Yield of intermittent versus continuous EEG in comatose survivors of cardiac arrest treated with hypothermia.

INTRODUCTION: Electroencephalography (EEG) has a central role in the outcome prognostication in subjects with anoxic/hypoxic encephalopathy following a cardiac arrest (CA). Continuous EEG monitoring (cEEG) has been consistently developed and studied; however, its yield as compared to repeated standard EEG (sEEG) is unknown. METHODS: We studied a prospective cohort of comatose adults treated with therapeutic hypothermia (TH) after a CA. cEEG data regarding background activity and epileptiform components were compared to two 20 minute sEEG extracted from the cEEG recording (one during TH, and one in early normothermia). RESULTS: In this cohort, 34 recordings were studied. During TH, the agreement between cEEG and sEEG was 97.1% (95% CI: 84.6 - 99.9%) for background discontinuity and reactivity evaluation, while it was 94.1% (95% CI 80.3 - 99.2%) regarding epileptiform activity. In early normothermia, we did not find any discrepancies. Thus, concordance was very good during TH (kappa 0.83), and optimal during normothermia (kappa=1). The median delay between CA and the first EEG reactivity testing was 18 hours (range: 4.75 - 25) for patients with perfect agreement and 10 hours (range: 5.75 - 10.5) for the three patients in whom there were discordant findings (P=0.02, Wilcoxon). CONCLUSION: Standard intermittent EEG has comparable performance than continuous EEG both for variables important for outcome prognostication (EEG reactivity) and identification of epileptiform transients in this relatively small sample of comatose survivors of CA. This finding has an important practical implication, especially for centers where EEG resources are limited.

Analysis, modelling and classification of geospatial data using machine learning

The research considers the problem of spatial data classification using machine learning algorithms: probabilistic neural networks (PNN) and support vector machines (SVM). As a benchmark model simple k-nearest neighbor algorithm is considered. PNN is a neural network reformulation of well known nonparametric principles of probability density modeling using kernel density estimator and Bayesian optimal or maximum a posteriori decision rules. PNN is well suited to problems where not only predictions but also quantification of accuracy and integration of prior information are necessary. An important property of PNN is that they can be easily used in decision support systems dealing with problems of automatic classification. Support vector machine is an implementation of the principles of statistical learning theory for the classification tasks. Recently they were successfully applied for different environmental topics: classification of soil types and hydro-geological units, optimization of monitoring networks, susceptibility mapping of natural hazards. In the present paper both simulated and real data case studies (low and high dimensional) are considered. The main attention is paid to the detection and learning of spatial patterns by the algorithms applied.

Synchronizability of EEG-Based Functional Networks in Early Alzheimer's Disease.

Recently graph theory and complex networks have been widely used as a mean to model functionality of the brain. Among different neuroimaging techniques available for constructing the brain functional networks, electroencephalography (EEG) with its high temporal resolution is a useful instrument of the analysis of functional interdependencies between different brain regions. Alzheimer's disease (AD) is a neurodegenerative disease, which leads to substantial cognitive decline, and eventually, dementia in aged people. To achieve a deeper insight into the behavior of functional cerebral networks in AD, here we study their synchronizability in 17 newly diagnosed AD patients compared to 17 healthy control subjects at no-task, eyes-closed condition. The cross-correlation of artifact-free EEGs was used to construct brain functional networks. The extracted networks were then tested for their synchronization properties by calculating the eigenratio of the Laplacian matrix of the connection graph, i.e., the largest eigenvalue divided by the second smallest one. In AD patients, we found an increase in the eigenratio, i.e., a decrease in the synchronizability of brain networks across delta, alpha, beta, and gamma EEG frequencies within the wide range of network costs. The finding indicates the destruction of functional brain networks in early AD.

