Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 50.867
Filtrar
1.
BMC Pregnancy Childbirth ; 20(1): 587, 2020 Oct 06.
Artigo em Inglês | MEDLINE | ID: mdl-33023500

RESUMO

BACKGROUND: There are no published cases of tonic-clonic seizures and posterior bilateral blindness during pregnancy and Severe Acute Respiratory Syndrome (SARS) Coronavirus (COV) 2 (SARS-COV-2) infection. We do not just face new and unknown manifestations, but also how different patient groups are affected by SARS-COV-2 infection, such as pregnant women. Coronavirus Disease 2019 (COVID-19), preeclampsia, eclampsia and posterior reversible leukoencephalopathy share endothelium damage and similar pathophysiology. CASE PRESENTATION: A 35-year-old pregnant woman was admitted for tonic-clonic seizures and SARS-COV-2 infection. She had a normal pregnancy control and no other symptoms before tonic-clonic seizures development. After a Caesarean section (C-section) she developed high blood pressure, and we initiated antihypertensive treatment with labetalol, amlodipine and captopril. Few hours later she developed symptoms of cortical blindness that resolved in 72 h with normal brain computed tomography (CT) angiography. CONCLUSION: The authors conclude that SARS COV-2 infection could promote brain endothelial damage and facilitate neurological complications during pregnancy.


Assuntos
Anti-Hipertensivos/administração & dosagem , Betacoronavirus/isolamento & purificação , Cegueira Cortical , Cesárea/métodos , Infecções por Coronavirus , Eclampsia , Fibrinolíticos/administração & dosagem , Pandemias , Pneumonia Viral , Complicações Infecciosas na Gravidez , Convulsões , Adulto , Cegueira Cortical/diagnóstico , Cegueira Cortical/virologia , Encéfalo/diagnóstico por imagem , Angiografia por Tomografia Computadorizada/métodos , Infecções por Coronavirus/diagnóstico , Infecções por Coronavirus/fisiopatologia , Diagnóstico Diferencial , Eclampsia/diagnóstico , Eclampsia/terapia , Eclampsia/virologia , Feminino , Humanos , Exame Neurológico/métodos , Pneumonia Viral/diagnóstico , Pneumonia Viral/fisiopatologia , Gravidez , Complicações Infecciosas na Gravidez/diagnóstico , Complicações Infecciosas na Gravidez/etiologia , Complicações Infecciosas na Gravidez/fisiopatologia , Resultado da Gravidez , Convulsões/diagnóstico , Convulsões/etiologia , Convulsões/terapia , Tomografia Computadorizada por Raios X/métodos , Resultado do Tratamento
2.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 4248-4251, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018934

RESUMO

Epilepsy affects more than 50 million people and ranks among the most common neurological diseases worldwide. Despite advances in treatment, one-third of patients still suffer from refractory epilepsy. Wearable devices for real-time patient monitoring can potentially improve the quality of life for such patients and reduce the mortality rate due to seizure-related accidents and sudden death in epilepsy. However, the majority of employed seizure detection techniques and devices suffer from unacceptable false-alarm rate. In this paper, we propose a robust seizure detection methodology for a wearable platform and validate it on the Physionet.org CHB-MIT Scalp EEG database. It reaches sensitivity of 0.966 and specificity of 0.925, and reducing the false-alarm rate by 34.7%. We also evaluate the battery lifetime of the wearable system including our proposed methodology and demonstrate the feasibility of using it in real time for up to 40.87 hours on a single battery charge.


