the available devices and clinical characteristics, showing their limitations and strengths. Several factors were considered in the optimization of RAAT intervention, including the technological characteristics of the devices (e.g., support and constriction), the residual upper limb motor function, and the clinical phase of stroke. Finally, we outline key areas for improvement to advance the field in the near future and provide neuroscientific bases for hypotheses of tailored RAAT training to improve the outcome of robotic rehabilitation.

Background and Objective: The metaverse refers to a digital realm accessible via internet connections using virtual reality and augmented reality glasses for promoting a new era of social rehabilitation. It represents the next-generation mobile computing platform expected to see widespread utilization in the future. In the context of rehabilitation, the metaverse is envisioned as a novel approach to enhance the treatment of human functioning exploiting the “synchronized brains” potential exacerbated by social interactions in virtual scenarios. Results: The metaverse emerges as an ideal domain for adapting the principles of the—International Classification of Functioning. Its intrinsic capacity to simulate interactions within virtual environments shared by multi-users, while providing a profound sense of presence and comprehensive perception, should facilitate learning and experiential understanding. Technical and conceptual aspects are currently under definition, including the interplay with artificial intelligence, definition of social metrics performance, and the utilization of blockchain technology for economic purposes. Conclusion: Building upon these foundations, this paper explores potential areas of metaverse applications in rehabilitation and examines how they may facilitate the pillars outlined in the World Health Organization’s Rehabilitation 2030 call for action.

Background/Objectives: Limited research has examined the relationship between preoperative health status and health-related quality of life (HRQoL) in patients with lumbar spinal stenosis (LSS) undergoing surgery. This study aims to assess the role of clinical, preoperative health and demographic factors on short-term HRQoL and functional outcomes following LSS surgery. Methods: A longitudinal study was conducted on 61 LSS patients (mean age 72.2 ± 8.8 years) undergoing surgery, assessing HRQoL and clinical outcomes before and 30 days post-surgery. Demographic and preoperative health status data were collected at baseline. HRQoL was measured using the Short Form Health Survey 36 (SF-36); clinical evaluations included assessments of disability, pain, and psychological status. Changes in HRQoL and clinical scores were analyzed with repeated measures ANOVA. HRQoL improvement was correlated with demographic and clinical variables, using Pearson’s correlation. Results: Spinal surgery for LSS led to significant improvements in HRQoL, with notable gains in both physical and mental health components (both p < 0.001), and in particular, in the body pain (+34%) and physical functioning, role physical, and social functioning (+20%) subscales of SF-36. Clinical scores also showed significant post-surgery improvements, strongly correlating with HRQoL. Correlations between ΔSF-36 subscale scores and preoperative factors revealed negative associations with BMI, smoking, comorbidities, and psychological distress. Conversely, physical activity was positively correlated with HRQoL improvements, especially in items showing the greatest score increases. Conclusions: Surgical treatment for LSS determines a significant improvement in HRQoL and functional outcome, which are however influenced by preoperative factors such as psychological distress, high BMI, smoking, and comorbidities. Conversely, regular physical activity is associated with better daily functioning, work performance, and social engagement. A comprehensive preoperative assessment may be a useful and appropriate tool to identify patients who are most likely to benefit and optimize quality of life after LSS surgery.

Background/Objectives: Neurological disorders often result in a broad spectrum of disabilities that impact mobility, communication, cognition, and sensory processing, leading to significant limitations in independence and quality of life. Assistive technologies (ATs) offer tools to compensate for these impairments, support daily living, and improve quality of life. The World Health Organization encourages the adoption and diffusion of effective assistive technology (AT). This narrative review aims to explore the integration, benefits, and challenges of assistive technologies in individuals with neurological disabilities, focusing on their role across mobility, communication, cognitive, and sensory domains. Methods: A narrative approach was adopted by reviewing relevant studies published between 2014 and 2024. Literature was sourced from PubMed and Scopus using specific keyword combinations related to assistive technology and neurological disorders. Results: Findings highlight the potential of ATs, ranging from traditional aids to intelligent systems like brain–computer interfaces and AI-driven devices, to enhance autonomy, communication, and quality of life. However, significant barriers remain, including usability issues, training requirements, accessibility disparities, limited user involvement in design, and a low diffusion of a health technology assessment approach. Conclusions: Future directions emphasize the need for multidimensional, user-centered solutions that integrate personalization through machine learning and artificial intelligence to ensure long-term adoption and efficacy. For instance, combining brain–computer interfaces (BCIs) with virtual reality (VR) using machine learning algorithms could help monitor cognitive load in real time. Similarly, ATs driven by artificial intelligence technology could be useful to dynamically respond to users’ physiological and behavioral data to optimize support in daily tasks.

