Diagnosis Of Neurological Disorders Research Articles

Generalizable electroencephalographic classification of Parkinson's disease using deep learning

Growing interest surrounds the use of electroencephalography (EEG) and deep learning for diagnosing neurological conditions like Parkinson's Disease (PD). Despite the existing proof-of-concept literature demonstrating the potential of deep learning in classifying PD from EEG data, neurologists have been slow to adopt these tools due to insufficient evidence of their real-world diagnostic generalizable performance. Our study aimed to evaluate the potential of deep learning for inter-subject PD classification using a conservative training approach and testing on an external independent dataset. Specifically, we utilized publicly available resting-state EEG data from PD patients at two separate centers, the University of New Mexico (n = 54) and the University of Iowa (n = 28), as our training and testing sets, respectively. Each of these recordings had a minimum of 2 minutes of data. We implemented a channel-wise convolutional neural network, tuning it with a leave-one-subject-out cross-validation approach. Our approach achieved a patient-level accuracy of 80.4% (epoch-level accuracy = 72.7%), which remained consistent when tested on the external dataset (patient-level accuracy = 82.8%, epoch-level accuracy = 75.7%). Our model performs equal-or-better than other standard classification models and our approach compares favourably to similar works. Our publicly available code serves as a foundation for future research exploring different deep learning architectures, investigating other pathologies, and involving larger datasets with the hope of accelerating the adoption of objective computational approaches for the diagnosis and monitoring of neurological disorders.

Enfermidades neurológicas de origem viral em bovinos no estado de Pernambuco, Brasil: estudo clínico e anatomopatológico

Abstract Studies related to neurological diseases are of great importance in Veterinary Medicine, particularly those involving production animals, such as cattle, due to their wide sanitary and public health significance. Therefore, the current study aims to describe the frequency of occurrence of the main clinical, laboratory, and anatomopathological findings of cattle diagnosed with neurological diseases of viral origin. Screening was performed in the general register of patients diagnosed through anatomopathological and/or complementary examination with illnesses of viral origin, admitted (live or dead) to the Clínica de Bovinos de Garanhuns-UFRPE from January 2009 to December 2019. The information recovered was entered in a database created in the computer program Microsoft Excel 2010®, distributed into clinical, laboratory, and anatomopathological data. The clinical findings on neurological diseases of viral etiology were very varied and non-specific, and the anatomopathological findings, together with laboratory methods, were of fundamental importance for the establishment of the diagnosis. The high frequency of rabies cases in this study demonstrates the importance of this disease for cattle rearing, as well as for Public Health. We emphasize the importance of including malignant catarrhal fever and herpes meningoencephalitis in the differential diagnosis of neurological diseases in the region, as well as the adoption of sanitary measures.

Adaptive Gated Graph Convolutional Network for Explainable Diagnosis of Alzheimer's Disease Using EEG Data.

Graph neural network (GNN) models are increasingly being used for the classification of electroencephalography (EEG) data. However, GNN-based diagnosis of neurological disorders, such as Alzheimer's disease (AD), remains a relatively unexplored area of research. Previous studies have relied on functional connectivity methods to infer brain graph structures and used simple GNN architectures for the diagnosis of AD. In this work, we propose a novel adaptive gated graph convolutional network (AGGCN) that can provide explainable predictions. AGGCN adaptively learns graph structures by combining convolution-based node feature enhancement with a correlation-based measure of power spectral density similarity. Furthermore, the gated graph convolution can dynamically weigh the contribution of various spatial scales. The proposed model achieves high accuracy in both eyes-closed and eyes-open conditions, indicating the stability of learned representations. Finally, we demonstrate that the proposed AGGCN model generates consistent explanations of its predictions that might be relevant for further study of AD-related alterations of brain networks.

Scattering angle resolved optical coherence tomography measures morphological changes in Bacillus subtilis colonies.