Assuntos
Epilepsia , Dispositivos Eletrônicos Vestíveis , Eletroencefalografia , Epilepsia/diagnóstico , Humanos , Qualidade de Vida , Convulsões/diagnóstico
3.
Zh Nevrol Psikhiatr Im S S Korsakova ; 120(8. Vyp. 2): 10-16, 2020.
Artigo em Russo | MEDLINE | ID: mdl-33016671

RESUMO

OBJECTIVE: To determine the incidence of non-convulsive status epilepticus, epileptiform activity, rhythmic and periodic patterns in patients with acute stroke. MATERIAL AND METHOD: An analysis of electroencephalography (EEG) in 86 stroke patients in the neurointensive care unit of the tertiary medical center was performed. Criteria for starting EEG recording were epileptic seizures or clinical suspicion of uncontrolled epileptic status. The ictal-interictal continuum biomarkers and the diagnostic value of EEG for prediction of survival and recovery were assessed. RESULTS: Pathological changes on EEG were recorded in 84% of patients. These patients showed the absence of the dominant occipital rhythm (66%) and hemispheric slowing (42%). Diffuse slowing below the theta range was observed in 41% of patients. EEG reactivity was absent in 20%. Sporadic epileptiform discharges were recorded in 36% of patients and rhythmic and periodic patterns in 26%. Reliable predictors of the unfavorable outcome were the absence of dominant occipital rhythm, lack of reactivity, and low amplitude of the background EEG. No association between the recording of epileptiform activity and the probability of death was shown. CONCLUSION: The most useful EEG biomarkers for predicting survival are amplitude, dominant frequency of background EEG activity and reactivity to external stimulus. Sporadic epileptiform discharges, rhythmic, and periodic patterns are not mandatory associated with a negative prognosis in stroke patients.


Assuntos
Epilepsia , Estado Epiléptico , Acidente Vascular Cerebral/diagnóstico , Eletroencefalografia , Humanos , Convulsões
4.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 2524-2527, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018520

RESUMO

Surgical resection of the seizure onset zone (SOZ) could potentially lead to seizure-freedom in medically refractory epilepsy patients. However, localizing the SOZ can be a time consuming and tedious process involving visual inspection of intracranial electroencephalographic (iEEG) recordings captured during passive patient monitoring. Single pulse electrical stimulation (SPES) is currently performed on patients undergoing invasive EEG monitoring for the main purposes of mapping functional brain networks such as language and motor networks. We hypothesize that evoked responses from SPES can also be used to localize the SOZ as they may express the natural frequencies and connectivity of the iEEG network. To test our hypothesis, we construct patient specific single-input multi-output transfer function models from the evoked responses recorded from five epilepsy patients that underwent SPES evaluation and iEEG monitoring. Our preliminary results suggest that the stimulation electrodes that produced the highest gain transfer functions, as measured by the ${\mathcal{H}_\infty }$ norm, correspond to those electrodes clinically defined in the SOZ in successfully treated patients.Clinical Relevance- This study creates an innovative tool that allows clinicians to identify the seizure onset zone in medically refractory epilepsy patients using quantitative metrics thereby increasing surgical success outcomes, mitigating patient risks, and decreasing costs.


Assuntos
Epilepsia Resistente a Medicamentos , Epilepsia , Epilepsia Resistente a Medicamentos/terapia , Estimulação Elétrica , Eletrocorticografia , Epilepsia/terapia , Humanos , Convulsões/terapia
5.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 2528-2531, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018521

RESUMO

Surgical removal of the seizure onset zone (SOZ) in epilepsy patients is a potentially curative treatment, but the process heavily relies on accurate localization of the SOZ via visual inspection. SPES (Single-pulse electrical stimulation) is a method recently used to explore inter-areal connectivity in vivo to probe functional brain networks such as language and motor networks, and to a much lesser degree, seizure networks. We hypothesized that a dynamical quantification of the connectivity networks derived from the evoked responses induced by SPES could also be used to localize the SOZ. To test our hypothesis, we used an intracranial EEG (iEEG) data set in which five epilepsy patients underwent extensive SPES evaluation. For each patient, and for each dataset that stimulated a different pair of electrodes, we constructed a state-space model from the patient's data. Specifically, we simultaneously estimated model parameters under an exogenous pulse input to a dynamical system whose state vector consisted of the response iEEG signals. Then, the size of the reachable state space, as quantified by the maximum singular value of the reachability matrix, σmax(R), was computed and denoted as the "largest" network response possible when stimulating the given pair. Our results suggest high agreement between σmax(R) and clinically annotated SOZ for patients with localizable SOZs.Clinical Relevance- Our study applies dynamical systems theory to identify epileptogenic brain regions, creating a novel tool that clinicians may use in surgical planning for medically-refractory epilepsy patients.


