eDeeplepsy: An artificial neural framework to reveal different brain states in children with epileptic spasms.

OBJECTIVE: Despite advances, analysis and interpretation of EEG still essentially rely on visual inspection by a super-specialized physician. Considering the vast amount of data that composes the EEG, much of the detail inevitably escapes ordinary human scrutiny. Significant information may not be evident and is missed, and misinterpretation remains a serious problem. Can we develop an artificial intelligence system to accurately and efficiently classify EEG and even reveal novel information? In this study, deep learning techniques and, in particular, Convolutional Neural Networks, have been used to develop a model (which we have named eDeeplepsy) for distinguishing different brain states in children with epilepsy. METHODS: A novel EEG database from a homogenous pediatric population with epileptic spasms beyond infancy was constituted by epileptologists, representing a particularly intriguing seizure type and challenging EEG. The analysis was performed on such samples from long-term video-EEG recordings, previously coded as images showing how different parts of the epileptic brain are distinctly activated during varying states within and around this seizure type. RESULTS: Results show that not only could eDeeplepsy differentiate ictal from interictal states but also discriminate brain activity between spasms within a cluster from activity away from clusters, usually undifferentiated by visual inspection. Accuracies between 86 % and 94 % were obtained for the proposed use cases. SIGNIFICANCE: We present a model for computer-assisted discrimination that can consistently detect subtle differences in the various brain states of children with epileptic spasms, and which can be used in other settings in epilepsy with the purpose of reducing workload and discrepancies or misinterpretations. The research also reveals previously undisclosed information that allows for a better understanding of the pathophysiology and evolving characteristics of this particular seizure type. It does so by documenting a different state (interspasms) that indicates a potentially non-standard signal with distinctive epileptogenicity at that period.

Discriminating and understanding brain states in children with epileptic spasms using deep learning and graph metrics analysis of brain connectivity.

BACKGROUND AND OBJECTIVE: Epilepsy is a brain disorder consisting of abnormal electrical discharges of neurons resulting in epileptic seizures. The nature and spatial distribution of these electrical signals make epilepsy a field for the analysis of brain connectivity using artificial intelligence and network analysis techniques since their study requires large amounts of data over large spatial and temporal scales. For example, to discriminate states that would otherwise be indistinguishable from the human eye. This paper aims to identify the different brain states that appear concerning the intriguing seizure type of epileptic spasms. Once these states have been differentiated, an attempt is made to understand their corresponding brain activity. METHODS: The representation of brain connectivity can be done by graphing the topology and intensity of brain activations. Graph images from different instants within and outside the actual seizure are used as input to a deep learning model for classification purposes. This work uses convolutional neural networks to discriminate the different states of the epileptic brain based on the appearance of these graphs at different times. Next, we apply several graph metrics as an aid to interpret what happens in the brain regions during and around the seizure. RESULTS: Results show that the model consistently finds distinctive brain states in children with epilepsy with focal onset epileptic spasms that are indistinguishable under the expert visual inspection of EEG traces. Furthermore, differences are found in brain connectivity and network measures in each of the different states. CONCLUSIONS: Computer-assisted discrimination using this model can detect subtle differences in the various brain states of children with epileptic spasms. The research reveals previously undisclosed information regarding brain connectivity and networks, allowing for a better understanding of the pathophysiology and evolving characteristics of this particular seizure type. From our data, we speculate that the prefrontal, premotor, and motor cortices could be more involved in a hypersynchronized state occurring in the few seconds immediately preceding the visually evident EEG and clinical ictal features of the first spasm in a cluster. On the other hand, a disconnection in centro-parietal areas seems a relevant feature in the predisposition and repetitive generation of epileptic spasms within clusters.

The hippocampus as the switchboard between perception and memory.

Adaptive memory recall requires a rapid and flexible switch from external perceptual reminders to internal mnemonic representations. However, owing to the limited temporal or spatial resolution of brain imaging modalities used in isolation, the hippocampal-cortical dynamics supporting this process remain unknown. We thus employed an object-scene cued recall paradigm across two studies, including intracranial electroencephalography (iEEG) and high-density scalp EEG. First, a sustained increase in hippocampal high gamma power (55 to 110 Hz) emerged 500 ms after cue onset and distinguished successful vs. unsuccessful recall. This increase in gamma power for successful recall was followed by a decrease in hippocampal alpha power (8 to 12 Hz). Intriguingly, the hippocampal gamma power increase marked the moment at which extrahippocampal activation patterns shifted from perceptual cue toward mnemonic target representations. In parallel, source-localized EEG alpha power revealed that the recall signal progresses from hippocampus to posterior parietal cortex and then to medial prefrontal cortex. Together, these results identify the hippocampus as the switchboard between perception and memory and elucidate the ensuing hippocampal-cortical dynamics supporting the recall process.