An unmet need is recognized for early detection and diagnosis of neurological diseases. Many psychological markers emerge years after disease onset. Mitochondrial dysfunction and corresponding neurodegeneration occur before onset of large-scale cell and tissue pathology. Early detection of subcellular morphology changes could serve as a beacon for early detection of neurological diseases. This study is on bacterial colonies, Bacillus subtilis, which are similar in size to mitochondria. This study investigates whether morphological changes can be detected in Bacillus subtilis using scattering angle resolved optical coherence tomography (SAR-OCT). The SAR-OCT was applied to detect scattering angle distribution changes in Bacillus subtilis. The rod-to-coccus shape transition of the bacteria was imaged, and the backscattering angle was analyzed by recording the distribution of the ratio of low- to medium angle scattering (L/M ratio). Bacillus orientation at different locations in colonies was analytically modeled and compared with SAR-OCT results. Significant differences in the distribution of backscattering angle were observed in Bacillus subtilis transitioning from rod-to-coccus shapes. In Bacillus subtilis, the -parameter of the Burr distribution of the SAR-OCT-derived L/M ratio was significantly smaller in coccus compared with rod-shaped bacteria. SAR-OCT-derived L/M ratio varied with bacterial position in the colony and is consistent with predicted orientations from previous studies. Study results support the potential of utilizing SAR-OCT to detect bacterial morphological changes.

MLMRS-Net: Electroencephalography (EEG) motion artifacts removal using a multi-layer multi-resolution spatially pooled 1D signal reconstruction network

Electroencephalogram (EEG) signals suffer substantially from motion artifacts when recorded in ambulatory settings utilizing wearable sensors. Because the diagnosis of many neurological diseases is heavily reliant on clean EEG data, it is critical to eliminate motion artifacts from motion-corrupted EEG signals using reliable and robust algorithms. Although a few deep learning-based models have been proposed for the removal of ocular, muscle, and cardiac artifacts from EEG data to the best of our knowledge, there is no attempt has been made in removing motion artifacts from motion-corrupted EEG signals: In this paper, a novel 1D convolutional neural network (CNN) called multi-layer multi-resolution spatially pooled (MLMRS) network for signal reconstruction is proposed for EEG motion artifact removal. The performance of the proposed model was compared with ten other 1D CNN models: FPN, LinkNet, UNet, UNet+, UNetPP, UNet3+, AttentionUNet, MultiResUNet, DenseInceptionUNet, and AttentionUNet++ in removing motion artifacts from motion-contaminated single-channel EEG signal. All the eleven deep CNN models are trained and tested using a single-channel benchmark EEG dataset containing 23 sets of motion-corrupted and reference ground truth EEG signals from PhysioNet. Leave-one-out cross-validation method was used in this work. The performance of the deep learning models is measured using three well-known performance matrices viz. mean absolute error (MAE)-based construction error, the difference in the signal-to-noise ratio (ΔSNR), and percentage reduction in motion artifacts (η). The proposed MLMRS-Net model has shown the best denoising performance, producing an average ΔSNR, η, and MAE values of 26.64 dB, 90.52%, and 0.056, respectively, for all 23 sets of EEG recordings. The results reported using the proposed model outperformed all the existing state-of-the-art techniques in terms of average η improvement.

PHYSICAL RESTRAINTS AT HOME AND THEIR FACTORS: A ONE-YEAR LONGITUDINAL SURVEY AMONG HOME CARE SERVICE USERS IN JAPAN

Abstract We conducted a one-year survey of homecare service users aged 75 years and older. Data from 769 clients were examined. Altogether 47 (6.1%) received physical restraint at least once among the five survey points conducted over a one-year period. Among them, 27 (57.4%) received restraint only at one point, and only 2 received restraint in all five points. In the bivariate analyses, the factors associated with the use of physical restraint were: diagnosis of neurological disease, unstable general condition or terminal stage, high level of care required, medical treatment, and family burden. When those who were released from the restraint at 12 months (n=30) were compared with those who were not (n=17), not having stroke, not receiving suctioning, and not having home-visit medical care were significant factors. Physical restraints at home were not common but we must be careful when we serve clients with significant factors of prolonged restraints.