Assuntos
Epilepsia Resistente a Medicamentos , Convulsões , Animais , Encéfalo , Eletrocorticografia , Potenciais Evocados , Humanos
6.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 2687-2690, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018560

RESUMO

The purpose of this study is to analyse the ictal variations in peripheral blood flow using photoplethysmogram (PPG) and single lead Electrocardiogram (ECG) signals. 11 subjects with 56 partial seizures were recorded with the PPG sensor worn on their left ankles. 6 different features from PPG pulse morphology related to hemodynamics were derived. The seizures were divided into two groups based on the side of the seizure activity. The investigation of ictal variations in features did not show any significant difference between the seizures' lateralizations. The analysis of latencies of ictal changes in the PPG features revealed the PPG pulse amplitude precede the variations in other PPG features including ictal heart rate variability. In addition, analysis of the effect of seizure lengths on ictal variations showed the seizures' lengths have no significant effect on the feature variation rates.Clinical relevance- Analysis of the extracted PPG features and their timing suggest an increase in vascular resistance due to increase in sympathetic tone which occurs prior to the ictal tachycardia. These variations is independent of the seizures' lengths and lateralizations.


Assuntos
Epilepsia , Fotopletismografia , Epilepsia/diagnóstico , Frequência Cardíaca , Humanos , Convulsões/diagnóstico , Resistência Vascular
7.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 2833-2836, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018596

RESUMO

Seizure types and characteristics may vary with time in a patient with distinct mechanisms underlying the propagation of ictal activity. Similarly, we found that both focal and generalized seizures coexist in some pilocarpine-induced chronic temporal lobe epilepsy (TLE) rats. In different seizure patterns, mapping complex networks and analyzing epileptic characteristics involved in seizure propagation are likely to reflect seizure propagation mechanisms, and indicate the establishment of stimulation strategy for epilepsy treatment, especially on the selection of stimulation targets. In our study, we used Granger causality method to track the time-variant epileptic brain functional connectivity in focal and generalized seizures from multi-site local field potentials (LFPs). Results showed that these two major types of seizures had different propagation patterns during ictal period. When comparing them, generalized seizures involved in a network with more complex relationships and spread to more extensive brain regions than in local seizures at mid-ictal stage. Moreover, we observed that focal seizures had a focused causal hub with strong interactions, while generalized seizures had relative distributed causal hubs to drive the development of seizure during seizure-onset stage. These findings suggest that stimulation strategy might need to be adapted to different seizure types thus allowing for retuning abnormal epileptic brain network and obtaining better treatment effect on seizure suppression.


Assuntos
Epilepsia do Lobo Temporal , Epilepsia , Animais , Encéfalo , Humanos , Pilocarpina , Ratos , Convulsões
8.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 3440-3443, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018743

RESUMO

The phase-amplitude coupling in EEG signal of different frequencies is considered as a useful biomarker in delineating epileptogenic tissues, but some physiological processes can also generate phase-amplitude coupling pattern, such as memory process. Current analysis on cross-frequency coupling (CFC) feature is mostly based on extracting the strength of coupling but not coupling patterns in frequency-frequency domain. In this paper, we proposed a method for identifying epileptogenic tissue using convolutional neural networks (CNN) based on CFC pattern. Stereo-electroencephalograph (SEEG) from six patients with intractable epilepsy were used in this analysis. First, modulation indexes (MIs) were calculated using a moving window for each channel across seizures. Then those MIs were marked as inside epileptogenic zone (EZ) or outside EZ based on the surgical resection area. CNN was trained by those two-dimensional coupling patterns and tested by leave-one-out method. The receiver operating characteristics (ROC) curve was further generated. The results showed that average area-under-curve (AUC) performance reached 0.88. The sensitivity was 0.81, and the specificity was 0.79. Those results suggest that the CFC pattern can be used to identify SEEG channels in the epileptogenic region using the CNN.Clinical Relevance- This method has the potential to be used as an analytical tool for neurologists to identify epileptogenic brain tissues.