Las evoluciones atípicas de la epilepsia rolándica son complicaciones predecibles / The atypical developments of rolandic epilepsy are predictable complications

Introducción. Las evoluciones atípicas de la epilepsia rolándica son parte de un espectro clínico de fenotipos variables, idiopáticos, dependientes de la edad y con una predisposición genéticamente determinada. Objetivo. Estudiar las características electroclínicas sugestivas de una evolución atípica en la epilepsia rolándica. Pacientes y métodos. Se realizó una búsqueda retrospectiva de 133 niños diagnosticados de epilepsia focal benigna atípica (EFBA), síndrome de Landau-Kleffner y epilepsia de punta-onda continua durante el sueño (POCS). Se seleccionaron nueve pacientes que, en el trascurso de su epilepsia rolándica, presentaron un cuadro clínico atípico y un patrón electroencefalográfico (EEG) de estado epiléptico eléctrico durante el sueño (ESES). Resultados. El inicio de la epilepsia rolándica fue, en promedio, a los 5 años. Los pacientes presentaron un empeoramiento clínico y del EEG año y medio más tarde en promedio. En tres pacientes se observaron características de EFBA, y en seis, de POCS. No se encontraron casos de síndrome de Landau-Kleffner. El EEG en vigilia mostró una focalidad centrotemporal izquierda en seis pacientes, y derecha, en tres. Todos los pacientes presentaron un ESES en el EEG de sueño. En tres de ellos se observó un patrón atípico de ESES regional. Además, se detectaron alteraciones cognitivas y conductuales por déficits en áreas específicas del aprendizaje, como lenguaje, memoria, atención e inquietud. Conclusiones. El inicio precoz de la epilepsia rolándica, la aparición de nuevas crisis con un incremento en su frecuencia y una focalidad frontocentrotemporal en el EEG, que aumenta en frecuencia, tanto en vigilia como en sueño, son características electroclínicas sugerentes de una evolución atípica (AU)

Introduction. The development of atypical features in rolandic epilepsy is part of a clinical spectrum of phenotypes that are variable, idiopathic and age-dependent, as well as having a genetically determined predisposition. Aim. To study the electroclinical characteristics suggesting an atypical development in rolandic epilepsy Patients and methods. A retrospective search was performed in 133 children diagnosed with atypical benign focal epilepsy (ABFE), Landau-Kleffner syndrome and continuous spike-wave during sleep (CSWS). Nine patients were selected, all of whom presented atypical clinical features and an electroencephalogram (EEG) pattern of electrical status epilepticus during sleep (ESES) in the course of their rolandic epilepsy. Results. The average age at onset of rolandic epilepsy was 5 years. Patients showed a deterioration of both their clinical features and their EEG recording one and a half years later, on average. ABFE was observed in three of them and CSWS in six. No cases of Landau-Kleffner syndrome were found. The EEG in wakefulness showed the focus to be in the left centrotemporal region in six patients and in three of them it was on the right-hand side. All the patients presented ESES in the EEG during sleep. An atypical pattern was observed in the regional ESES in three of the patients. Moreover, cognitive and behavioural disorders were detected due to deficits in specific learning areas, such as language, memory, attention and restlessness. Conclusions. The early onset of rolandic epilepsy, the appearance of new seizures with an increased frequency and the frontocentrotemporal focus in the EEG, which increases in frequency, both in wakefulness and in sleep, are all electroclinical characteristics of an atypical development (AU)

[The atypical developments of rolandic epilepsy are predictable complications]. / Las evoluciones atipicas de la epilepsia rolandica son complicaciones predecibles.

INTRODUCTION: The development of atypical features in rolandic epilepsy is part of a clinical spectrum of phenotypes that are variable, idiopathic and age-dependent, as well as having a genetically determined predisposition. AIM: To study the electroclinical characteristics suggesting an atypical development in rolandic epilepsy. PATIENTS AND METHODS: A retrospective search was performed in 133 children diagnosed with atypical benign focal epilepsy (ABFE), Landau-Kleffner syndrome and continuous spike-wave during sleep (CSWS). Nine patients were selected, all of whom presented atypical clinical features and an electroencephalogram (EEG) pattern of electrical status epilepticus during sleep (ESES) in the course of their rolandic epilepsy. RESULTS: The average age at onset of rolandic epilepsy was 5 years. Patients showed a deterioration of both their clinical features and their EEG recording one and a half years later, on average. ABFE was observed in three of them and CSWS in six. No cases of Landau-Kleffner syndrome were found. The EEG in wakefulness showed the focus to be in the left centrotemporal region in six patients and in three of them it was on the right-hand side. All the patients presented ESES in the EEG during sleep. An atypical pattern was observed in the regional ESES in three of the patients. Moreover, cognitive and behavioural disorders were detected due to deficits in specific learning areas, such as language, memory, attention and restlessness. CONCLUSIONS: The early onset of rolandic epilepsy, the appearance of new seizures with an increased frequency and the frontocentrotemporal focus in the EEG, which increases in frequency, both in wakefulness and in sleep, are all electroclinical characteristics of an atypical development.

