Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 14.695
Filtrar
1.
J Neurosci Res ; 101(1): 20-33, 2023 Jan.
Artigo em Inglês | MEDLINE | ID: mdl-36148534

RESUMO

Sleep state transitions are closely related to insomnia, drowsiness, and sleep maintenance. However, how the cortical network varies during such a transition process remains unclear. Changes in the cortical interaction during the short-term process of sleep stage transitions were investigated. In all, 40 healthy young participants underwent overnight polysomnography. The phase transfer entropy of six frequency bands was obtained from 16 electroencephalography channels to assess the strength and direction of information flow between the cortical regions. Differences in the cortical network between the first and the last 10 s in a 40-s transition period across wakefulness, N1, N2, N3, and rapid eye movement were, respectively, studied. Various frequency bands exhibited different patterns during the sleep stage transitions. It was found that the mutual transitions between the sleep stages were not necessarily the opposite. More significant changes were observed in the sleep deepening process than in the process of sleep awakening. During sleep stage transitions, changes in the inflow and outflow strength of various cortical regions led to regional differences, but for the entire sleep progress, such an imbalance did not intensify, and a dynamic balance was instead observed. The detailed findings of variations in cortical interactions during sleep stage transition promote understanding of sleep mechanism, sleep process, and sleep function. Additionally, it is expected to provide helpful clues for sleep improvement, like reducing the time required to fall asleep and maintaining sleep depth.


Assuntos
Encéfalo , Sono , Humanos , Vigília , Fases do Sono , Eletroencefalografia
2.
Sleep Med ; 100: 573-576, 2022 Dec.
Artigo em Inglês | MEDLINE | ID: mdl-36327586

RESUMO

Previous research has shown an interplay between the thalamus and cerebral cortex during NREM sleep in humans, however the directionality of the thalamocortical synchronization is as yet unknown. In this study thalamocortical connectivity during different NREM sleep stages using sleep scalp electroencephalograms and local field potentials from the left and right anterior thalamus was measured in three epilepsy patients implanted with deep brain stimulation electrodes. Connectivity was assessed as debiased weighted phase lag index and granger causality between the thalamus and cortex for the NREM sleep stages N1, N2 and N3. Results showed connectivity was most prominently directed from cortex to thalamus. Moreover, connectivity varied in strength between the different sleep stages, but barely in direction or frequency. These results imply relatively stable thalamocortical connectivity during NREM sleep directed from the cortex to the thalamus.


Assuntos
Estimulação Encefálica Profunda , Humanos , Estimulação Encefálica Profunda/métodos , Fases do Sono/fisiologia , Eletroencefalografia/métodos , Tálamo , Córtex Cerebral/fisiologia , Sono/fisiologia
3.
Sensors (Basel) ; 22(22)2022 Nov 15.
Artigo em Inglês | MEDLINE | ID: mdl-36433422

RESUMO

The polysomnogram (PSG) is the gold standard for evaluating sleep quality and disorders. Attempts to automate this process have been hampered by the complexity of the PSG signals and heterogeneity among subjects and recording hardwares. Most of the existing methods for automatic sleep stage scoring rely on hand-engineered features that require prior knowledge of sleep analysis. This paper presents an end-to-end deep transfer learning framework for automatic feature extraction and sleep stage scoring based on a single-channel EEG. The proposed framework was evaluated over the three primary signals recommended by the American Academy of Sleep Medicine (C4-M1, F4-M1, O2-M1) from two data sets that have different properties and are recorded with different hardware. Different Time-Frequency (TF) imaging approaches were evaluated to generate TF representations for the 30 s EEG sleep epochs, eliminating the need for complex EEG signal pre-processing or manual feature extraction. Several training and detection scenarios were investigated using transfer learning of convolutional neural networks (CNN) and combined with recurrent neural networks. Generating TF images from continuous wavelet transform along with a deep transfer architecture composed of a pre-trained GoogLeNet CNN followed by a bidirectional long short-term memory (BiLSTM) network showed the best scoring performance among all tested scenarios. Using 20-fold cross-validation applied on the C4-M1 channel, the proposed framework achieved an average per-class accuracy of 91.2%, sensitivity of 77%, specificity of 94.1%, and precision of 75.9%. Our results demonstrate that without changing the model architecture and the training algorithm, our model could be applied to different single-channel EEGs from different data sets. Most importantly, the proposed system receives a single EEG epoch as an input at a time and produces a single corresponding output label, making it suitable for real time monitoring outside sleep labs as well as to help sleep lab specialists arrive at a more accurate diagnoses.