Assuntos
Epilepsia Resistente a Medicamentos , Redes Neurais de Computação , Algoritmos , Eletroencefalografia , Humanos , Convulsões
9.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 3460-3464, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018748

RESUMO

The absence of epileptiform activity in a scalp electroencephalogram (EEG) recorded from a potential epilepsy patient can cause delays in clinical care delivery. Here we present a machine-learning-based approach to find evidence for epilepsy in scalp EEGs that do not contain any epileptiform activity, according to expert visual review (i.e., "normal" EEGs). We found that deviations in the EEG features representing brain health, such as the alpha rhythm, can indicate the potential for epilepsy and help lateralize seizure focus, even when commonly recognized epileptiform features are absent. Hence, we developed a machine-learning-based approach that utilizes alpha-rhythm-related features to classify 1) whether an EEG was recorded from an epilepsy patient, and 2) if so, the seizure-generating side of the patient's brain. We evaluated our approach using "normal" scalp EEGs of 48 patients with drug-resistant focal epilepsy and 144 healthy individuals, and a naive Bayes classifier achieved area under ROC curve (AUC) values of 0.81 and 0.72 for the two classification tasks, respectively. These findings suggest that our methodology is useful in the absence of interictal epileptiform activity and can enhance the probability of diagnosing epilepsy at the earliest possible time.


Assuntos
Epilepsia , Teorema de Bayes , Encéfalo , Eletroencefalografia , Epilepsia/diagnóstico , Humanos , Convulsões/diagnóstico
10.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 3695-3698, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018803

RESUMO

Epilepsy affects over 50 million people worldwide and 30% of patients' seizures are medically refractory. The process of localizing and removing the epileptogenic zone is error-prone and ill-posed in part because we do not understand how epilepsy manifests. It has recently been proposed that the epileptic cortex is fragile in the sense that seizures manifest through small perturbations in the synaptic connections that render the entire cortical network unstable. If the fragility of the cortical network could be computed over a period in which seizure genesis occurs, then it might elucidate network mechanisms correlated to the epileptogenic zone. In this study, we used local field potentials (LFP) from neocortex by implementing an acute model of epilepsy in mice. These recordings were used to develop a dynamical network model that quantifies the fragility of the nodes from LFP epochs of baseline activity, preictal and ictal states. Fragility was quantified by the generation of a linear time-varying model to which we then applied a perturbation to determine the sensitivity of nodes in the network. Spatiotemporal fragility maps showed clear quantifiable changes in the epileptogenic network's properties throughout different states of seizure genesis. We quantified this difference over a baseline, preictal and ictal periods to show that network fragility is modulated in the manifestation of epilepsy.


Assuntos
Epilepsia , Neocórtex , Animais , Humanos , Camundongos , Convulsões
11.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 3699-3702, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018804

RESUMO

Time- and frequency-domain studies of EEG signals are most commonly employed to study the electrical activities of the brain in order to diagnose potential neurological disorders. In this work, we applied the global coherence approach to help estimating the neural synchrony across multiple nodes in the brain, prior and during a seizure. The ratio of the largest eigenvalue to the sum of the eigenvalues of the cross spectral matrix at a certain frequency and time allowed detecting a strong coordinated neural activity in alpha sub-band for the frontal lobe epilepsy. Kruskal Wallis test reveals that global coherence is an efficient tool before the seizure for the temporal lobe epilepsy in a wide range of frequencies from Delta to Beta sub-bands.Clinical Relevance-The work introduces global coherence as a new and efficient feature in prediction of seizure and specifically for the frontal lobe epilepsy.