MORPHOMETRIC STUDY OF THE FRONTAL HORN OF LATERAL VENTRICLES OF BRAIN BY IMAGING USING COMPUTERIZED TOMOGRAPHY

Introduction The cerebral ventricular system consists of a series of interconnecting spaces and channels which originate from the central lumen of the embryonic neural tube. The ventricular system lled with cerebrospinal uid, is an essential part of the brain. Understanding the normal anatomy and the variations of the ventricular system of brain is helpful for clinicians, neurosurgeons and radiologists in day-to-day clinical practice1. Aims And Objectives To determine the average dimensions and variations of the frontal horn of the normal lateral ventricles of brain by CT scan. Materials And Methods The study was conducted in individuals who attended the Department of Radiodiagnosis in Government Medical College, Thiruvananthapuram. Those patients whose brain CT scans were read as normal by the radiologist were taken up for the study. A total of 200 CT brain of individuals above 10 years of age were taken during the period from January 2017 to June 2018.100 males and 100 females were included in the study group. Results The length of the frontal horn of lateral ventricle of brain was found to be more on the left side and in male gender. It was also observed to be increasing with age. Conclusion The present study outlines the normal values of the length of frontal horn of the lateral ventricles of brain using Computerized tomography which would aid in the diagnosis and management of neurological disorders.

Detection of Neonicotinoid Insecticides and Their Metabolites in Human Cerebrospinal Fluid.

Detection of Neonicotinoid Insecticides and Their Metabolites in Human Cerebrospinal Fluid.

Factors associated with discharge from hospital to residential aged care for younger people with neuropsychiatric disorders: an exploratory case–control study in New South Wales, Australia

ObjectivesTo examine the sociodemographic and diagnostic factors associated with a discharge from hospital to residential aged care (RAC) for younger people (aged 15–64 years) with neuropsychiatric disorders.DesignAn exploratory case–control study...

Late‐life behavioral disorder: when is it FTD?

AbstractBackgroundDistinguishing the behavioural variant of Frontotemporal Dementia (bvFTD) from late‐onset primary psychiatric diseases (PPD) remains challenging with the lack of robust biomarkers for either disorder. Optimal duration of follow‐up of potential FTD cases remains elusive. Our aim was to determine whether a follow up duration of 5 years has added value compared to 2 years in the late‐onset frontal lobe syndrome. Second, we defined which clinical characteristics are valuable for diagnostic precision.MethodClinical outcomes of participants of the Late‐Onset frontal lobe (LOF) study were retrieved from 137 patients at least 5 years after baseline visit (T5). Endpoint diagnosis of bvFTD, PPD or Other Neurological Disorders (OND) were obtained. Baseline demographics and measures were compared between the T5 diagnosis groups. Clinical records of cases that switched diagnosis during follow‐up were assessed.ResultIn the 137 patients that were included in the study, the final diagnoses at T5 were bvFTD in 24.1% (n = 33, n = 29 probable bvFTD and n = 4 definite bvFTD), PPD 39.4% (n = 54), OND 33.6% (n = 46) and unknown 2.9% (n = 4). Between T2 and T5, 8 patients switched diagnosis compared to 29 patients during the first 2 years after inclusion (figure 1). Patients with a T2 diagnosis of probable bvFTD with an abnormal FDG‐PET whilst having normal structural imaging results (MRI) were prone to a diagnostic switch between T2 and T5.ConclusionA follow up duration of two years is sufficient for patients with a late‐onset frontal lobe syndrome to distinguish bvFTD from PPD on the condition that in cases with non‐supporting structural imaging results after two years further diagnostic work‐up is done.