Assuntos
Eletroencefalografia , Fases do Sono , Humanos , Eletroencefalografia/métodos , Polissonografia/métodos , Sono , Aprendizado de Máquina
4.
J Neural Eng ; 19(6)2022 Nov 28.
Artigo em Inglês | MEDLINE | ID: mdl-36368035

RESUMO

Objective.The use of deep learning for electroencephalography (EEG) classification tasks has been rapidly growing in the last years, yet its application has been limited by the relatively small size of EEG datasets. Data augmentation, which consists in artificially increasing the size of the dataset during training, can be employed to alleviate this problem. While a few augmentation transformations for EEG data have been proposed in the literature, their positive impact on performance is often evaluated on a single dataset and compared to one or two competing augmentation methods. This work proposes to better validate the existing data augmentation approaches through a unified and exhaustive analysis.Approach.We compare quantitatively 13 different augmentations with two different predictive tasks, datasets and models, using three different types of experiments.Main results.We demonstrate that employing the adequate data augmentations can bring up to 45% accuracy improvements in low data regimes compared to the same model trained without any augmentation. Our experiments also show that there is no single best augmentation strategy, as the good augmentations differ on each task.Significance.Our results highlight the best data augmentations to consider for sleep stage classification and motor imagery brain-computer interfaces. More broadly, it demonstrates that EEG classification tasks benefit from adequate data augmentation.


Assuntos
Interfaces Cérebro-Computador , Eletroencefalografia , Eletroencefalografia/métodos , Imagens, Psicoterapia , Fases do Sono , Sono
5.
Sci Rep ; 12(1): 18409, 2022 Nov 01.
Artigo em Inglês | MEDLINE | ID: mdl-36319742

RESUMO

Unfolding the overnight dynamics in human sleep features plays a pivotal role in understanding sleep regulation. Studies revealed the complex reorganization of the frequency composition of sleep electroencephalogram (EEG) during the course of sleep, however the scale-free and the oscillatory measures remained undistinguished and improperly characterized before. By focusing on the first four non-rapid eye movement (NREM) periods of night sleep records of 251 healthy human subjects (4-69 years), here we reveal the flattening of spectral slopes and decrease in several measures of the spectral intercepts during consecutive sleep cycles. Slopes and intercepts are significant predictors of slow wave activity (SWA), the gold standard measure of sleep intensity. The overnight increase in spectral peak sizes (amplitudes relative to scale-free spectra) in the broad sigma range is paralleled by a U-shaped time course of peak frequencies in frontopolar regions. Although, the set of spectral indices analyzed herein reproduce known age- and sex-effects, the interindividual variability in spectral slope steepness is lower as compared to the variability in SWA. Findings indicate that distinct scale-free and oscillatory measures of sleep EEG could provide composite measures of sleep dynamics with low redundancy, potentially affording new insights into sleep regulatory processes in future studies.


Assuntos
Eletroencefalografia , Sono de Ondas Lentas , Humanos , Sono/fisiologia , Fases do Sono/fisiologia
6.
Int J Mol Sci ; 23(19)2022 Oct 04.
Artigo em Inglês | MEDLINE | ID: mdl-36233081

RESUMO

This work aimed to study the recovery of consciousness during forced awakening from slow-wave sleep (SWS) and rapid eye movement sleep (REM) in healthy volunteers. To track the changes in the degree of awareness of the stimuli during the transition to wakefulness, event-related potentials (ERPs) and motor responses (MR) in the auditory local-global paradigm were analyzed. The results show that during awakening from both SWS and REM, first, alpha-activity restores in the EEG, and only 20 and 25 s (for REM and SWS awakenings, respectively) after alpha onset MR to target stimuli recovers. During REM awakening, alpha-rhythm, MR, and conscious awareness of stimuli recover faster than during SWS awakening. Moreover, pre-attentive processing of local irregularities emerges earlier, even before alpha-rhythm onset, while during SWS awakening, the local effect we registered only after alpha restoration. The P300-like response both on global and local irregularities was found only when accurate MR was restored. Thus, the appearance in EEG predominating alpha-activity is insufficient either for conscious awareness of external stimuli or for generating MR to them. This work may help to understand the pathophysiology of sleep disorders well as conditions characterized by the dissociation between behavior and various aspects of consciousness.


