Background: Assessing fall risk, especially in individuals with neurological disorders, is essential to prevent hospitalization, hypomobility, and reduced functional independence. Wearable sensors are increasingly used in neurorehabilitation, as they enable unsupervised fall risk assessment by providing continuous monitoring during daily functional tasks, thereby offering a reflection of the individual’s real-world fall risk. Objective: We systematically reviewed the literature on reliable biomechanical gait parameters detected with wearable sensors to assess fall risk in neurological disorders, focusing on patients with Parkinson disease, multiple sclerosis, stroke, or Alzheimer disease. In addition, we examined the latest advancements in wearable sensor technology, including best practices for device placement as well as data processing and analysis. Methods: We conducted a comprehensive systematic search for relevant peer-reviewed articles published up to April 18, 2025, using PubMed, Web of Science, Embase, and IEEE Xplore, which are the most used databases in the fields of health and bioengineering. Results: The 19 included studies involved 2630 patients with neurological disorders, including 226 (8.59%) with multiple sclerosis (n=7, 37% studies), 2305 (87.64%) with Parkinson disease (n=8, 53% studies), 51 (1.94%) with stroke (n=3, 16% studies), and 48 (1.83%) with Alzheimer disease or cognitive impairment (n=1, 5% study). Conclusions: This review highlights the role of wearable technologies in assessing fall risk in patients with neurological disorders. Although the included studies showed variation in methods and a focus on technology over clinical context, the lack of standardization reflects ongoing advancements, which may be seen as a strength. Trial Registration: PROSPERO CRD42023463944; https://www.crd.york.ac.uk/PROSPERO/view/CRD42023463944

Language disorders are characterized by impairments in verbal expression/understanding, including difficulties with one or more language components. The Virtual Reality Rehabilitation System (VRRS) is a bioelectromedical device equipped with exercise sections aimed at improving cognitive and language deficits. It also increases patient motivation and engagement. The aim of our study was to test the feasibility and efficacy of VRRS intervention to improve speech therapy treatment for children with speech disorders. Thirty-two patients were enrolled in this study and randomly assigned to the experimental (EG) or control group (CG). The CG underwent conventional speech therapy, while EG underwent VRRS-implemented speech therapy. Both groups were evaluated before (T0) and after (T1) the intervention using the Language Assessment Test. The results showed improvements in both groups. However, the EG group showed greater improvement in various areas, including comprehension of total words, repetition, naming of body parts, naming of everyday objects, total naming, morphosyntactic accuracy, sentence construction, average length of utterance, and spontaneous word production. This study demonstrated that VRRS can be a valuable tool for implementing effective speech rehabilitation. Further studies are needed, as the use of VRRS is still in its early stages, requiring larger samples sizes and long-term follow-up.

The human pulvinar is considered a prototypical associative thalamic nucleus as it represents a key node in several cortico‐subcortical networks. Through this extensive connectivity to widespread brain areas, it has been suggested that the pulvinar may play a central role in modulating cortical oscillatory dynamics of complex cognitive and executive functions. Additionally, derangements of pulvinar activity are involved in different neuropsychiatric conditions including Lewy‐body disease, Alzheimer's disease, and schizophrenia. Anatomical investigations in nonhuman primates have demonstrated a topographical organization of cortico‐pulvinar connectivity along its dorsoventral and rostrocaudal axes; this specific organization shows only partial overlap with the traditional subdivision into subnuclei (anterior, lateral, medial, and inferior) and is thought to coordinate information processing within specific brain networks. However, despite its relevance in mediating higher‐order cognitive functions, such a structural and functional organization of the pulvinar in the human brain remains poorly understood. Track‐weighted dynamic functional connectivity (tw‐dFC) is a recently developed technique that combines structural and dynamic functional connectivity, allowing the identification of white matter pathways underlying the fluctuations observed in functional connectivity between brain regions over time. Herein, we applied a data‐driven parcellation approach to reveal topographically organized connectivity clusters within the human pulvinar complex, in two large cohorts of healthy human subjects. Unsupervised clustering of tw‐dFC time series within the pulvinar complex revealed dorsomedial, dorsolateral, ventral anterior, and ventral posterior connectivity clusters. Each of these clusters shows functional coupling to specific, widespread cortico‐subcortical white matter brain networks. Altogether, our findings represent a relevant step towards a better understanding of pulvinar anatomy and function, and a detailed characterization of his role in healthy and pathological conditions.