Brain Connectivity: A Journal of Clinical Neurology, Neuroscience, & Neuroimaging Advancing the Field of Neurology

<i>Brain Connectivity: A Journal of Clinical Neurology, Neuroscience, &amp; Neuroimaging</i> Advancing the Field of Neurology

Ganglion cell complex thickness with spectral domain optical coherence tomography and correlations in a normative pediatric South Asian cohort.

Spectral domain optical coherence tomography (SD-OCT) was used to assess the perifoveal Ganglion cell complex (GCC) thickness in healthy Pakistani children. 174 eyes of 87 healthy children (3 to 16 years) were included after a thorough eye examination. Significant refractive error was excluded (>± 5 DS), glaucoma, ocular pathology, intraocular surgery, trauma, and systemic ailments. The perifoveal GCC analysis was done by Optopol Revo 80® high resolution SD-OCT. The average age was 11.1 ± 3.12 years. The average GCC thickness globally was 120.01 ± 76.74 μm, superiorly; 117.51 ± 8.77 μm, superonasally; 120.47 ± 8.78 μm, superotemporally, 103.83 ± 8.25 μm, inferiorly; 117.41 ± 8.71 μm, inferonasally 120.57 ± 8.88 μm, and inferotemporally; 107.15 ± 7.69 μm. The average GCC thickness was positively correlated with axial length (p=.02) and the GCC thickness in all sectors was significantly higher amongst males as compared to females (p < .05). Our study provides normative data for the macular GCC thickness in healthy children of our population. GCC thickness estimation is an important diagnostic parameter in glaucoma and optic neuropathies. Establishing a normative database for our pediatric population would help immensely in the diagnosis and monitoring of optic nerve disorders. RESEARCH HIGHLIGHTS: Spectral domain optical coherence tomography guided measurement of the ganglion cell complex thickness of the Pakistani pediatric population has not been done before. Our study provides normative data for the macular ganglion cell complex in healthy children of our population and studies its correlations with age, gender, intraocular pressure, axial length, refractive status, and corneal thickness. This will guide us in optic nerve and neurological disease diagnosis and monitoring.

Extracellular Vesicles in Chronic Demyelinating Diseases: Prospects in Treatment and Diagnosis of Autoimmune Neurological Disorders.

Extracellular vesicles (EVs) represent membrane-enclosed structures that are likely to be secreted by all living cell types in the animal organism, including cells of peripheral (PNS) and central nervous systems (CNS). The ability to cross the blood-brain barrier (BBB) provides the possibility not only for various EV-loaded molecules to be delivered to the brain tissues but also for the CNS-to-periphery transmission of these molecules. Since neural EVs transfer proteins and RNAs are both responsible for functional intercellular communication and involved in the pathogenesis of neurodegenerative diseases, they represent attractive diagnostic and therapeutic targets. Here, we discuss EVs' role in maintaining the living organisms' function and describe deviations in EVs' structure and malfunctioning during various neurodegenerative diseases.

Feedback Chain Network For Hippocampus Segmentation

The hippocampus plays a vital role in the diagnosis and treatment of many neurological disorders. Recent years, deep learning technology has made great progress in the field of medical image segmentation, and the performance of related tasks has been constantly refreshed. In this paper, we focus on the hippocampus segmentation task and propose a novel hierarchical feedback chain network. The feedback chain structure unit learns deeper and wider feature representation of each encoder layer through the hierarchical feature aggregation feedback chains, and achieves feature selection and feedback through the feature handover attention module. Then, we embed a global pyramid attention unit between the feature encoder and the decoder to further modify the encoder features, including the pair-wise pyramid attention module for achieving adjacent attention interaction and the global context modeling module for capturing the long-range knowledge. The proposed approach achieves state-of-the-art performance on three publicly available datasets, compared with existing hippocampus segmentation approaches. The code and results can be found from the link of https://github.com/easymoneysniper183/sematic_seg.

Textural feature based intelligent approach for neurological abnormality detection from brain signal data.