Assuntos
Sono REM , Sono de Ondas Lentas , Estado de Consciência , Eletroencefalografia , Potenciais Evocados , Humanos , Sono/fisiologia , Fases do Sono/fisiologia , Vigília/fisiologia
7.
Sleep Med ; 100: 364-377, 2022 Dec.
Artigo em Inglês | MEDLINE | ID: mdl-36201888

RESUMO

OBJECTIVE/BACKGROUND: Slow wave activity (SWA) and sigma frequency activity (SFA) are hallmarks of NREM sleep EEG and important indicators of neural plasticity, development of the central nervous system, and cognition. However, little is known about the factors that modulate these sleep EEG activities, especially in small children. PATIENTS/METHODS: We analyzed the power spectral densities of SWA (1-4 Hz) and SFA range (10-15 Hz) from six EEG derivations of 56 infants (8 months) and 60 toddlers (24 months) during their all-night sleep and during the first and the last half of night sleep. The spectral values were compared between the four seasons. RESULTS: In the spring group of infants, compared with the darker seasons, SFA was lower in the centro-occipital EEG derivations during both halves of the night. The SWA findings of the infants were restricted to the last half of the night (SWA2) and frontally, where SWA2 was higher during winter than spring. The toddlers presented less frontal SWA2 during winter compared with autumn. Both age groups showed a reduction in both SWA and SFA towards the last half of the night. CONCLUSIONS: The sleep EEG spectral power densities are more often associated with seasons in infants' SFA range. The results might stem from seasonally changing light exposure, but the exact mechanism warrants further study. Moreover, contrary to the adult-like increment of SFA, the SFA at both ages was lower at the last part of the night sleep. This suggests different regulation of spindle activity in infants and toddlers.


Assuntos
Sono de Ondas Lentas , Sono , Adulto , Lactente , Pré-Escolar , Humanos , Estações do Ano , Sono/fisiologia , Eletroencefalografia/métodos , Fases do Sono/fisiologia
8.
Sleep Med ; 100: 390-403, 2022 Dec.
Artigo em Inglês | MEDLINE | ID: mdl-36206600

RESUMO

Classifying sleep stages in real-time represents considerable potential, for instance in enabling interactive noise masking in noisy environments when persons are in a state of light sleep or to support clinical staff in analyzing sleep patterns etc. However, the current gold standard for classifying sleep stages, Polysomnography (PSG), is too cumbersome to apply outside controlled hospital settings and requires manual as well as highly specialized knowledge to classify sleep stages. Using data from Consumer Sleep Technologies (CSTs) to inform machine learning algorithms represent a promising opportunity for automating the process of classifying sleep stages, also in settings outside the confinements of clinical expert settings. This study reviews 27 papers that use CSTs in combination with Artificial Intelligence (AI) models to classify sleep stages. AI models and their performance are described and compared to synthesize current state of the art in sleep stage classification with CSTs. Furthermore, gaps in the current approaches are shown and how these AI models could be improved in the near-future. Lastly, the challenges of designing interactions for users that are asleep are highlighted pointing towards avenues of more interactive sleep interventions based on AI-infused CSTs solutions.


Assuntos
Inteligência Artificial , Sono , Humanos , Polissonografia , Fases do Sono , Algoritmos
9.
Sleep Med ; 100: 419-426, 2022 Dec.
Artigo em Inglês | MEDLINE | ID: mdl-36244316