Background: Emotionally salient music may enhance attention-focused rehabilitation, yet concurrent music plus virtual-reality programs in chronic stroke are largely untested. We assessed whether personalized emotional music stimulation (EMS) layered onto a standardized virtual reality rehabilitation system (VRRS) augments cognitive, affective, physiological, and functional outcomes. Methods: In a quasi-randomized outpatient trial, 20 adults ≥ 6 months post-ischemic stroke were allocated by order of recruitment to VRRS alone (control, n = 10) or VRRS+EMS (experimental, n = 10). Both groups performed 45 min of active VRRS cognitive training (3×/week, 8 weeks), while the EMS group received approximately 60 min sessions including setup and feedback phases. Primary outcomes were cognition and global function; secondary outcomes were intrinsic motivation, depression, anxiety, and heart rate. Non-parametric tests with effect sizes and Δ-scores were used. Results: The experimental group improved across all domains: cognition (median +4.5 points), motivation (median +54 points), depression (median −3.5 points), anxiety (median −4.0 points), heart rate (median −6.35 beats per minute), and disability (median one-grade improvement), each with large effects. The control group showed smaller gains in cognition and motivation and a modest heart-rate reduction, without significant changes in mood or disability. At post-treatment, the music group outperformed controls on cognition, motivation, and disability. Change-score analyses favored the music group for every endpoint. Larger heart-rate reductions correlated with greater improvements in depression (ρ = 0.73, p < 0.001) and anxiety (ρ = 0.58, p = 0.007). Conclusions: Adding personalized emotional music to virtual-reality attention training produced coherent, clinically relevant gains in cognition, mood, motivation, autonomic regulation, and independence compared with virtual reality alone.

Medicine has become increasingly receptive to the use of artificial intelligence (AI). This overview of systematic reviews (SRs) aims to categorise current evidence about it and identify the current methodological state of the art in the field proposing a classification of AI model (CLASMOD-AI) to improve future reporting. PubMed/MEDLINE, Scopus, Cochrane library, EMBASE and Epistemonikos databases were screened by four blinded reviewers and all SRs that investigated AI tools in clinical medicine were included. 1923 articles were found, and of these, 360 articles were examined via the full-text and 161 SRs met the inclusion criteria. The search strategy, methodological, medical and risk of bias information were extracted. The CLASMOD-AI was based on input, model, data training, and performance metric of AI tools. A considerable increase in the number of SRs was observed in the last five years. The most covered field was oncology accounting for 13.9% of the SRs, with diagnosis as the predominant objective in 44.4% of the cases). The risk of bias was assessed in 49.1% of included SRs, yet only 39.2% of these used tools with specific items to assess AI metrics. This overview highlights the need for improved reporting on AI metrics, particularly regarding the training of AI models and dataset quality, as both are essential for a comprehensive quality assessment and for mitigating the risk of bias using specialized evaluation tools.

IntroductionCerebral palsy (CP) is a group of permanent disorders of movement development that may cause activity limitations. In this context, robot-assisted therapy might play a key role in clinical management. This comprehensive systematic review aimed to investigate the efficacy of robotic systems in improving upper limb (UL) functions in children with CP.MethodsPubMed, EMBASE, Scopus, and PEDro were searched from inception to February 2024. The risk of bias was assessed with the Joanna Briggs Institute critical appraisal tools battery.ResultsOf 756 articles identified, 14 studies involving 193 children with CP with a judged to be of good methodological quality, but with a lack in the study design, were included in the final synthesis. In the included studies a wide range of devices was used, both exoskeletons and end-effectors, both wearable and non-wearable. The CP children who underwent robot-assisted therapy reported a significant overall increase in clinical assessment, specifically in UL movements and manual dexterity. The clinical improvement was often accompanied by a gain also in instrumental assessments (i.e., kinematic analysis, EMG).DiscussionThe present review suggested that robot-assisted therapy can improve UL motor functions in children with CP. Moreover, the availability of different devices with adjustable parameters can represent an important resource in proposing patient-centered-personalized rehabilitation protocols to enhance the efficacy of rehabilitation and integration into daily life. However, the limited sample size and lack of standardized and clearly reproducible protocols impose to recommend the use of robot-assisted therapy as an integration to usual rehabilitation and not as a replacement.Systematic review registrationhttps://osf.io/a78zb/.

IntroductionParkinson’s disease (PD), a common neurodegenerative disorder affecting motor functions, is associated with abnormal gait patterns characterized by altered kinematic, kinetic, and electrophysiological parameters. This observational study aims to instrumentally identify and quantify these gait dysfunctions in PD patients compared to normal values from healthy subjects.MethodsSixty-nine PD patients underwent clinical and instrumental evaluations to assess gait. Demographic and clinical data were collected before motor assessment. Clinical scales evaluated the level of impairment, gait, balance, risk of falls and ability to complete activities of daily living. Instrumental evaluations were conducted using optoelectronic, force plates and electromyographic (EMG) systems in a motion analysis laboratory. Statistical analysis involved a non-parametric test to compare pathological and normal data, clustering methods to identify groups based on clinical evaluations, and a combination of non-parametric analysis and linear models to assess dependencies on clinical scales.ResultsThe results showed that PD patients had significant gait kinematic differences compared to normal values, with increased temporal and shortened spatial parameters. In addition, PD patients were grouped into four clusters based on clinical scales. While some gait features were influenced by clinical scales reflecting impairment, gait and balance, and independence, others were more affected by the perceived fear of falling (FoF).DiscussionIn conclusion, the study identified specific biomechanical gait dysfunctions in kinematic, kinetic, and electrophysiological parameters in PD patients, undetectable by standard clinical scales. Additionally, higher FoF was associated with dysfunctional biomechanical patterns, independent of impairment severity, gait and balance dysfunction, or overall independence.