Assuntos
Epilepsia do Lobo Frontal , Epilepsia do Lobo Temporal , Encéfalo , Eletroencefalografia , Epilepsia do Lobo Frontal/diagnóstico , Epilepsia do Lobo Temporal/diagnóstico , Humanos , Convulsões/diagnóstico
12.
Medicine (Baltimore) ; 99(41): e22478, 2020 Oct 09.
Artigo em Inglês | MEDLINE | ID: mdl-33031279

RESUMO

RATIONALE: Pleomorphic xanthoastrocytoma (PXA) is a rare low-grade glial neoplasm of the central nervous system, which is difficult to distinguish from other neoplastic and non-neoplastic entities. Herein, we report 2 cases of PXA that had been misdiagnosed as an inflammatory granuloma. PATIENT CONCERNS: The first case was a 22-year-old man who originally presented with a generalized seizure 7 years previously. Magnetic resonance imaging (MRI) revealed a lesion in the right parietal lobe, leading to a diagnosis of inflammatory granuloma. The second case was a 43-year-old man who presented with repeated generalized seizures. MRI revealed a nodular lesion in the left temporal lobe. The magnetic resonance spectrum showed elevated Cho and NAA peaks and a decreased Cr peak. An inflammatory granuloma was suspected. DIAGNOSIS: After surgical treatment, histopathological examination revealed PXA. INTERVENTIONS: In the first case, after 10 months of anti-inflammatory treatment, the lesion was significantly reduced in size. During the following 7 years, the patient experienced generalized seizures 3 to 4 times annually. To control intractable epilepsy, the lesion was resected. In the second case, conservative treatment provided no benefit, and then the lesion was resected. OUTCOMES: In the first case, during a follow-up period of 14 months, the patient was seizure-free with no tumor recurrence. In the second case, after a 6 months of follow-up, the patient remained seizure-free with no tumor recurrence. LESSONS: The preoperative differential diagnosis of PXA is challenging due to the nonspecific symptoms and imaging manifestations. Considering the potential risk of malignant transformation of PXA, early surgery should be highlighted, and gross total resection is associated with a favorable prognosis.


Assuntos
Astrocitoma/diagnóstico por imagem , Neoplasias Encefálicas/diagnóstico por imagem , Granuloma/diagnóstico por imagem , Adulto , Astrocitoma/patologia , Astrocitoma/cirurgia , Neoplasias Encefálicas/patologia , Neoplasias Encefálicas/cirurgia , Cérebro , Diagnóstico Diferencial , Erros de Diagnóstico , Humanos , Imagem por Ressonância Magnética , Masculino , Convulsões/etiologia , Adulto Jovem
13.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 5416-5419, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33019205

RESUMO

Epileptic Seizure (Epilepsy) is a neurological disorder that occurs due to abnormal brain activities. Epilepsy affects patients' health and lead to life-threatening situations. Early prediction of epilepsy is highly effective to avoid seizures. Machine Learning algorithms have been used to classify epilepsy from Electroencephalograms (EEG) data. These algorithms exhibited reduced performance when classes are imbalanced. This work presents an integrated machine learning approach for epilepsy detection, which can effectively learn from imbalanced data. This approach utilizes Principal Component Analysis (PCA) at the first stage to extract both high- and low- variant Principal Components (PCs), which are empirically customized for imbalanced data classification. Conventionally, PCA is used for dimension reduction of a dataset leveraging PCs with high variances. In this paper, we propose a model to show that PCs associated with low variances can capture the implicit pattern of minor class of a dataset. The selected PCs are then fed into different machine learning classifiers to predict seizures. We performed experiments on the Epileptic Seizure Recognition dataset to evaluate our model. The experimental results show the robustness and effectiveness of the proposed model.