RESUMO

INTRODUCTION: Temporal lobe epilepsy due to hippocampal sclerosis (TLE-HS) is one of the most common drug-resistant epilepsy. Surgery is currently accepted as an effective and safe therapeutic approach compared to antiseizure medications (ASMs). The study aims to evaluate the effect of surgical treatment of TLE-HS on sleep profile and architecture by subjective and objective evaluation of sleep in basal condition after one month and one year. METHODS: Thirteen patients with TLE-HS were recruited to undergo overnight polysomnography and a subjective evaluation of nocturnal sleep utilizing the Pittsburgh Sleep Quality Index (PSQI) and daytime somnolence through the Epworth Sleepiness Scale (ESS) in basal condition (T0), one month (T1) and one year after surgery (T2), respectively. Thirteen healthy controls (HC) matched for age, sex and BMI were recruited. Scoring and analysis of sleep macrostructure and cyclic alternating pattern (CAP) parameters were performed. RESULTS: The comparison between patients in basal condition (T0) and HC showed a significant lower sleep efficiency (p = 0.003) and REM percentage (p < 0.001). Regarding CAP, patients at T0 showed higher total CAP rate (p < 0.001), CAP rate in N2 (p < 0.001), higher A3 (%) (p = 0.001), higher mean duration of A1 (p = 0.002), A3 index (p < 0.001), cycle in sequences (p < 0.001), lower B duration (p < 0.001), cycle mean duration (p < 0.001) than HC. Surgery did not induce significant changes in nocturnal macrostructural polysomnographic variables in T1 and T2. Lower CAP rate (T1 vs T0 and T2 vs T0 p < 0.001), CAP rate in N3 (T1 vs T0 and T2 vs T0 p < 0.001), A3 (%) (T1 vs T0 and T2 vs T0 p < 0.001); lower phase A2 index (T1 vs T0 p < 0.001) and A3 index (T1 vs T0 p < 0.001), lower phase A1 index (T2 vs T0 p < 0.001) and cycle in sequences (T2 vs T0 p = 0.002) higher B mean duration (T2 vs T0 p = 0.002). No significant differences were found between T1 and T2 in CAP parameters. CONCLUSION: We found a significant NREM sleep instability in patients with TLE-HS compared with HC. In addition, anterior temporal lobectomy (ATL) induced a significant improvement in sleep continuity as evaluated by cyclic alternating pattern already one month later and this effect persisted after one year. ALT seems to restore a more resilient sleeping brain.


Assuntos
Epilepsia do Lobo Temporal , Fases do Sono , Humanos , Estudos Prospectivos , Esclerose/cirurgia , Eletroencefalografia , Sono , Epilepsia do Lobo Temporal/cirurgia , Atrofia , Hipocampo/cirurgia
10.
Adv Exp Med Biol ; 1384: 107-130, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-36217081

RESUMO

Conventionally, sleep and associated events are scored visually by trained technologists according to the rules summarized in the American Academy of Sleep Medicine Manual. Since its first publication in 2007, the manual was continuously updated; the most recent version as of this writing was published in 2020. Human expert scoring is considered as gold standard, even though there is increasing evidence of limited interrater reliability between human scorers. Significant advances in machine learning have resulted in powerful methods for addressing complex classification problems such as automated scoring of sleep and associated events. Evidence is increasing that these autoscoring systems deliver performance comparable to manual scoring and offer several advantages to visual scoring: (1) avoidance of the rather expensive, time-consuming, and difficult visual scoring task that can be performed only by well-trained and experienced human scorers, (2) attainment of consistent scoring results, and (3) proposition of added value such as scoring in real time, sleep stage probabilities per epoch (hypnodensity), estimates of signal quality and sleep/wake-related features, identifications of periods with clinically relevant ambiguities (confidence trends), configurable sensitivity and rule settings, as well as cardiorespiratory sleep staging for home sleep apnea testing. This chapter describes the development of autoscoring systems since the first attempts in the 1970s up to the most recent solutions based on deep neural network approaches which achieve an accuracy that allows to use the autoscoring results directly for review and interpretation by a physician.


Assuntos
Síndromes da Apneia do Sono , Fases do Sono , Humanos , Redes Neurais de Computação , Reprodutibilidade dos Testes , Sono , Síndromes da Apneia do Sono/diagnóstico , Estados Unidos
11.
Adv Exp Med Biol ; 1384: 17-29, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-36217076

RESUMO

A growing number of studies have shown the strong relationship between sleep and different cognitive processes, especially those that involve memory consolidation. Traditionally, these processes were attributed to mechanisms related to the macroarchitecture of sleep, as sleep cycles or the duration of specific stages, such as the REM stage. More recently, the relationship between different cognitive traits and specific waves (sleep spindles or slow oscillations) has been studied. We here present the most important physiological processes induced by sleep, with particular focus on brain electrophysiology. In addition, recent and classical literature were reviewed to cover the gap between sleep and cognition, while illustrating this relationship by means of clinical examples. Finally, we propose that future studies may focus not only on analyzing specific waves, but also on the relationship between their characteristics as potential biomarkers for multiple diseases.