Prognostic value of continuous eeg monitoring during therapeutic hypothermia in patients with coma after cardiac arrest

INTRODUCTION: Continuous EEG (cEEG) is increasingly used to monitor brain function in neuro-ICU patients. However, its value in patients with coma after cardiac arrest (CA), particularly in the setting of therapeutic hypothermia (TH), is only beginning to be elucidated. The aim of this study was to examine whether cEEG performed during TH may predict outcome. METHODS: From April 2009 to April 2010, we prospectively studied 34 consecutive comatose patients treated with TH after CA who were monitored with cEEG, initiated during hypothermia and maintained after rewarming. EEG background reactivity to painful stimulation was tested. We analyzed the association between cEEG findings and neurologic outcome, assessed at 2 months with the Glasgow-Pittsburgh Cerebral Performance Categories (CPC). RESULTS: Continuous EEG recording was started 12 ± 6 hours after CA and lasted 30 ± 11 hours. Nonreactive cEEG background (12 of 15 (75%) among nonsurvivors versus none of 19 (0) survivors; P < 0.001) and prolonged discontinuous "burst-suppression" activity (11 of 15 (73%) versus none of 19; P < 0.001) were significantly associated with mortality. EEG seizures with absent background reactivity also differed significantly (seven of 15 (47%) versus none of 12 (0); P = 0.001). In patients with nonreactive background or seizures/epileptiform discharges on cEEG, no improvement was seen after TH. Nonreactive cEEG background during TH had a positive predictive value of 100% (95% confidence interval (CI), 74 to 100%) and a false-positive rate of 0 (95% CI, 0 to 18%) for mortality. All survivors had cEEG background reactivity, and the majority of them (14 (74%) of 19) had a favorable outcome (CPC 1 or 2). CONCLUSIONS: Continuous EEG monitoring showing a nonreactive or discontinuous background during TH is strongly associated with unfavorable outcome in patients with coma after CA. These data warrant larger studies to confirm the value of continuous EEG monitoring in predicting prognosis after CA and TH.

Evolution of source EEG synchronization in early Alzheimer's disease.

Alzheimer's disease (AD) disrupts functional connectivity in distributed cortical networks. We analyzed changes in the S-estimator, a measure of multivariate intraregional synchronization, in electroencephalogram (EEG) source space in 15 mild AD patients versus 15 age-matched controls to evaluate its potential as a marker of AD progression. All participants underwent 2 clinical evaluations and 2 EEG recording sessions on diagnosis and after a year. The main effect of AD was hyposynchronization in the medial temporal and frontal regions and relative hypersynchronization in posterior cingulate, precuneus, cuneus, and parietotemporal cortices. However, the S-estimator did not change over time in either group. This result motivated an analysis of rapidly progressing AD versus slow-progressing patients. Rapidly progressing AD patients showed a significant reduction in synchronization with time, manifest in left frontotemporal cortex. Thus, the evolution of source EEG synchronization over time is correlated with the rate of disease progression and should be considered as a cost-effective AD biomarker.

Attention-related potentials allow for a highly accurate discrimination of mild cognitive impairment subtypes.

The three most frequent forms of mild cognitive impairment (MCI) are single-domain amnestic MCI (sd-aMCI), single-domain dysexecutive MCI (sd-dMCI) and multiple-domain amnestic MCI (md-aMCI). Brain imaging differences among single domain subgroups of MCI were recently reported supporting the idea that electroencephalography (EEG) functional hallmarks can be used to differentiate these subgroups. We performed event-related potential (ERP) measures and independent component analysis in 18 sd-aMCI, 13 sd-dMCI and 35 md-aMCI cases during the successful performance of the Attentional Network Test. Sensitivity and specificity analyses of ERP for the discrimination of MCI subgroups were also made. In center-cue and spatial-cue warning stimuli, contingent negative variation (CNV) was elicited in all MCI subgroups. Two independent components (ICA1 and 2) were superimposed in the time range on the CNV. The ICA2 was strongly reduced in sd-dMCI compared to sd-aMCI and md-aMCI (4.3 vs. 7.5% and 10.9% of the CNV component). The parietal P300 ERP latency increased significantly in sd-dMCI compared to md-aMCI and sd-aMCI for both congruent and incongruent conditions. This latency for incongruent targets allowed for a highly accurate separation of sd-dMCI from both sd-aMCI and md-aMCI with correct classification rates of 90 and 81%, respectively. This EEG parameter alone performed much better than neuropsychological testing in distinguishing sd-dMCI from md-aMCI. Our data reveal qualitative changes in the composition of the neural generators of CNV in sd-dMCI. In addition, they document an increased latency of the executive P300 component that may represent a highly accurate hallmark for the discrimination of this MCI subgroup in routine clinical settings.