BackgroundChildren with cerebral palsy (CP) may present motor and gait impairment.ObjectiveThis systematic review aims to assess the potential of robot-assisted gait training (RAGT) with Lokomat® exoskeleton to improve gait in children with CP.MethodsThe search was conducted and repoted according to PRISMA guidelines on PubMed, Scopus, Cochrane Library and PEDro databases. All randomised controlled trials (RCT) including children with CP who underwent RAGT with Lokomat® were considered eligible. Risk of bias was assessed with the Rob2 tool by two blinded reviewers. The review was previously registered on the PROSPERO database (CRD42023488699).Results948 articles were found, and 9 studies involving 403 children with CP met the inclusion criteria. We found a heterogeneity in the RAGT protocol and a higher risk of bias for two included studies. Seven out nine studies reported a statistically significant improvement (p < 0.05) on gait, balance, or global functions with respect to control groups. Specifically, walking speed and stride length were improved after RAGT.ConclusionsChildren with CP can benefit from the add-on therapy with RAGT through Lokomat® to improve walking and balance function. There is a need for RCTs with better patient stratification and with less heterogeneity in outcomes to improve the quality of the pooled evidence.

Background: The time lapse between the acute event and the beginning of rehabilitation seems to play a significant role in determining the effectiveness of rehabilitation together with the severity of neurological deficits and impairments of motor and cognitive functions. The present study aims to further explore the prognostic role of cognitive and motor functions, concerning the different times of the beginning of neurorehabilitation. Methods: A secondary examination was conducted by applying a cluster analysis on the data of 386 stroke patients in the subacute phase who were enrolled in the Cognitive and Recovery of Motor Functions (CogniReMo) study. Results: The Barthel Index at the admission predicts clinical outcome: if BI was 0, it was on average 28.7 ± 24.1 at discharge. For patients with Barthel Index <15 at discharge, the discriminant was unaltered executive functions having an average output of 61.3 instead of 45.5. In the range of BI at admission between 16 and 45, the discriminant variable was to have an NIHSS ≤ 5 to obtain a high outcome (BI = 75.4 instead of BI = 61.9). Subjects with a BI at admission >45 were the best responders to rehabilitation, with a mean BI at discharge of 85 if they have alteration in spatial attention, and 95.3 if they have no deficits in spatial attention. Also, for inpatients hospitalized in a period ranging from the 20th to the 37th day after stroke, spatial attention was a discriminant variable to have a poor outcome (BI = 34.3) vs. a good one (BI = 76.7). Conclusions: The algorithm identified a hierarchical decision tree that might assume a significant role for clinicians in defining an appropriate rehabilitation pathway, depending on the time of rehabilitation beginning and the severity of motor and cognitive deficits.

Background and aim:Lumbar spinal stenosis (LSS) is a leading cause of low back pain and lower limbs pain often associated with functional impairment which entails the loss or the impairment of independence in older adults. Conservative treatment is effective in a small percentage of patients, while a significant percentage undergo surgery, even if often without a complete resolution of clinical symptoms and motor deficits. The aim of the study is to identify clinical and demographic prognostic factors characterising the patients who would benefit most from surgical treatment in relation to the functional independence recovery using an innovative approach based on an artificial neural network. Methods:Adult patients with LSS and indication of neurosurgical treatment were enrolled in the study. Clinical evaluation was performed in the preoperative-phase (into the 48 h before surgery) and after two months. Clinical battery investigated the motor, functional, cognitive, behavioural, and pain status. Demographics and clinical characteristics were analysed via Artificial Neural Network (ANN) using 24 input variables, 2 hidden layers and a single final output layer to predict the outcome. ANN results were compared with those of a multiple linear regression. Results:108 patients were included in the study and 90 of them [66.5 ± 12.8 years; 27.8 % F] were submitted to surgery treatment and completed longitudinal evaluation. Statistically significant improvement was recorded in all clinical scales comparing pre- and post-surgery. The ANN results showed a prediction ability up to 81 %. Disability, functional limitations, and pain concerning clinical assessment and stature, onset and age about demographic characteristics are the main variables impacting on surgical outcome. Conclusions:ANN can support clinical decision making, using clinical and demographic characteristics of patients with LSS identifying the characteristics of those who might benefit more from the surgical treatment in terms of global functional recovery.