Assuntos
Eletroencefalografia , Consolidação da Memória , Encéfalo/fisiologia , Cognição , Consolidação da Memória/fisiologia , Sono/fisiologia , Fases do Sono/fisiologia
12.
Comput Intell Neurosci ; 2022: 6104736, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-36188714

RESUMO

Sleep stage classification is essential in diagnosing and treating sleep disorders. Many deep learning models have been proposed to classify sleep stages by automatic learning features and temporal context information. These temporal context features come from the intra-epoch temporal features, which represent the overall morphology of an epoch, and temporal features of adjacent epochs and long epochs, which represent the influence between epochs. However, most existing methods do not fully use the complementarity of the three-level temporal features, resulting in incomplete extracted temporal features. To solve this problem, we propose a multilevel temporal context network (MLTCN) to learn the temporal features from intra-epoch, adjacent epochs, and long epochs, which utilizes the complete temporal features to improve classification accuracy. We evaluate the performance of the proposed model on the Sleep-EDF datasets published in 2013 and 2018. The experimental results show that our MLTCN can achieve an overall accuracy of 84.2% and a kappa coefficient of 0.78 on the Sleep-EDF-2013 dataset. On the larger Sleep-EDF-2018 dataset, the overall accuracy is 81.0%, and a kappa coefficient is 0.74. Our model can better assist sleep experts in diagnosing sleep disorders.


Assuntos
Eletroencefalografia , Transtornos do Sono-Vigília , Humanos , Polissonografia , Sono , Fases do Sono
13.
Artigo em Inglês | MEDLINE | ID: mdl-36293844

RESUMO

An automated sleep stage categorization can readily face noise-contaminated EEG recordings, just as other signal processing applications. Therefore, the denoising of the contaminated signals is inevitable to ensure a reliable analysis of the EEG signals. In this research work, an empirical mode decomposition is used in combination with stacked autoencoders to conduct automatic sleep stage classification with reliable analytical performance. Due to the decomposition of the composite signal into several intrinsic mode functions, empirical mode decomposition offers an effective solution for denoising non-stationary signals such as EEG. Preliminary results showed that through these intrinsic modes, a signal with a high signal-to-noise ratio can be obtained, which can be used for further analysis with confidence. Therefore, later, when statistical features were extracted from the denoised signals and were classified using stacked autoencoders, improved results were obtained for Stage 1, Stage 2, Stage 3, Stage 4, and REM stage EEG signals using this combination.


Assuntos
Inteligência Artificial , Eletroencefalografia , Eletroencefalografia/métodos , Processamento de Sinais Assistido por Computador , Fases do Sono , Sono , Algoritmos
14.
Artigo em Inglês | MEDLINE | ID: mdl-36223360

RESUMO

Sleep data are typically characterized by class imbalance, which can cause the model to be overly biased toward frequent classes, resulting in low accuracy of minority class classification. However, the minority class of sleep staging has important value in diagnosing certain disorders, such as an N1 Stage that is too short indicating possible hypersomnia or narcolepsy. To address this problem, we propose a multi-view CNN model based on adaptive margin-aware loss. A novel margin-aware factor that considers the relative sample sizes of both frequent and minority classes can improve the overfitting of minority classes by increasing the regularization strength of minority classes without changing the sample size to maximize the decision margins of minority classes. On this basis, we propose margin-aware cross-entropy and margin-aware complement entropy loss, respectively. Margin-aware complement entropy can be achieved to increase the regularization for minority classes while neutralizing errors for minority classes, thus improving the classification accuracy for minority classes. Finally, the synergy of margin-aware complement entropy and cross-entropy is realized in an adaptive way to improve the sleep staging classification accuracy. We tested on three sleep datasets and compared them with the state-of-the-art, and the results demonstrate that our proposed algorithm not only improves the accuracy of sleep staging in general, but also improves the minority classes to a greater extent.


Assuntos
Eletroencefalografia , Fases do Sono , Humanos , Entropia , Eletroencefalografia/métodos , Algoritmos , Sono
15.
Comput Biol Med ; 149: 106044, 2022 10.
Artigo em Inglês | MEDLINE | ID: mdl-36084381