The diagnosis of neurological diseases is one of the biggest challenges in modern medicine, which is a major issue at the moment. Electroencephalography (EEG) recordings is usually used to identify various neurological diseases. EEG produces a large volume of multi-channel time-series data that neurologists visually analyze to identify and understand abnormalities within the brain and how they propagate. This is a time-consuming, error-prone, subjective, and exhausting process. Moreover, recent advances in EEG classification have mostly focused on classifying patients of a specific disease from healthy subjects using EEG data, which is not cost effective as it requires multiple systems for checking a subject's EEG data for different neurological disorders. This forces researchers to advance their work and create a single, unified classification framework for identifying various neurological diseases from EEG signal data. Hence, this study aims to meet this requirement by developing a machine learning (ML) based data mining technique for categorizing multiple abnormalities from EEG data. Textural feature extractors and ML-based classifiers are used on time-frequency spectrogram images to develop the classification system. Initially, noises and artifacts are removed from the signal using filtering techniques and then normalized to reduce computational complexity. Afterwards, normalized signals are segmented into small time segments and spectrogram images are generated from those segments using short-time Fourier transform. Then two histogram based textural feature extractors are used to calculate features separately and principal component analysis is used to select significant features from the extracted features. Finally, four different ML based classifiers are used to categorize those selected features into different disease classes. The developed method is tested on four real-time EEG datasets. The obtained result has shown potential in classifying various abnormality types, indicating that it can be utilized to identify various neurological abnormalities from brain signal data.

Simulation of nerve fiber based on anti-resonant reflecting optical waveguide

Light and optical techniques are widely used for the diagnosis and treatment of neurological diseases as advanced methods. Understanding the optical properties of nervous tissue and nerve cells is vital. Using light sources in these methods raises significant challenges, such as finding the place of light transmission in nerve fibers that could be an appropriate substrate for neural signaling. The myelinated axons are a promising candidate for transmitting neural signals and light due to their waveguide structures. On the other hand, with the emergence of diseases such as multiple sclerosis and disorders within the production and transmission of nerve signals, because of the demyelination, understanding the properties of the myelinated axon as a waveguide is obtaining additional necessity. The present study aims to show that the myelinated axon’s refractive index (RI) profile plays an essential role in transmitting the beams in it. According to the nerve fiber, RI profile and its similarity to depressed core fiber with lower RI of the core compared to the cladding, the behaviors of the nerve fiber based on anti-resonant reflecting optical waveguide structure are investigated by taking into account the realistic optical imperfections. Light launching to the myelin sheath and axon is shown by introducing the axon and myelin sheath as a waveguide in the presence of both axon and myelin with bends, myelin sheath variation, and node of Ranvier.

NerveStitcher: Corneal confocal microscope images stitching with neural networks

Corneal nerves are of great interest to clinicians and scientists due to their potential for the diagnosis of early neurological disorders. In vivo confocal microscopy (IVCM) has been used as a novel and reliable tool for observing and quantifying corneal sub-basal nerves. Creating a wide-field montage of the nerve plexus from a large amount of IVCM images facilitates the measurement of corneal nerve morphology. In this paper, we propose a fully automatic image stitching method using neural networks. Firstly, we extend a self-supervised point detector to find the feature points on IVCM images. Then a flexible points correspondence based on the attention mechanism is developed for partial assignment of image pair. The scattered IVCM images are consequently integrated and fused according to the local offsets. We experimented with our method on 30 sets of IVCM images. Compared to conventional methods, our method improves matching accuracy and significantly reduces processing time. And by calculating the morphological parameters of the corneal nerve for both single images and stitched images, our method can evaluate the corneal nerve of patients more accurately and reliably. The implemented code is available at https://github.com/LiTianYu6/NerveStitcher.

A Machine Learning Approach for Detecting Idiopathic REM Sleep Behavior Disorder.