Assuntos
Epilepsia , Convulsões , Eletroencefalografia , Epilepsia/diagnóstico , Humanos , Aprendizado de Máquina , Análise de Componente Principal , Convulsões/diagnóstico
14.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 108-111, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33017942

RESUMO

The traditional emotion classification framework usually fits all the features segments of the same trial to a fixed annotation. Considering the fact that emotion is a reaction to stimuli that lasts for varied periods, we argue that the indiscriminate annotation is equivalent to taking the emotional state as fixed within the whole trial, leading to a decrease of the classification accuracy. In this study, we attempt to alleviate this issue by developing a thresholding scheme, converting the continuous emotional trace into a three-class annotation temporally. The features within a trial are therefore assigned to varied emotional states, resulting in an improvement in the accuracy. A long short term memory (LSTM) networks-based emotion classification framework is implemented, to which the proposed thresholding scheme is applied. A subset of MAHNOB-HCI dataset with continuous emotional annotation is used. The EEG signal and frontal facial video are used for feature extraction. The experiment results demonstrate that the proposed scheme provides statistically significant improvement to the three-class classification accuracy of the EEG feature-based LSTM network (p-value = 0.0329).


Assuntos
Aprendizado Profundo , Eletroencefalografia , Emoções , Humanos , Memória de Longo Prazo , Convulsões
15.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 112-115, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33017943

RESUMO

Epilepsy is a neurological disorder which causes seizures in over 65 million people worldwide. Recently developed implantable therapeutic devices aim to prevent symptoms by applying acute electrical stimulation to the seizure-generating brain region in response to activity detected by on-device machine learning hardware. Many training algorithms require an equal number of examples for each target class (e.g. normal activity and seizures), and performance can suffer if this condition is not satisfied. In the case of epilepsy, poor performance can cause seizures to be missed, or stimulation to be applied erroneously. As there is an abundance of normal (interictal) data in clinical EEG recordings, but seizures are rare events (less than 1% of the dataset), the data available for training is severely imbalanced. There are several conventional pre-processing methods used to address imbalanced class learning, such as down-sampling of the majority class and up-sampling of the minority class, but each have performance drawbacks. This paper presents an improved method which involves reducing the majority class down to the most effective interictal outlier samples. Outliers are determined by using Exponentially Decaying Memory Signal Energy (EDMSE) features with Isolation Forests and an ANOVA-based method, which involves comparing a moving feature window to a baseline reference window. Outlier-based sampling is tested with two classifiers (KNN and Logistic Regression) and achieves higher accuracy (∼2% increase) and fewer false positives (∼38% decrease), along with a lower latency (∼3 seconds shorter) compared to conventional training set pre-processing methods.


Assuntos
Epilepsia , Aprendizado de Máquina , Algoritmos , Eletroencefalografia , Epilepsia/diagnóstico , Humanos , Convulsões/diagnóstico
16.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 184-187, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33017960

RESUMO

Recent advances in deep learning have enabled the development of automated frameworks for analysing medical images and signals. For analysis of physiological recordings, models based on temporal convolutional networks and recurrent neural networks have demonstrated encouraging results and an ability to capture complex patterns and dependencies in the data. However, representations that capture the entirety of the raw signal are suboptimal as not all portions of the signal are equally important. As such, attention mechanisms are proposed to divert focus to regions of interest, reducing computational cost and enhancing accuracy. Here, we evaluate attention-based frameworks for the classification of physiological signals in different clinical domains. We evaluated our methodology on three classification scenarios: neurogenerative disorders, neurological status and seizure type. We demonstrate that attention networks can outperform traditional deep learning models for sequence modelling by identifying the most relevant attributes of an input signal for decision making. This work highlights the benefits of attention-based models for analysing raw data in the field of biomedical research.