RESUMO

Automatic sleep stage classification is an effective technology compared to conventional artificial visual inspection in the field of sleep staging. Numerous algorithms based on machine learning and deep learning on single-channel electroencephalogram (EEG) have been proposed in recent years, however, category imbalance and cross-subject discrepancy are still the main factors restricting the accuracy of existing methods. This study proposed an innovative end-to-end neural network to solve these problems, specifically, four data augmentation methods were designed to eliminate category imbalance, and domain adaptation modules were designed for the alignment of marginal distribution, conditional distribution, and channel and spatial level distribution of feature maps, as well as the capture of transferable regions on the feature maps using a transfer attention mechanism. We conducted experiments on two publicly available datasets (Sleep-EDF Database Expanded, 2013 and 2018 version), Cohen's kappa coefficient (k) of 0.77 (Fpz-Cz) and 0.73 (Pz-Oz) were realized on the Sleep-EDF-2013 dataset, and a k of 0.75 (Fpz-Cz) and 0.68 (Pz-Oz) were realized on the Sleep-EDF-2018 dataset. An experiment was also conducted on the dataset drawn from the 2018 Physionet challenge, which containing people with sleep disorders, and a performance improvement was still found. Our comparative experiments with similar studies showed that our model was superior to most other studies, indicating our proposed EEG data augmentation and domain adaptation based cross-subject discrepancy alleviation approach is effective to improve the performance of automatic sleep staging.


Assuntos
Eletroencefalografia , Fases do Sono , Eletroencefalografia/métodos , Humanos , Aprendizado de Máquina , Redes Neurais de Computação , Sono
16.
Annu Int Conf IEEE Eng Med Biol Soc ; 2022: 1643-1646, 2022 07.
Artigo em Inglês | MEDLINE | ID: mdl-36086296

RESUMO

Recent years have shown a growth in the application of deep learning architectures such as convolutional neural networks (CNNs), to electrophysiology analysis. However, using neural networks with raw time-series data makes explainability a significant challenge. Multiple explainability approaches have been developed for insight into the spectral features learned by CNNs from EEG. However, across electrophysiology modalities, and even within EEG, there are many unique waveforms of clinical relevance. Existing methods that provide insight into waveforms learned by CNNs are of questionable utility. In this study, we present a novel model visualization-based approach that analyzes the filters in the first convolutional layer of the network. To our knowledge, this is the first method focused on extracting explainable information from EEG waveforms learned by CNNs while also providing insight into the learned spectral features. We demonstrate the viability of our approach within the context of automated sleep stage classification, a well-characterized domain that can help validate our approach. We identify 3 subgroups of filters with distinct spectral properties, determine the relative importance of each group of filters, and identify several unique waveforms learned by the classifier that were vital to the classifier performance. Our approach represents a significant step forward in explainability for electrophysiology classifiers, which we also hope will be useful for providing insights in future studies. Clinical Relevance- Our approach can assist with the development and validation of clinical time-series classifiers.


Assuntos
Redes Neurais de Computação , Fases do Sono , Sono
17.
Annu Int Conf IEEE Eng Med Biol Soc ; 2022: 4453-4456, 2022 07.
Artigo em Inglês | MEDLINE | ID: mdl-36086600

RESUMO

Recently there has seen promising results on auto-matic stage scoring by extracting spatio-temporal features from electroencephalogram (EEG). Such methods entail laborious manual feature engineering and domain knowledge. In this study, we propose an adaptive scheme to probabilistically encode, filter and accumulate the input signals and weight the resultant features by the half-Gaussian probabilities of signal intensities. The adaptive representations are subsequently fed into a transformer model to automatically mine the relevance between features and corresponding stages. Extensive exper-iments on the largest public dataset against state-of-the-art methods validate the effectiveness of our proposed method and reveal promising future directions.


Assuntos
Eletroencefalografia , Fases do Sono , Eletroencefalografia/métodos , Distribuição Normal , Probabilidade , Projetos de Pesquisa
18.
PLoS One ; 17(9): e0275530, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-36174095