Seizure semiology: an overview of the 'inverse problem'.

In clinical practice, a classification of seizures based on clinical signs and symptoms leads to an improved understanding of epilepsy-related issues and therefore strongly contributes to a better patient care. The inverse problem involves inferring the anatomical brain localization of a seizure from the scalp surface EEG, a concept we apply here to correlate seizure origin with seizure semiology. The spheres of sensorium, motor features, consciousness changes and autonomic alterations during ictal and postictal manifestations are reviewed, including several subdivisions used to better categorize particular features. Particular attention is given to behavioral features, as well as to features occurring in idiopathic generalized epileptic syndromes and psychogenic nonepileptic spells.

Asymmetric POSTS associated with unilateral EEG abnormalities.

OBJECTIVE: Positive occipital sharp transient of the sleep (POSTS) are considered a normal variant of non-REM sleep EEG. We describe a small series of patients with asymmetric POSTS and ipsilateral abnormal EEG findings. METHODS: Over a period of 30 weeks, we prospectively observed five consecutive subjects with strictly unilateral POSTS associated with ispilateral electrographic abnormalities. They represent 0.4% of all EEG performed over the same time lapse (5/1130), including inpatients, outpatients and long-term monitoring. RESULTS: Four women and one boy suffering from epileptic seizures (aged 7-76 years old) had unilateral POSTS, occurring only on the right side, during light sleep. They also presented ipsilateral epileptiform abnormalities. CONCLUSION: The fact that POSTS were asymmetric and found only on the same side as the abnormalities raises the question whether these transients should still be considered physiological or could be interpreted at times as markers of underlying electrical abnormalities, pointing to an increased cortical excitability on the more active side. Although larger samples are needed to confirm our preliminary results, this case study questions the interpretation of POSTS as a uniformly normal variant.

Automatic Mapping and Classification of Spatial Environmental Data

The paper deals with the development and application of the generic methodology for automatic processing (mapping and classification) of environmental data. General Regression Neural Network (GRNN) is considered in detail and is proposed as an efficient tool to solve the problem of spatial data mapping (regression). The Probabilistic Neural Network (PNN) is considered as an automatic tool for spatial classifications. The automatic tuning of isotropic and anisotropic GRNN/PNN models using cross-validation procedure is presented. Results are compared with the k-Nearest-Neighbours (k-NN) interpolation algorithm using independent validation data set. Real case studies are based on decision-oriented mapping and classification of radioactively contaminated territories.

A colorectal cancer classification system that associates cellular phenotype and responses to therapy.

Colorectal cancer (CRC) is a major cause of cancer mortality. Whereas some patients respond well to therapy, others do not, and thus more precise, individualized treatment strategies are needed. To that end, we analyzed gene expression profiles from 1,290 CRC tumors using consensus-based unsupervised clustering. The resultant clusters were then associated with therapeutic response data to the epidermal growth factor receptor-targeted drug cetuximab in 80 patients. The results of these studies define six clinically relevant CRC subtypes. Each subtype shares similarities to distinct cell types within the normal colon crypt and shows differing degrees of 'stemness' and Wnt signaling. Subtype-specific gene signatures are proposed to identify these subtypes. Three subtypes have markedly better disease-free survival (DFS) after surgical resection, suggesting these patients might be spared from the adverse effects of chemotherapy when they have localized disease. One of these three subtypes, identified by filamin A expression, does not respond to cetuximab but may respond to cMET receptor tyrosine kinase inhibitors in the metastatic setting. Two other subtypes, with poor and intermediate DFS, associate with improved response to the chemotherapy regimen FOLFIRI in adjuvant or metastatic settings. Development of clinically deployable assays for these subtypes and of subtype-specific therapies may contribute to more effective management of this challenging disease.

Glutathione precursor N-acetyl-cysteine modulates EEG synchronization in schizophrenia patients: a double-blind, randomized, placebo-controlled trial.