Assuntos
Atenção , Redes Neurais de Computação , Bases de Dados Genéticas , Humanos , Convulsões
17.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 523-527, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018042

RESUMO

Electroencephalogram (EEG) has been intensively used as a diagnosis tool for epilepsy. The traditional diagnostic procedure relies on a recording of EEG from several days up to a few weeks, and the recordings are visually inspected by trained medical professionals. This procedure is time consuming with a high misdiagnosis rate. In recent years, computer-aided techniques have been proposed to automate the epilepsy diagnosis by using machine learning methods to analyze EEG data. Considering the time-varying nature of EEG, the goal of this work is to characterize dynamic changes of EEG patterns for the detection and classification of epilepsy. Four different dynamic Bayesian modeling methods were evaluated using multi-subject epileptic EEG data. Experimental results show that an accuracy of 98.0% can be achieved by one of the four methods. The same method also provides an overall accuracy of 87.7% for the classification of seven different seizure types.


Assuntos
Eletroencefalografia , Epilepsia , Teorema de Bayes , Epilepsia/diagnóstico , Humanos , Aprendizado de Máquina , Convulsões/diagnóstico
18.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 528-531, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018043

RESUMO

Current seizure detection systems rely on machine learning classifiers that are trained offline and subsequently require manual retraining to maintain high detection accuracy over long periods of time. For a true deploy-and-forget implantable seizure detection system, a low power, at-the-edge, online learning algorithm can be employed to dynamically adapt to the neural signal drifts over time. This work proposes SOUL: Stochastic-gradient-descent-based Online Unsupervised Logistic regression classifier, which provides continuous unsupervised online model updates that was initially trained with labels offline. SOUL was tested on two datasets, the CHB-MIT scalp EEG dataset, and a long (>250 hours) human ECoG dataset from the University of Melbourne. SOUL achieves an average cumulative sensitivity of 97.5% and 97.9% for the two datasets respectively, while maintaining <1.2 false alarms per day. When compared with state-of-the-art, a moderate sensitivity improvement of 1-3% is observed on the majority of subjects and a large sensitivity improvement of >12% is observed on three subjects with <1% impact on specificity.


Assuntos
Educação a Distância , Algoritmos , Eletroencefalografia , Humanos , Convulsões/diagnóstico , Sensibilidade e Especificidade
19.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 532-535, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018044

RESUMO

Absence seizures are expressed with distinctive spike-and-wave complexes in the electroencephalogram (EEG), which can be used to automatically distinguish them from other types of seizures and interictal activity. Considering the chaotic nature of the EEG signal, it is very unlikely that such continuous, repetitive patterns with strict periodic behavior would occur naturally under normal conditions. Searching for spectral activity in the range of 2.5-4.5 Hz and assessing the presence of synchronous, repeated patterns across multiple EEG channels in an unsupervised manner, the proposed methodology provides high absence seizure detection sensitivity of 93.94% with a low false detection rate of 0.168 FD/h using the open TUSZ dataset.


Assuntos
Epilepsia Tipo Ausência , Convulsões , Eletroencefalografia , Epilepsia Tipo Ausência/diagnóstico , Humanos , Convulsões/diagnóstico
20.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 536-540, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018045

RESUMO

Recent years have seen a growing interest in the development of non-invasive devices capable of detecting seizures which can be worn in everyday life. Such devices must be lightweight and unobtrusive which severely limit their on-board computing power and battery life. In this paper, we propose a novel technique based on hyperdimensional (HD) computing to detect epileptic seizures from 2-channel surface EEG recordings. The proposed technique eliminates the need for complicated feature extraction techniques required in conventional ML algorithms. The HD algorithm is also simple to implement and does not require expert knowledge for architectural optimizations needed for approaches based on neural networks. In addition, our proposed technique is light-weight and meets the computation and memory constraints of ultra-small devices. Experimental results on a publicly available dataset indicates our approach improves the accuracy compared to state-of-the-art techniques while consuming smaller or comparable power.


Assuntos
Eletroencefalografia , Epilepsia , Algoritmos , Epilepsia/diagnóstico , Humanos , Redes Neurais de Computação , Convulsões/diagnóstico
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA