Background: Migraine is a debilitating neurological condition often impacting the quality of life and resulting in physical, emotional, and social burdens. Pharmaceutical interventions are the conventional treatment for migraine; however, behavioral interventions provide safe alternatives. Both mindfulness meditation and neurofeedback are behavioral interventions that have been separately studied for migraine treatment. To date, no studies have investigated neurofeedback-assisted mindfulness meditation for migraine treatment and prevention.
Objective: The objective of our study was to document the experiences of individuals with migraines who participated in an 8-week neurofeedback-based mindfulness meditation intervention as part of a randomized controlled trial.
Methods: Semistructured interviews were undertaken with 10 participants (7 female and 3 male participants) aged 23 to 55 years who had previously completed an 8-week neurofeedback-based mindfulness meditation program using Muse wearable sensory headbands as part of a randomized control trial. The interview data were analyzed using reflexive thematic analysis.
Results: Participants spoke to 3 categories of experiences: the positive impact of neurofeedback-based mindfulness meditation on migraine experiences, enhanced well-being and improved quality of life resulting from the intervention, and the benefits and drawbacks of incorporating a portable electroencephalogram technology into mindfulness meditation practices in the context of migraine treatment. In total, 9 participants felt that their ability to manage migraine symptoms was improved, and all participants expressed benefits beyond migraine prevention and pain management. Participants also spoke to the interconnectedness of migraine symptoms, daily stressors, and the framing of lived experience.
Conclusions: Notably, as the first study to evaluate the experiences of individuals with migraines using an at-home, neurofeedback-based mindfulness meditation intervention, this investigation adds to our understanding of nonpharmaceutical migraine treatment. Participants reported that this neurofeedback-based mindfulness meditation intervention improved migraine management, leading to significant reductions in pain intensity, migraine frequency, and medication use. They also described improved quality of life and emotional regulation related to this intervention, which they attributed to enhanced attentional control and body awareness. This research supports the consideration of neurofeedback-based mindfulness meditation interventions using emerging technologies, such as wearable electroencephalogram devices, as an accessible behavioral intervention for migraine management.
Background: Pediatric and adolescent patients with attention-deficit/hyperactivity disorder (ADHD) present unique challenges in adherence to device-based therapies outside the clinical environment. The development, approval, and availability of neurostimulation devices for the treatment of ADHD have prompted extraclinical research (ie, outside the sphere of the clinic) on the real-world implementation of such therapies in a population that has difficulty remembering tasks and staying attentive to therapy.
Objective: This study aims to explore the extraclinical pediatric ADHD treatment environment to ensure that design considerations and stakeholder contributions to future innovations are effective.
Methods: Using the Lean LaunchPad methodology with its emphasis on customer discovery and the business model canvas, qualitative analysis methods were applied to elicit the most pertinent themes regarding ADHD treatment in children and the general perception of a new device-based treatment regimen.
Results: Stakeholders expressed a desire that, for innovative ADHD therapies to appeal to children, they include a remote adherence monitoring component and maintain strong evidence of efficacy.
Conclusions: Such barriers to access and desired design features should be strongly considered in the development of neurostimulation therapies for pediatric patients with ADHD. Pediatric and adolescent patients with ADHD require attentive device design considerations to achieve therapeutic adherence in a real-world setting.
Background: Neuromodulation of the auricular branch of the vagus nerve using low-intensity focused ultrasound (LIFU) is an emerging mode of treatment for anxiety that could provide a complementary or alternative treatment modality for individuals who are refractory to conventional interventions. The proposed benefits of this technology have been largely unexamined with clinical populations. Further research is required to understand its clinical potential and use in improving and managing moderate to severe symptoms.
Objectives: The aim of this study was to do a preliminary investigation into the efficacy, safety, and usability of the wearable headset that delivers LIFU to the auricular branch of the vagus nerve for the purpose of alleviating anxiety disorder symptoms.