Glutathione (GSH) dysregulation at the gene, protein, and functional levels has been observed in schizophrenia patients. Together with disease-like anomalies in GSH deficit experimental models, it suggests that such redox dysregulation can play a critical role in altering neural connectivity and synchronization, and thus possibly causing schizophrenia symptoms. To determine whether increased GSH levels would modulate EEG synchronization, N-acetyl-cysteine (NAC), a glutathione precursor, was administered to patients in a randomized, double-blind, crossover protocol for 60 days, followed by placebo for another 60 days (or vice versa). We analyzed whole-head topography of the multivariate phase synchronization (MPS) for 128-channel resting-state EEGs that were recorded at the onset, at the point of crossover, and at the end of the protocol. In this proof of concept study, the treatment with NAC significantly increased MPS compared to placebo over the left parieto-temporal, the right temporal, and the bilateral prefrontal regions. These changes were robust both at the group and at the individual level. Although MPS increase was observed in the absence of clinical improvement at a group level, it correlated with individual change estimated by Liddle's disorganization scale. Therefore, significant changes in EEG synchronization induced by NAC administration may precede clinically detectable improvement, highlighting its possible utility as a biomarker of treatment efficacy. TRIAL REGISTRATION: ClinicalTrials.gov NCT01506765.

Adaptive tracking of EEG oscillations.

Neuronal oscillations are an important aspect of EEG recordings. These oscillations are supposed to be involved in several cognitive mechanisms. For instance, oscillatory activity is considered a key component for the top-down control of perception. However, measuring this activity and its influence requires precise extraction of frequency components. This processing is not straightforward. Particularly, difficulties with extracting oscillations arise due to their time-varying characteristics. Moreover, when phase information is needed, it is of the utmost importance to extract narrow-band signals. This paper presents a novel method using adaptive filters for tracking and extracting these time-varying oscillations. This scheme is designed to maximize the oscillatory behavior at the output of the adaptive filter. It is then capable of tracking an oscillation and describing its temporal evolution even during low amplitude time segments. Moreover, this method can be extended in order to track several oscillations simultaneously and to use multiple signals. These two extensions are particularly relevant in the framework of EEG data processing, where oscillations are active at the same time in different frequency bands and signals are recorded with multiple sensors. The presented tracking scheme is first tested with synthetic signals in order to highlight its capabilities. Then it is applied to data recorded during a visual shape discrimination experiment for assessing its usefulness during EEG processing and in detecting functionally relevant changes. This method is an interesting additional processing step for providing alternative information compared to classical time-frequency analyses and for improving the detection and analysis of cross-frequency couplings.