RESUMO

STUDY OBJECTIVES: To investigate inter-scorer agreement and scoring time differences associated with visual and computer-assisted analysis of polysomnographic (PSG) recordings. METHODS: A group of 12 expert scorers reviewed 5 PSGs that were independently selected in the context of each of the following tasks: (i) sleep staging, (ii) scoring of leg movements, (iii) detection of respiratory (apneic-related) events, and (iv) of electroencephalographic (EEG) arousals. All scorers independently reviewed the same recordings, hence resulting in 20 scoring exercises per scorer from an equal amount of different subjects. The procedure was repeated, separately, using the classical visual manual approach and a computer-assisted (semi-automatic) procedure. Resulting inter-scorer agreement and scoring times were examined and compared among the two methods. RESULTS: Computer-assisted sleep scoring showed a consistent and statistically relevant effect toward less time required for the completion of each of the PSG scoring tasks. Gain factors ranged from 1.26 (EEG arousals) to 2.41 (leg movements). Inter-scorer kappa agreement was also consistently increased with the use of supervised semi-automatic scoring. Specifically, agreement increased from Κ = 0.76 to K = 0.80 (sleep stages), Κ = 0.72 to K = 0.91 (leg movements), Κ = 0.55 to K = 0.66 (respiratory events), and Κ = 0.58 to Κ = 0.65 (EEG arousals). Inter-scorer agreement on the examined set of diagnostic indices did also show a trend toward higher Interclass Correlation Coefficient scores when using the semi-automatic scoring approach. CONCLUSIONS: Computer-assisted analysis can improve inter-scorer agreement and scoring times associated with the review of PSG studies resulting in higher efficiency and overall quality in the diagnosis sleep disorders.


Assuntos
Nível de Alerta , Fases do Sono , Computadores , Eletroencefalografia , Humanos , Polissonografia
19.
Biomed Eng Online ; 21(1): 66, 2022 Sep 12.
Artigo em Inglês | MEDLINE | ID: mdl-36096868

RESUMO

BACKGROUND: Obtaining medical data using wearable sensors is a potential replacement for in-hospital monitoring, but the lack of data for such sensors poses a challenge for development. One solution is using in-hospital recordings to boost performance via transfer learning. While there are many possible transfer learning algorithms, few have been tested in the domain of EEG-based sleep staging. Furthermore, there are few ways for determining which transfer learning method will work best besides exhaustive testing. Measures of transferability do exist, but are typically used for selection of pre-trained models rather than algorithms and few have been tested on medical signals. We tested several supervised transfer learning algorithms on a sleep staging task using a single channel of EEG (AF7-Fpz) captured from an in-home commercial system. RESULTS: Two neural networks-one bespoke and another state-of-art open-source architecture-were pre-trained on one of six source datasets comprising 11,561 subjects undergoing clinical polysomnograms (PSGs), then re-trained on a target dataset of 75 full-night recordings from 24 subjects. Several transferability measures were then tested to determine which is most effective for assessing performance on unseen target data. Performance on the target dataset was improved using transfer learning, with re-training the head layers being the most effective in the majority of cases (up to 63.9% of cases). Transferability measures generally provided significant correlations with accuracy (up to [Formula: see text]). CONCLUSION: Re-training the head layers provided the largest performance boost. Transferability measures are useful indicators of transfer learning effectiveness.


Assuntos
Fases do Sono , Dispositivos Eletrônicos Vestíveis , Algoritmos , Humanos , Aprendizado de Máquina , Redes Neurais de Computação
20.
PLoS One ; 17(9): e0268720, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-36178910

RESUMO

OBJECTIVE: Alternating Hemiplegia of Childhood (AHC) is characterised by paroxysmal hemiplegic episodes and seizures. Remission of hemiplegia upon sleep is a clinical diagnostic feature of AHC. We investigated whether: 1) Hemiplegic events are associated with spectral EEG changes 2) Sleep in AHC is associated with clinical or EEG spectral features that may explain its restorative effect. METHODS: We retrospectively performed EEG spectral analysis in five adults with AHC and twelve age-/gender-matched epilepsy controls. Five-minute epochs of hemiplegic episodes and ten-minute epochs of four sleep stages were selected from video-EEGs. Arousals were counted per hour of sleep. RESULTS: We found 1) hemispheric differences in pre-ictal and ictal spectral power (p = 0.034), during AHC hemiplegic episodes 2) 22% reduced beta power (p = 0.017) and 26% increased delta power (p = 0.025) during wakefulness in AHC versus controls. There were 98% more arousals in the AHC group versus controls (p = 0.0003). CONCLUSIONS: There are hemispheric differences in spectral power preceding hemiplegic episodes in adults with AHC, and sleep is disrupted. SIGNIFICANCE: Spectral EEG changes may be a potential predictive tool for AHC hemiplegic episodes. Significantly disrupted sleep is a feature of AHC.


Assuntos
Eletroencefalografia , Hemiplegia , Adulto , Hemiplegia/complicações , Humanos , Estudos Retrospectivos , Fases do Sono , ATPase Trocadora de Sódio-Potássio
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA
...