Methods: This study was a pre-post intervention study design for which we recruited 28 participants with a Beck Anxiety Inventory score of 16 points or greater. Participants completed 5 minutes of treatment daily consisting of LIFU neuromodulation delivered to the auricular branch of the vagus nerve. Participants did this for a period of 4 weeks. Assessments of anxiety symptom severity (Beck Anxiety Inventory), depression symptom severity (Beck Depression Inventory), posttraumatic stress disorder symptom severity (Post Traumatic Stress Disorder Checklist for the Diagnostic and Statistical Manual of Mental Disorders [Fifth Edition]), and sleep quality (Pittsburgh Sleep Quality Index) were taken prior to starting treatment and weekly for 4 weeks of treatment. Usability and safety were also assessed using an exit questionnaire and adverse event logging.
Results: After completing 4 weeks of LIFU neuromodulation to the auricular branch of the vagus nerve, the average Beck Anxiety Inventory score decreased by 14.9 (SD 10.6) points (Cohen d=1.06; P<.001), the average Beck Depression Inventory score decreased by 10.3 (SD 7.8) points (Cohen d=0.81; P<.001), the average Post Traumatic Stress Disorder Checklist for the Diagnostic and Statistical Manual of Mental Disorders (Fifth Edition) score decreased by 20.0 (SD 20.5) points (Cohen d=0.94; P<.001), and the average Pittsburgh Sleep Quality Index score decreased by 2.2 (SD 3.1) points (Cohen d=0.65; P=.001). On the exit questionnaire, participants rated the treatment highly for ease of use, effectiveness, and worthiness of the time invested. Only 1 adverse event was reported throughout the entire trial, which was mild and temporary.
Conclusions: This preliminary study provided justification for further research into the efficacy, safety, and feasibility of using LIFU to modulate the auricular branch of the vagus nerve and reduce the symptoms of anxiety, depression, and posttraumatic stress disorder.
Background: Alzheimer disease (AD) is a progressive neurodegenerative disorder that impairs cognitive function, memory, and behavior. Early and accurate diagnosis is essential for effective management; however, traditional cognitive tests often lack the sensitivity and specificity required for early detection.
Objective: This study aims to develop and evaluate NeuroFusionNet-a diagnostic tool that integrates a custom convolutional neural network (CNN) with a pretrained VGG16 model-to improve the accuracy and reliability of AD diagnosis from neuroimaging data across multiple cognitive classes.
Methods: A comprehensive preprocessing pipeline, including brain region segmentation, was implemented to isolate regions of interest and reduce noise. NeuroFusionNet extracts multilevel features by combining a custom CNN with VGG16, while Local Interpretable Model-Agnostic Explanations enhances interpretability. Data were obtained from the Alzheimer's Disease Neuroimaging Initiative database, comprising 600 test samples (120 per class for AD, cognitively normal, early mild cognitive impairment, late mild cognitive impairment, and mild cognitive impairment). Given the multiclass nature of the study, odds ratios were not applied. Statistical significance was assessed using the McNemar test for paired predictions.
Results: NeuroFusionNet achieved an overall accuracy of 0.81 (95% CI 0.779-0.841; P<.001). Per-class performance metrics were as follows: AD: precision 0.90 (95% CI 0.85-0.95), recall 0.78 (95% CI 0.72-0.84), F 1-score 0.84; cognitively normal: precision 0.67 (95% CI 0.60-0.74), recall 0.97 (95% CI 0.94-1.00), F 1-score 0.79; early mild cognitive impairment: precision 0.90 (95% CI 0.84-0.96), recall 0.82 (95% CI 0.76-0.88), F 1-score 0.86; late mild cognitive impairment: precision 0.95 (95% CI 0.90-1.00), recall 0.87 (95% CI 0.81-0.93), F 1-score 0.90; and mild cognitive impairment: precision 0.71 (95% CI 0.64-0.78), recall 0.61 (95% CI 0.53-0.69), F 1-score 0.65. Training and validation curves over 50 epochs indicated robust learning with minimal overfitting.
Conclusions: NeuroFusionNet demonstrated robust performance in a multiclass diagnostic setting, achieving high accuracy and balanced per-class performance. The combination of a custom CNN and fine-tuned VGG16, along with the interpretability provided by Local Interpretable Model-Agnostic Explanations, yields a reliable tool for early AD detection with significant potential to enhance clinical decision-making. Further validation on larger datasets is warranted.
