Journal of NeuroEngineering and Rehabilitation最新文献

{"title":"Postural sway serves as a predictive biomarker in balance and gait assessments for diabetic peripheral neuropathy screening: a community-based study.","authors":"Yun-Ru Lai, Wen-Chan Chiu, Chi-Ping Ting, Yi-Fang Chiang, Ting-Yin Lin, Hui-Ching Chiang, Chih-Cheng Huang, Cheng-Hsien Lu","doi":"10.1186/s12984-025-01644-6","DOIUrl":"10.1186/s12984-025-01644-6","url":null,"abstract":"<p><strong>Background: </strong>Traditional screening methods for diabetic peripheral neuropathy (DPN) can be time-consuming in community settings. Balance and gait impairments are common in individuals with DPN, but these functional impairments are often not detectable with standard neurological examinations. This study aimed to examine whether quantitative balance and gait assessment could serve as a viable alternative screening tool for DPN.</p><p><strong>Methods: </strong>All participants were recruited from a community-based daycare center and underwent peripheral nerve function assessments, including the Toronto Clinical Neuropathy Score (TCNS), sural nerve conduction studies (amplitude and velocity) for large fiber function, and Sudoscan testing for small fiber function. Subsequently, participants underwent balance and gait assessments, including static postural sway measurements and gait analysis of spatiotemporal parameters and joint range of motion (ROM) assessment during walking.</p><p><strong>Results: </strong>Of the 146 participants, 35 had diabetes, including 22 with DPN, while 111 were healthy controls. Participants with DPN demonstrate increased postural sway velocity and total path length, along with reduced gait speed, shorter stride length, and decreased range of motion in hip flexion and extension. The logistic regression analysis identified diabetes duration and postural sway velocity as the only significant predictors of DPN presence. Postural sway velocity demonstrated strong correlations with elevated TCNS, reduced sural sensory nerve action potential and sensory nerve conduction velocity, and lower Sudoscan values in hands and feet. Additionally, receiver operating characteristic analysis yielded a sensitivity of 68.2%, specificity of 85.5%, and an area under the curve of 0.76, with a cut-off value of 0.98 cm/s.</p><p><strong>Conclusions: </strong>Balance and gait impairments are prevalent among participants with DPN. This study supports the integration of balance and gait assessments into community-based screening protocols to facilitate early identification and intervention. Postural sway velocity emerged as a practical early biomarker for the screening of DPN.</p>","PeriodicalId":16384,"journal":{"name":"Journal of NeuroEngineering and Rehabilitation","volume":"22 1","pages":"123"},"PeriodicalIF":5.2,"publicationDate":"2025-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12128393/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144199365","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Delayed muscle fatigue during electrical stimulation of the proximal nerve using asymmetric random high-frequency carrier pulse cluster.","authors":"Rui Yuan, Yang Zheng, Henry Shin, Guanghua Xu, Shengnuo Fan, Zhanhong Du","doi":"10.1186/s12984-025-01658-0","DOIUrl":"10.1186/s12984-025-01658-0","url":null,"abstract":"<p><strong>Background: </strong>Transcutaneous peripheral nerve electrical stimulation using high-frequency pulse clusters has been shown to relieve muscle fatigue, though its efficacy remains limited. Furthermore, this approach tends to exacerbate pain during stimulation, which constrains its clinical applications. This paper proposed a novel stimulation waveform to reduce muscle fatigue and the discomfort associated with high-frequency electrical stimulation, and compares it with previously reported high-frequency pulsed cluster stimulation.</p><p><strong>Methods: </strong>We evaluated our waveform experimentally and through model simulations. During the experiment, two distinct high-frequency narrow pulse clusters were applied to the proximal segment of the median/ulnar nerve bundles: asymmetric random (aSymR) and previously reported symmetric (Sym) stimulation, both with a carrier frequency of 10 kHz. The two stimulation modes aimed to elicit the same contraction level and were maintained for 5 min to induce muscle fatigue. Finger force, high-density electromyographic (EMG) signals of the flexor muscles and the pain score were recorded. In addition, we developed a finite element model of the upper arm and a motor fiber model to simulate motor axon activation of the peripheral nerve induced by the two electrical stimulation modes.</p><p><strong>Results: </strong>Compared with the Sym stimulation, the aSymR stimulation resulted in less pain and a significant reduction of muscle fatigue rate, which was characterized by slower force decay rate, less absolute force decay, greater plateau force, and ultimately greater force output. In addition, the simulation results showed that the delay for different fibers to reach the threshold was increased by the aSymR mode. Consistent with this, the experiment study showed that the EMG amplitude under the aSymR stimulation condition was smaller before fatigue onset, indicating the less synchronized activation of different muscle fibers.</p><p><strong>Conclusions: </strong>Compared with the Sym stimulation, the aSymR stimulation can significantly relieve muscle fatigue possibly by reducing the synchronous activation across different fibers. This proposed aSymR stimulation mode not only reduces fatigue but also relieves pain, potentially contributing to the wide application of electrical stimulation in motor function rehabilitation for people with stroke.</p><p><strong>Trial registration: </strong>Ethics committee of the Medical College of Xi'an Jiaotong University, 2021 - 1550. Registered 4 November 2021.</p>","PeriodicalId":16384,"journal":{"name":"Journal of NeuroEngineering and Rehabilitation","volume":"22 1","pages":"125"},"PeriodicalIF":5.2,"publicationDate":"2025-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12128545/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144199363","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Patient-centered insights into virtual reality rehabilitation for stroke: a systematic review and qualitative meta-synthesis.","authors":"Kun Ding, Yan Ma, Lingling Zhang, Yufang Gu, Huixuan Pan, Zhi-E Gu, Hengzhu Zhang","doi":"10.1186/s12984-025-01641-9","DOIUrl":"10.1186/s12984-025-01641-9","url":null,"abstract":"<p><strong>Background: </strong>Virtual reality rehabilitation (VRR) is an emerging technology that offers new possibilities for stroke recovery. Understanding stroke survivors' experiences and expectations is essential for optimizing its application.</p><p><strong>Objective: </strong>This systematic review synthesizes qualitative evidence on stroke survivors' experiences with and participation in VRR to identify benefits, challenges, and areas for improvement.</p><p><strong>Methods: </strong>This systematic review follows the meta-aggregation method guided by ENTREQ and PRISMA and uses the Critical Appraisal Skills Programme (CASP) to assess the quality of included studies. We searched eight English and Chinese databases for qualitative or mixed-method studies on stroke survivors' experiences with VRR, published by May 31, 2024. Selected studies were independently reviewed, and data were synthesized into core themes.</p><p><strong>Results: </strong>Fourteen studies were included, involving a total of 133 participants aged 13 to 85 years. The analysis identified four key themes: (1) perceived self-benefits, including physical and psychological improvements; (2) facilitators, such as user engagement and supportive environments; (3) barriers, including technical and personal limitations; and (4) expectations.The quality of the included studies was assessed using the CASP tool, with scores ranging from 26 to 30, indicating moderate to high quality across the studies.</p><p><strong>Conclusion: </strong>VRR has the potential to enhance stroke rehabilitation outcomes, but its success depends on addressing individual and systemic challenges. Personalized interventions and multidisciplinary efforts are needed to develop user-friendly, adaptable VRR systems that fully leverage the advantages of this technology.</p>","PeriodicalId":16384,"journal":{"name":"Journal of NeuroEngineering and Rehabilitation","volume":"22 1","pages":"124"},"PeriodicalIF":5.2,"publicationDate":"2025-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12128322/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144199364","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Using machine learning to identify Parkinson's disease severity subtypes with multimodal data.","authors":"Hwayoung Park, Changhong Youm, Sang-Myung Cheon, Bohyun Kim, Hyejin Choi, Juseon Hwang, Minsoo Kim","doi":"10.1186/s12984-025-01648-2","DOIUrl":"https://doi.org/10.1186/s12984-025-01648-2","url":null,"abstract":"<p><strong>Background: </strong>Classifying and predicting Parkinson's disease (PD) is challenging because of its diverse subtypes based on severity levels. Currently, identifying objective biomarkers associated with disease severity that can distinguish PD subtypes in clinical trials is necessary. This study aims to address the clinical applicability and heterogeneity of PD using PD severity subtypes classification and digital biomarker development by combining objective multimodal data with machine learning (ML) approaches.</p><p><strong>Methods: </strong>We analyzed datasets that combine clinical characteristics, physical function and lifestyle data, gait parameters in motion analysis systems, and wearable sensors collected from persons with PD (n = 102) to perform clustering for subtype classification.</p><p><strong>Results: </strong>We identified three PD severity subtypes, each exhibiting different patterns of clinical severity, with the severity increasing as it progressed from clusters 1 to 3. We found significant mutual information between all/single modalities and the unified PD rating scale scores, identifying potential modalities with high feature importance using ML. Among all modalities, the principal components of gait parameters derived from wearable sensors were identified as the most associated indicators of PD severity. A model utilizing the first principal component of the left and right ankle achieved perfect classification with an area under the curve of 1.0, accurately distinguishing clinically severe subtypes from mild subtypes of PD. These findings suggest that gait features in both ankles can reflect asymmetry factors associated with PD severity subtypes, which contributes to high classification performance.</p><p><strong>Conclusions: </strong>Digital biomarkers obtained from wearable sensors attached bilaterally to body segments demonstrate potential for classifying PD severity subtypes and tracking disease progression. Our findings emphasized the clinical value of sensor-based gait analysis in PD management, which suggested its integration into personalized monitoring systems and therapeutic interventions for persons with PD.</p>","PeriodicalId":16384,"journal":{"name":"Journal of NeuroEngineering and Rehabilitation","volume":"22 1","pages":"126"},"PeriodicalIF":5.2,"publicationDate":"2025-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144208747","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effects of oral care combined with neuromuscular electrical stimulation on clinical outcomes in the acute phase of acute ischemic stroke: a pilot randomized controlled trial.","authors":"Yi-Ting Huang, Chia-Chun Tang, Chen-Chih Chung, Chi-Hsiang Chung","doi":"10.1186/s12984-025-01652-6","DOIUrl":"10.1186/s12984-025-01652-6","url":null,"abstract":"<p><strong>Background: </strong>Stroke-associated dysphagia significantly increases the risk of pneumonia in persons with acute ischemic stroke (AIS), yet effective early interventions remain limited. This pilot randomized controlled trial examined the feasibility and clinical effects of a nurse-delivered combined intervention involving neuromuscular electrical stimulation (NMES) and comprehensive oral care-including toothbrushing using the Bass method, tongue cleaning, and moisturizing twice daily-during the acute stroke phase.</p><p><strong>Methods: </strong>This randomized, parallel group pilot trial assigned persons with AIS into three groups: (i) oral care only, (ii) oral care + NMES, and (iii) standard care (control). Interventions began within 48 h of stroke onset and continued twice daily for five days, starting within 48 h of stroke onset. Outcome measures, including the Revised Oral Assessment Guide (ROAG) and Gugging Swallowing Screening (GUSS), were assessed at baseline, day 4, and day 8 post-stroke. Statistical analysis employed one-way analysis of variance (ANOVA), chi-square tests, and generalized estimating equations (GEE) to analyze group differences and longitudinal trends.</p><p><strong>Results: </strong>Among 35 participants (mean age 68.3 ± 12.5 years; 51.4% men), both intervention groups demonstrated significant improvements in swallowing and oral health outcomes over time, compared to standard care (p < 0.05). Although this pilot study was not powered to determine superiority between the two intervention groups, the oral care + NMES group demonstrated the greatest improvements in GUSS and ROAG scores.</p><p><strong>Conclusion: </strong>Findings from this pilot trial support the feasibility of nursing staff implementing combined oral care and NMES within 48 h of AIS onset. The results highlight the potential for meaningful clinical benefits, particularly in settings with limited access to specialized rehabilitation. Larger, blinded, multi-center trials are warranted to further evaluate the efficacy and broader applicability of this early intervention strategy.</p><p><strong>Registration: </strong>The study protocol was registered in the Protocol Registration and Results System (PRS) under ID N202108021 as a supplementary registration due to initial unfamiliarity with PRS registration requirements, with the registration date recorded as 11/14/2024.</p>","PeriodicalId":16384,"journal":{"name":"Journal of NeuroEngineering and Rehabilitation","volume":"22 1","pages":"122"},"PeriodicalIF":5.2,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12123995/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144187173","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparative efficacy of robotic exoskeleton and conventional gait training in patients with spinal cord injury: a meta-analysis of randomized controlled trials.","authors":"Shengye Liu, Fangyuan Chen, Jianqiao Yin, Guanqi Wang, Liyu Yang","doi":"10.1186/s12984-025-01649-1","DOIUrl":"10.1186/s12984-025-01649-1","url":null,"abstract":"<p><strong>Objective: </strong>The purpose of this meta-analysis was to investigate the effects of Robotic exoskeleton gait training (REGT) on lower limb mobility, walking balance, functional scores and respiratory function in patients with spinal cord injury (SCI).</p><p><strong>Data sources: </strong>The PubMed, Embase, Cochrane Library databases were systematically searched from inception until December 24, 2024.</p><p><strong>Study selection: </strong>Eligible randomized controlled trials contained information on the population (SCI), intervention (REGT), and outcomes (walking speed and distance, walking balance, functional scores for SCI rehabilitation, respiratory function). Participants in the REGT intervention group were compared with those in conventional physical gait training (CPT) groups. Two independent researchers conducted the research,screened the articles, and assessed their eligibility.</p><p><strong>Data extraction: </strong>Two independent researchers extracted key information from each eligible study. The authors' names, year of publication, setting, total sample size, REGT, CPT training schedule, baseline/mean difference (MD), and 95% confidence interval (CI) were extracted using a standardized form, and the methodological quality was assessed using the GRADE (Grading of Recommendations, Assessment, Development, and Evaluation) system.</p><p><strong>Data synthesis: </strong>Of 595 studies identified, 15 randomized controlled trials (n = 579) were included for meta-analysis. Compared with conventional physical gait training (CPT), REGT showed no significant efficacy in walking speed (10-Meter Walk Test, WMD (95%CI) = - 0.03 (- 0.06, 0.00) m/s, P = 0.08) and walking distance, (6-Minute Walk Test, WMD (95% CI) = -1.83 (- 14.48, 10.83) meters, P = 0.78). REGT showed statistically significant efficacy in walking stability (Timed Up and Go, WMD (95%CI) = 6.62 (0.35, 12.88) s, P = 0.04) and functional scores such as Walking Index for Spinal Cord Injury Version II (WMD (95%CI) = 2.17 (1.05, 3.29), P = 0.0001) and Lower Extremity Motor Score (WMD (95%CI) = 1.33 (0.58, 2.07), P = 0.0005). Additional Significant efficacy was also found in terms of respiratory function (forced expiratory volume in one second, WMD (95%CI) = 0.60 (0.05, 1.16) L, P = 0.03).</p><p><strong>Conclusions: </strong>This meta-analysis discovered the evidence that robotic exoskeleton gait training can improve the walking balance, strength of lower limbs, functional scores and respiratory function in the patients with spinal cord injury (SCI) compared to conventional gait training (CPT). No obvious evidence showed that REGT has more advantages than CPT in improving walking speed and distance. REGT combined with CPT are more recommended in the discovery of walking speed and distance of patients above 6 months after SCI.</p>","PeriodicalId":16384,"journal":{"name":"Journal of NeuroEngineering and Rehabilitation","volume":"22 1","pages":"121"},"PeriodicalIF":5.2,"publicationDate":"2025-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12121209/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144181603","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effect of electroencephalography-based motor imagery neurofeedback on mu suppression during motor attempt in patients with stroke.","authors":"Seungwoo Cha, Kyoung Tae Kim, Won Kee Chang, Nam-Jong Paik, Ji Soo Choi, Hyunmi Lim, Won-Seok Kim, Jeonghun Ku","doi":"10.1186/s12984-025-01653-5","DOIUrl":"10.1186/s12984-025-01653-5","url":null,"abstract":"<p><strong>Objective: </strong>The primary aim of this study was to explore the neurophysiological effects of motor imagery neurofeedback using electroencephalography (EEG), specifically focusing on mu suppression during serial motor attempts, and to assess its potential benefits in patients with subacute stroke.</p><p><strong>Methods: </strong>A total of 15 patients with hemiplegia following subacute ischemic stroke were prospectively enrolled in this randomized cross-over study. This study comprised two experiments: neurofeedback and sham. Each experiment included four blocks: three blocks of resting, grasp, resting, and an interventional task, followed by one block of resting and grasp. During the resting sessions, participants fixated on a white cross on a black background for 2 min without moving their upper extremities. In the grasp sessions, participants were instructed to grasp and release their paretic hand at a frequency of about 1 Hz for 3 min while maintaining fixation on the white cross. During the interventional task, the neurofeedback presented a punching image using the affected upper limb, corresponding to the mu suppression induced by imagined movement for 3 min. In contrast, the sham presented an image based on mu suppression data from randomly selected participants. EEG data were recorded throughout the experiment, and data from electrodes C3/C4 and P3/P4 were analyzed to compare the degree of mu suppression between the neurofeedback and sham experiments.</p><p><strong>Results: </strong>Significant mu suppression was observed in the bilateral motor and parietal cortices during the neurofeedback experiment compared with the sham across serial sessions (p < 0.001). Following neurofeedback, real grasping sessions showed progressive strengthening of mu suppression in the ipsilesional motor cortex and bilateral parietal cortices compared to sessions following sham (p < 0.05). This effect was not observed in the contralesional motor cortex.</p><p><strong>Conclusions: </strong>Motor imagery neurofeedback significantly enhances mu suppression in the ipsilesional motor and bilateral parietal cortices during motor attempts in patients with subacute stroke. These findings suggest that motor imagery neurofeedback could serve as a promising adjunctive therapy to enhance motor-related cortical activity and support motor rehabilitation in patients with stroke.</p>","PeriodicalId":16384,"journal":{"name":"Journal of NeuroEngineering and Rehabilitation","volume":"22 1","pages":"119"},"PeriodicalIF":5.2,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12117778/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144174009","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cortical adaptations in Tai Chi practitioners during sensory conflict: an EEG-based effective connectivity analysis of postural control.","authors":"Guozheng Wang, Xiaoxia Liu, Yiming Cai, Jian Wang, Ying Gao, Jun Liu","doi":"10.1186/s12984-025-01650-8","DOIUrl":"10.1186/s12984-025-01650-8","url":null,"abstract":"<p><strong>Background: </strong>Tai Chi (TC) is recognized for enhancing balance and postural control. However, studies on its effects on the central nervous system are limited and often involve static experiments despite the dynamic nature of TC. This study addressed that gap by examining cortical network activity during dynamic, multisensory conflict balance tasks. We aimed to determine whether long-term TC practice leads to neuroplastic changes in brain connectivity that improve sensory integration for postural control.</p><p><strong>Methods: </strong>Fifty-two young adult participants (long-term TC practitioners = 22; non-practitioners = 30) performed balance tasks under sensory congruent and conflict conditions using a virtual reality headset with a rotating supporting surface. EEG was performed, and generalized partial directed coherence was used to assess directed functional connectivity in the mu rhythm (8-13 Hz) between predefined regions of interest (ROIs) in the cortex implicated in sensory and motor integration. Graph-theoretic measures (in-strength and out-strength) indexed the total incoming and outgoing connection strengths for each region. Statistical analysis used mixed-design ANOVAs (Group × Condition) to compare balance and connectivity measures.</p><p><strong>Results: </strong>TC practitioners demonstrated significantly better postural stability under both sensory conditions, with a reduced sway area. EEG analysis revealed that increased sensory conflict decreased the global efficiency of the visual integration network but increased that of the somatosensory integration network. Furthermore, TC practitioners demonstrated enhanced out-strength of the somatosensory cortex and lower out-strength of the right posterior parietal cortex (PPC) compared to non-practitioners.</p><p><strong>Conclusions: </strong>Long-term TC practice is associated with quantifiable neuroplastic changes in mu-band cortical effective connectivity, specifically enhanced information outflow from somatosensory reduce parietal influence regions. Our findings demonstrate central mechanisms by which TC practice may improve balance, providing neuroengineering evidence for TC as a neuroplasticity-driven balance intervention.</p>","PeriodicalId":16384,"journal":{"name":"Journal of NeuroEngineering and Rehabilitation","volume":"22 1","pages":"120"},"PeriodicalIF":5.2,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12121214/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144173982","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reveal the mechanism of brain function with fluorescence microscopy at single-cell resolution: from neural decoding to encoding.","authors":"Kangchen Li, Huanwei Liang, Jialing Qiu, Xulan Zhang, Bobo Cai, Depeng Wang, Diming Zhang, Bingzhi Lin, Haijun Han, Geng Yang, Zhijing Zhu","doi":"10.1186/s12984-025-01655-3","DOIUrl":"10.1186/s12984-025-01655-3","url":null,"abstract":"<p><p>As a key pathway for understanding behavior, cognition, and emotion, neural decoding and encoding provide effective tools to bridge the gap between neural mechanisms and imaging recordings, especially at single-cell resolution. While neural decoding aims to establish an interpretable theory of how complex biological behaviors are represented in neural activities, neural encoding focuses on manipulating behaviors through the stimulation of specific neurons. We thoroughly analyze the application of fluorescence imaging techniques, particularly two-photon fluorescence imaging, in decoding neural activities, showcasing the theoretical analysis and technological advancements from imaging recording to behavioral manipulation. For decoding models, we compared linear and nonlinear methods, including independent component analysis, random forests, and support vector machines, highlighting their capabilities to reveal the intricate mapping between neural activity and behavior. By employing synthetic stimuli via optogenetics, fundamental principles of neural encoding are further explored. We elucidate various encoding types based on different stimulus paradigms-quantity encoding, spatial encoding, temporal encoding, and frequency encoding-enhancing our understanding of how the brain represents and processes information. We believe that fluorescence imaging-based neural decoding and encoding techniques have deepened our understanding of the brain, and hold great potential in paving the way for future neuroscience research and clinical applications.</p>","PeriodicalId":16384,"journal":{"name":"Journal of NeuroEngineering and Rehabilitation","volume":"22 1","pages":"118"},"PeriodicalIF":5.2,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12107988/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144159665","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing patient rehabilitation outcomes: artificial intelligence-driven predictive modeling for home discharge in neurological and orthopedic conditions.","authors":"Leonardo Buscarini, Paola Romano, Elena Sofia Cocco, Carlo Damiani, Sanaz Pournajaf, Marco Franceschini, Francesco Infarinato","doi":"10.1186/s12984-025-01654-4","DOIUrl":"10.1186/s12984-025-01654-4","url":null,"abstract":"<p><p>In recent years, the fusion of the medical and computer science domains has gained significant traction in the scientific research landscape. Progress in both fields has enabled the generation of a vast amount of data used for making predictions and identifying interesting clusters and pathways. The Machine Learning (ML) model's application in the medical domain is one of the most compelling and challenging topics to explore, bridging the gap between Artificial Intelligence (AI) and healthcare. The combination of AI and medical information offers the possibility to create tools that can benefit both healthcare providers and physicians. This enables the enhancement of rehabilitation therapy and patient care. In the rehabilitation context, this work provides an alternative perspective: prediction of patients' home discharge upon completing the rehabilitation protocol. Demographic and clinical data were collected on 7282 inpatients from electronic Medical Record, each record was categorized into Neurological Patients (NP, N = 3222) or Orthopedic Patients (OP, N = 4060). To identify the most suitable machine learning model, an extensive data preprocessing phase was conducted. This process involved variables recoding, scaling, and the evaluation of different dataset balancing methods to optimize model performance. Following a thorough review and comparison of algorithms commonly employed in the clinical-rehabilitative field, the Random Over Sampling (ROS) technique, in combination with the Random Forest (RF) machine learning model, was selected. Subsequently, a comprehensive hyperparameter tuning phase was performed using a grid search approach. The optimized model achieved an average accuracy of 98% for OP and 96% for NP, based on 10-fold cross-validation applied to the balanced training set (unrealistic scenario). When tested on the unbalanced dataset (real-world condition), the RF model maintained strong generalization performance, achieving 90% accuracy for OP and 83% for NP. This work points out the increasing importance of AI in medicine, especially in the realm of personalized rehabilitation. The use of such approaches could signify a transformative shift in healthcare. The integration of machine learning not only enhances the precision of treatment but also opens new possibilities for patient-centered care, improving outcomes and quality of care for individuals undergoing rehabilitation.</p>","PeriodicalId":16384,"journal":{"name":"Journal of NeuroEngineering and Rehabilitation","volume":"22 1","pages":"117"},"PeriodicalIF":5.2,"publicationDate":"2025-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12105185/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144150666","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}