Background and purpose: Growing evidence suggests that Machine Learning (ML) models can assist the diagnosis of neurological disorders. However, little is known about the potential application of ML in diagnosing idiopathic REM sleep behavior disorder (iRBD), a parasomnia characterized by a high risk of phenoconversion to synucleinopathies. This study aimed to develop a model using ML algorithms to identify iRBD patients and test its accuracy. Methods: Data were acquired from 32 participants (20 iRBD patients and 12 controls). All subjects underwent a video-polysomnography. In all subjects, we measured the components of heart rate variability (HRV) during 24 h recordings and calculated night-to-day ratios (cardiac autonomic indices). Discriminating performances of single HRV features were assessed. ML models based on Logistic Regression (LR), Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) were trained on HRV data. The utility of HRV features and ML models for detecting iRBD was evaluated by area under the ROC curve (AUC), sensitivity, specificity and accuracy corresponding to optimal models. Results: Cardiac autonomic indices had low performances (accuracy 63-69%) in distinguishing iRBD from control subjects. By contrast, the RF model performed the best, with excellent accuracy (94%), sensitivity (95%) and specificity (92%), while XGBoost showed accuracy (91%), specificity (83%) and sensitivity (95%). The mean triangular index during wake (TIw) was the best discriminating feature between iRBD and HC, with 81% accuracy, reaching 84% accuracy when combined with VLF power during sleep using an LR model. Conclusions: Our findings demonstrated that ML algorithms can accurately identify iRBD patients. Our model could be used in clinical practice to facilitate the early detection of this form of RBD.

An Ultrathin Low-Invasive Flexible Probe for Accurate Neural Stimulating

Neural probe plays an important role in neuroscience research and neurological diseases diagnosis. The flexible neural probes made by polymer emerging in recent years have been manifested more compliant and compatible with bio-tissues. However, the implantation of the flexible probe becomes another problem to be solved. In this letter, we propose a platinum black (Ptb) enhanced ultrathin flexible neural probe for accurate implantation. Benefiting from the anchoring structure on the flexible probe and the probe coupling with the shuttle by polyethylene glycol (PEG), reliable high-precision implantation has been demonstrated in agar model. Compared with traditional probe made with stiff shank, this flexible probe with anchoring structure is biocompatible and shows less immune reaction. In addition, the population spike (PS) was evoked successfully by biphasic stimulation in vivo.

A broad and variable lumbosacral myotome map uncovered by foraminal nerve root stimulation.

The human myotome is fundamental to the diagnosis and treatment of neurological disorders. However, this map was largely constructed decades ago, and its breadth, variability, and reliability remain poorly described, limiting its practical use. The authors used a novel method to reconstruct the myotome map in patients (n = 42) undergoing placement of dorsal root ganglion electrodes for the treatment of chronic pain. They electrically stimulated nerve roots (n = 79) in the intervertebral foramina at T12-S1 and measured triggered electromyography responses. L4 and L5 stimulation resulted in quadriceps muscle (62% and 33% of stimulations, respectively) and tibialis anterior (TA) muscle (25% and 67%, respectively) activation, while S1 stimulation resulted in gastrocnemius muscle activation (46%). However, L5 and S1 both resulted in abductor hallucis (AH) muscle activation (17% and 31%), L5 stimulation resulted in gastrocnemius muscle stimulation (42%), and S1 stimulation in TA muscle activation (38%). The authors also mapped the breadth of the myotome in individual patients, finding coactivation of adductor and quadriceps, quadriceps and TA, and TA and gastrocnemius muscles under L3, L4, and both L5 and S1 stimulation, respectively. While the AH muscle was commonly activated by S1 stimulation, this rarely occurred together with TA or gastrocnemius muscle activation. Other less common coactivations were also observed throughout T12-S1 stimulation. The muscular innervation of the lumbosacral nerve roots varies significantly from the classic myotome map and between patients. Furthermore, in individual patients, each nerve root may innervate a broader range of muscles than is commonly assumed. This finding is important to prevent misdiagnosis of radicular pathologies.