Background: This paper presents an easy-to-use, affordable robotic manipulandum device (RMD) equipped with smart monitoring and assistive technologies to engage in game-based exercise and repetitive task practice. The RMD has been designed to enhance a wide range of fine motor manual dexterity skills, including thumb, finger, and wrist movements. By focusing on finger and hand functions, it extends its utility beyond basic reaching or object transfer movements. Various interchangeable 3D-printed therapy handles of different shapes and sizes can be easily attached to the RMD drive shaft. These handle movements can be used to engage with numerous affordable, commercially available computer games, allowing patients to practice tasks that involve varying movement amplitudes, speeds, precision, and cognitive challenges. Additionally, the device is capable of automatically recording and storing the patient's real-time performance data on any given computer, integrating assessment into treatment.
Objective: A pilot study was conducted with 5 patients with stroke to examine the feasibility and benefits of a 6-week game-based exercise program using the proposed device.
Methods: A feasibility study was conducted with 5 participants. Data were collected using the computer game-based upper extremity assessment of manual dexterity and Wolf Motor Function Test (WMFT) before and after the intervention lasting 6 weeks.
Results: The pilot study demonstrated that clients' expectations related to manual dexterity were met. The average improvement in the functional ability score of the WMFT was 14 (SD 3) points, with all participants exceeding the minimal clinically important difference. The average reduction in total time was 30 (SD 14) seconds, with 4 of 5 participants surpassing the minimal clinically important difference. For the computer game-based upper extremity assessment, the average improvement in success rate was 23% (SD 12%), and the average decrease in response time was 105 (SD 44) milliseconds.
Conclusions: Findings revealed acceptable, engaging, game-based, and task-oriented training with a high level of compliance. Substantial improvements from pre- to postintervention were observed using the WMFT and assessments of manual dexterity.
Background: Speech features are increasingly linked to neurodegenerative and mental health conditions, offering the potential for early detection and differentiation between disorders. As interest in speech analysis grows, distinguishing between conditions becomes critical for reliable diagnosis and assessment.
Objective: This pilot study explores speech biosignatures in two distinct neurodegenerative conditions: (1) mild traumatic brain injuries (eg, concussions) and (2) Parkinson disease (PD) as the neurodegenerative condition.
Methods: The study included speech samples from 235 participants (97 concussed and 94 age-matched healthy controls, 29 PD and 15 healthy controls) for the PaTaKa test and 239 participants (91 concussed and 104 healthy controls, 29 PD and 15 healthy controls) for the Sustained Vowel (/ah/) test. Age-matched healthy controls were used. Young age-matched controls were used for concussion and respective age-matched controls for neurodegenerative participants (15 healthy samples for both tests). Data augmentation with noise was applied to balance small datasets for neurodegenerative and healthy controls. Machine learning models (support vector machine, decision tree, random forest, and Extreme Gradient Boosting) were employed using 37 temporal and spectral speech features. A 5-fold stratified cross-validation was used to evaluate classification performance.
Results: For the PaTaKa test, classifiers performed well, achieving F 1-scores above 0.9 for concussed versus healthy and concussed versus neurodegenerative classifications across all models. Initial tests using the original dataset for neurodegenerative versus healthy classification yielded very poor results, with F 1-scores below 0.2 and accuracy under 30% (eg, below 12 out of 44 correctly classified samples) across all models. This underscored the need for data augmentation, which significantly improved performance to 60%-70% (eg, 26-31 out of 44 samples) accuracy. In contrast, the Sustained Vowel test showed mixed results; F 1-scores remained high (more than 0.85 across all models) for concussed versus neurodegenerative classifications but were significantly lower for concussed versus healthy (0.59-0.62) and neurodegenerative versus healthy (0.33-0.77), depending on the model.
Conclusions: This study highlights the potential of speech features as biomarkers for neurodegenerative conditions. The PaTaKa test exhibited strong discriminative ability, especially for concussed versus neurodegenerative and concussed versus healthy tasks, whereas challenges remain for neurodegenerative versus healthy classification. These findings emphasize the need for further exploration of speech-based tools for differential diagnosis and early identification in neurodegenerative health.
Neurological disorders are the leading cause of physical and cognitive disability across the globe, currently affecting up to 15% of the world population, with the burden of chronic neurodegenerative diseases having doubled over the last 2 decades. Two decades ago, neurologists relying solely on clinical signs and basic imaging faced challenges in diagnosis and treatment. Today, the integration of artificial intelligence (AI) and bioinformatic methods is changing this landscape. This paper explores this transformative journey, emphasizing the critical role of AI in neurology, aiming to integrate a multitude of methods and thereby enhance the field of neurology. Over the past 25 years, integrating biomedical data science into medicine, particularly neurology, has fundamentally transformed how we understand, diagnose, and treat neurological diseases. Advances in genomics sequencing, the introduction of new imaging methods, the discovery of novel molecular biomarkers for nervous system function, a comprehensive understanding of immunology and neuroimmunology shaping disease subtypes, and the advent of advanced electrophysiological recording methods, alongside the digitalization of medical records and the rise of AI, all led to an unparalleled surge in data within neurology. In addition, telemedicine and web-based interactive health platforms, accelerated by the COVID-19 pandemic, have become integral to neurology practice. The real-world impact of these advancements is evident, with AI-driven analysis of imaging and genetic data leading to earlier and more accurate diagnoses of conditions such as multiple sclerosis, Parkinson disease, amyotrophic lateral sclerosis, Alzheimer disease, and more. Neuroinformatics is the key component connecting all these advances. By harnessing the power of IT and computational methods to efficiently organize, analyze, and interpret vast datasets, we can extract meaningful insights from complex neurological data, contributing to a deeper understanding of the intricate workings of the brain. In this paper, we describe the large-scale datasets that have emerged in neurology over the last 25 years and showcase the major advancements made by integrating these datasets with advanced neuroinformatic approaches for the diagnosis and treatment of neurological disorders. We further discuss challenges in integrating AI into neurology, including ethical considerations in data use, the need for further personalization of treatment, and embracing new emerging technologies like quantum computing. These developments are shaping a future where neurological care is more precise, accessible, and tailored to individual patient needs. We believe further advancements in AI will bridge traditional medical disciplines and cutting-edge technology, navigating the complexities of neurological data and steering medicine toward a future of more precise, accessible, and patient-centric health care.
Background: Developing new clinical measures for degenerative cervical myelopathy (DCM) is an AO Spine RECODE-DCM research priority. Difficulties detecting DCM, and changes in DCM, cause diagnostic and treatment delays in clinical settings and heightened costs in clinical trials due to elevated recruitment targets. Digital outcome measures can tackle these challenges due to their ability to measure disease remotely, repeatedly, and more economically.
Objective: The study aims to assess the validity of MoveMed, a battery of performance outcome measures performed using a smartphone app, in the measurement of DCM.
Methods: A prospective observational study in decentralized secondary care was performed in England, United Kingdom. Validity and risk of bias were assessed using criteria from the COSMIN (Consensus-Based Standards for the Selection of Health Measurement Instruments) manual. Each MoveMed outcome was compared with 2 patient-reported comparators, with a priori hypotheses of convergence or divergence tested against consensus thresholds. The primary outcome was the correlation coefficient between the MoveMed outcome and the patient-reported comparators. The secondary outcome was the percentage of correlations that aligned with the a priori hypotheses. The comparators used were the patient-derived modified Japanese Orthopaedic Association score and the World Health Organization Quality of Life Brief Version questionnaire. Thresholds for convergence or divergence were set at ≥0.3 for convergence, <0.3 for divergence, and >0/<0 for directionality.
Results: A total of 27 adults aged 60 (SD 11) years who live with DCM and possess an approved smartphone were included in a preliminary analysis. As expected, MoveMed tests of neuromuscular function correlated most with questionnaires of neuromuscular function (≥0.3) and least with questionnaires of quality of life (<0.3). Furthermore, directly related constructs correlated positively to each other (>0), while inversely related constructs correlated negatively (<0). Overall, 74% (67/90) and 47% (8/17) of correlations (unidimensional and multidimensional, respectively) were in accordance with hypotheses. No risk-of-bias factors from the COSMIN Risk of Bias checklist were recorded. Overall, this was equivalent to "very good" quality evidence of sufficient construct validity in DCM.
Conclusions: MoveMed outcomes and patient-reported questionnaires converge and diverge in accordance with expectations. These findings support the validity of the MoveMed tests in an adult population living with DCM. Criteria from COSMIN provide "very good" quality evidence to support this.
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：