Advanced Kernel Methods For Remote Sensing Image Classification

Résumé Suite aux recentes avancées technologiques, les archives d'images digitales ont connu une croissance qualitative et quantitative sans précédent. Malgré les énormes possibilités qu'elles offrent, ces avancées posent de nouvelles questions quant au traitement des masses de données saisies. Cette question est à la base de cette Thèse: les problèmes de traitement d'information digitale à très haute résolution spatiale et/ou spectrale y sont considérés en recourant à des approches d'apprentissage statistique, les méthodes à noyau. Cette Thèse étudie des problèmes de classification d'images, c'est à dire de catégorisation de pixels en un nombre réduit de classes refletant les propriétés spectrales et contextuelles des objets qu'elles représentent. L'accent est mis sur l'efficience des algorithmes, ainsi que sur leur simplicité, de manière à augmenter leur potentiel d'implementation pour les utilisateurs. De plus, le défi de cette Thèse est de rester proche des problèmes concrets des utilisateurs d'images satellite sans pour autant perdre de vue l'intéret des méthodes proposées pour le milieu du machine learning dont elles sont issues. En ce sens, ce travail joue la carte de la transdisciplinarité en maintenant un lien fort entre les deux sciences dans tous les développements proposés. Quatre modèles sont proposés: le premier répond au problème de la haute dimensionalité et de la redondance des données par un modèle optimisant les performances en classification en s'adaptant aux particularités de l'image. Ceci est rendu possible par un système de ranking des variables (les bandes) qui est optimisé en même temps que le modèle de base: ce faisant, seules les variables importantes pour résoudre le problème sont utilisées par le classifieur. Le manque d'information étiquétée et l'incertitude quant à sa pertinence pour le problème sont à la source des deux modèles suivants, basés respectivement sur l'apprentissage actif et les méthodes semi-supervisées: le premier permet d'améliorer la qualité d'un ensemble d'entraînement par interaction directe entre l'utilisateur et la machine, alors que le deuxième utilise les pixels non étiquetés pour améliorer la description des données disponibles et la robustesse du modèle. Enfin, le dernier modèle proposé considère la question plus théorique de la structure entre les outputs: l'intègration de cette source d'information, jusqu'à présent jamais considérée en télédétection, ouvre des nouveaux défis de recherche. Advanced kernel methods for remote sensing image classification Devis Tuia Institut de Géomatique et d'Analyse du Risque September 2009 Abstract The technical developments in recent years have brought the quantity and quality of digital information to an unprecedented level, as enormous archives of satellite images are available to the users. However, even if these advances open more and more possibilities in the use of digital imagery, they also rise several problems of storage and treatment. The latter is considered in this Thesis: the processing of very high spatial and spectral resolution images is treated with approaches based on data-driven algorithms relying on kernel methods. In particular, the problem of image classification, i.e. the categorization of the image's pixels into a reduced number of classes reflecting spectral and contextual properties, is studied through the different models presented. The accent is put on algorithmic efficiency and the simplicity of the approaches proposed, to avoid too complex models that would not be used by users. The major challenge of the Thesis is to remain close to concrete remote sensing problems, without losing the methodological interest from the machine learning viewpoint: in this sense, this work aims at building a bridge between the machine learning and remote sensing communities and all the models proposed have been developed keeping in mind the need for such a synergy. Four models are proposed: first, an adaptive model learning the relevant image features has been proposed to solve the problem of high dimensionality and collinearity of the image features. This model provides automatically an accurate classifier and a ranking of the relevance of the single features. The scarcity and unreliability of labeled. information were the common root of the second and third models proposed: when confronted to such problems, the user can either construct the labeled set iteratively by direct interaction with the machine or use the unlabeled data to increase robustness and quality of the description of data. Both solutions have been explored resulting into two methodological contributions, based respectively on active learning and semisupervised learning. Finally, the more theoretical issue of structured outputs has been considered in the last model, which, by integrating outputs similarity into a model, opens new challenges and opportunities for remote sensing image processing.

Prognostic relevance of Masaoka and Müller-Hermelink classification in patients with thymic tumors.

BACKGROUND: To compare the prognostic relevance of Masaoka and Müller-Hermelink classifications. METHODS: We treated 71 patients with thymic tumors at our institution between 1980 and 1997. Complete follow-up was achieved in 69 patients (97%) with a mean follow up-time of 8.3 years (range, 9 months to 17 years). RESULTS: Masaoka stage I was found in 31 patients (44.9%), stage II in 17 (24.6%), stage III in 19 (27.6%), and stage IV in 2 (2.9%). The 10-year overall survival rate was 83.5% for stage I, 100% for stage IIa, 58% for stage IIb, 44% for stage III, and 0% for stage IV. The disease-free survival rates were 100%, 70%, 40%, 38%, and 0%, respectively. Histologic classification according to Müller-Hermelink found medullary tumors in 7 patients (10.1%), mixed in 18 (26.1%), organoid in 14 (20.3%), cortical in 11 (15.9%), well-differentiated thymic carcinoma in 14 (20.3%), and endocrine carcinoma in 5 (7.3%), with 10-year overall survival rates of 100%, 75%, 92%, 87.5%, 30%, and 0%, respectively, and 10-year disease-free survival rates of 100%, 100%, 77%, 75%, 37%, and 0%, respectively. Medullary, mixed, and well-differentiated organoid tumors were correlated with stage I and II, and well-differentiated thymic carcinoma and endocrine carcinoma with stage III and IV (p < 0.001). Multivariate analysis showed age, gender, myasthenia gravis, and postoperative adjuvant therapy not to be significant predictors of overall and disease-free survival after complete resection, whereas the Müller-Hermelink and Masaoka classifications were independent significant predictors for overall (p < 0.05) and disease-free survival (p < 0.004; p < 0.0001). CONCLUSIONS: The consideration of staging and histology in thymic tumors has the potential to improve recurrence prediction and patient selection for combined treatment modalities.