Introduction: Frontotemporal dementia (FTD) is a neurodegenerative disorder characterized by progressive degeneration of the frontal and temporal lobes, leading to significant changes in personality, behavior, and language abilities. Early and accurate differential diagnosis between FTD, its subtypes, and other dementias, such as Alzheimer's disease (AD), is crucial for appropriate treatment planning and patient care. Machine learning (ML) techniques have shown promise in enhancing diagnostic accuracy by identifying complex patterns in clinical and neuroimaging data that are not easily discernible through conventional analysis.Methods: This systematic review, following PRISMA guidelines and registered in PROSPERO, aimed to assess the strengths and limitations of current ML models used in differentiating FTD from other neurological disorders. A comprehensive literature search from 2013 to 2024 identified 25 eligible studies involving 6,544 patients with dementia, including 2,984 with FTD, 3,437 with AD, 103 mild cognitive impairment (MCI) and 20 Parkinson's disease dementia or probable dementia with Lewy bodies (PDD/DLBPD).Results: The review found that Support Vector Machines (SVMs) were the most frequently used ML technique, often applied to neuroimaging and electrophysiological data. Deep learning methods, particularly convolutional neural networks (CNNs), have also been increasingly adopted, demonstrating high accuracy in distinguishing FTD from other dementias. The integration of multimodal data, including neuroimaging, EEG signals, and neuropsychological assessments, has been suggested to enhance diagnostic accuracy.Discussion: ML techniques showed strong potential for improving FTD diagnosis, but challenges like small sample sizes, class imbalance, and lack of standardization limit generalizability. Future research should prioritize the development of standardized protocols, larger datasets, and explainable AI techniques to facilitate the integration of ML-based tools into real-world clinical practice.Systematic review registration: https://www.crd.york.ac.uk/PROSPERO/view/CRD42024520902.

Tremor is one of the most common symptoms of Parkinson’s disease (PD), assessed using clinician-assigned clinical scales, which can be subjective and prone to variability. This study evaluates the potential of unsupervised learning for the classification and assessment of tremor severity from wearable sensor data. We analyzed 25 resting tremor signals from 24 participants (13 PD patients and 11 controls), focusing on motion intensities derived from accelerometer recordings. The k-means clustering algorithm was employed, achieving a classification accuracy of 76% for tremor versus non-tremor states. However, performance decreased for multiclass tremor severity classification (57.1%) and binary classification of severe versus mild tremor (71.4%), highlighting challenges in detecting subtle intensity variations. The findings underscore the utility of unsupervised learning in enabling scalable, objective tremor analysis. Integration of such models into wearable systems could improve continuous monitoring, enhance rehabilitation strategies, and support standardized clinical assessments. Future work should explore advanced algorithms, enriched feature sets, and larger datasets to improve robustness and generalizability.

Introduction: A clinical audit is a tool that allows the evaluation of and improvement in the quality of stroke care processes. Fast, high-quality care and preventive interventions can reduce the negative impact of stroke. Objective: This review was conducted on studies investigating the effectiveness of clinical audits to improve the quality of stroke rehabilitation and stroke prevention. Method: We reviewed clinical trials involving stroke patients. Our search was performed on PubMed databases, Web of Science, and Cochrane library databases. Of the 2543 initial studies, 10 studies met the inclusion criteria. Results: Studies showed that an audit brought an improvement in rehabilitation processes when it included a team of experts, an active training phase with facilitators, and short-term feedback. In contrast, studies looking at an audit in stroke prevention showed contradictory results. Conclusions: A clinical audit highlights any deviations from clinical best practices in order to identify the causes of inefficient procedures so that changes can be implemented to improve the care system. In the rehabilitation phase, the audit is effective for improving the quality of care processes.