TITLE: Las evoluciones atipicas de la epilepsia rolandica son complicaciones predecibles.Introduccion. Las evoluciones atipicas de la epilepsia rolandica son parte de un espectro clinico de fenotipos variables, idiopaticos, dependientes de la edad y con una predisposicion geneticamente determinada. Objetivo. Estudiar las caracteristicas electroclinicas sugestivas de una evolucion atipica en la epilepsia rolandica. Pacientes y metodos. Se realizo una busqueda retrospectiva de 133 niños diagnosticados de epilepsia focal benigna atipica (EFBA), sindrome de Landau-Kleffner y epilepsia de punta-onda continua durante el sueño (POCS). Se seleccionaron nueve pacientes que, en el trascurso de su epilepsia rolandica, presentaron un cuadro clinico atipico y un patron electroencefalografico (EEG) de estado epileptico electrico durante el sueño (ESES). Resultados. El inicio de la epilepsia rolandica fue, en promedio, a los 5 años. Los pacientes presentaron un empeoramiento clinico y del EEG año y medio mas tarde en promedio. En tres pacientes se observaron caracteristicas de EFBA, y en seis, de POCS. No se encontraron casos de sindrome de Landau-Kleffner. El EEG en vigilia mostro una focalidad centrotemporal izquierda en seis pacientes, y derecha, en tres. Todos los pacientes presentaron un ESES en el EEG de sueño. En tres de ellos se observo un patron atipico de ESES regional. Ademas, se detectaron alteraciones cognitivas y conductuales por deficits en areas especificas del aprendizaje, como lenguaje, memoria, atencion e inquietud. Conclusiones. El inicio precoz de la epilepsia rolandica, la aparicion de nuevas crisis con un incremento en su frecuencia y una focalidad frontocentrotemporal en el EEG, que aumenta en frecuencia, tanto en vigilia como en sueño, son caracteristicas electroclinicas sugerentes de una evolucion atipica.

Epilepsy surgery in children with developmental tumours.

We report our experience regarding evaluation, surgical treatment and outcomes in a population of 21 children with histopathologically confirmed developmental tumours [nine dysembryoplastic neuroepithelial tumours (DNET), ten gangliogliomas (GG) and two gangliocytomas (GC)] and related epilepsy, analyzing video-EEG, MRI and neuropsychological data, before and after surgery. Most children had focal epilepsy correlating well with lesion location. One patient had epileptic spasms and generalized discharges. Tumours were located in the temporal lobe in 13 patients. Mean age at surgery was 11.16 years. Postsurgical MRI showed residual tumour growth in one DNET. One child had a recurrent ganglioglioma with anaplastic transformation. At latest follow-up (mean 4.68 years) 95.2% of patients were seizure-free and no significant neuropsychological declines were observed. Evidence from our study suggests that, in this setting, surgery should be performed before criteria for refractory epilepsy are met, particularly in cases with early seizure onset, in order to optimize cognitive outcome.

Validez y utilidad de la ecografía en el síndrome del túnel carpiano / Validity and usefulness of echography in the carpal tunnel syndrome

Objetivo: Evaluar la validez y la utilidad de la ecografía en el síndrome del túnel carpiano (STC). Material y método: Estudio ecográfico ciego y prospectivo en 75 carpos de 42 pacientes consecutivos con sospecha de STC. Se utiliza la electromiografía (EMG) como prueba de referencia. Se miden distintos parámetros ecográficos y mediante curvas ROC se estiman las probabilidades tras la prueba para los diferentes cortes del área de sección transversal del mediano (AST). Se analiza la fiabilidad entre explorador y lector con tres exploradores diferentes y dos lectores. Finalmente se efectúa un estudio de costes y de satisfacción del paciente. Resultados: Las medias de los parámetros ecográficos son significativamente mayores en el grupo con STC. Hay una alta concordancia entre la ecografía y la conducción nerviosa. Un punto de corte del AST en 9,5 mm2 clasifica correctamente el 83% de los casos (sensibilidad del 88% y especificidad del 67%). Un punto de corte mayor de 14 mm2 o menor de 7 mm2 tiene una probabilidad tras la prueba para el STC del 100% de especificidad y sensibilidad respectivamente. Los coeficientes de correlación intraclase (ICC) entre observadores fueron 0,915-0,980, y entre lectores, 0,912-0,987. La ecografía puede resultar más económica y ahorrar en el estudio 3.217,59 euros (42,9 euros por muñeca sintomática). El malestar percibido por los pacientes fue significativamente menor: EVA, 6,3 con ecografía frente a 56 con el EMG (p < 0,0005). Conclusiones: La ecografía es fiable y válida para definir si hay o no STC. La ecografía como prueba de primera línea es coste-efectiva y más satisfactoria para los pacientes (AU)

Objective: To evaluate the accuracy and utility of ultrasonography for the diagnosis of carpal tunnel syndrome (CTS). Material and method: Prospective and blind study of 75 wrists in 42 consecutive patients with suspected CTS. Electrodiagnostic testing (EDT) was used as gold standard. We measure different ultrasonographic parameters and based on a fitted receiver operating characteristic curve, we estimated post-test probabilities for the proximal, middle and distal cross-sectional area of median nerve. We analyzed interobserver and interreader reliability by 3 different explorers and 2 different readers, cost and the patient discomfort. Results: Mean ultrasound measurements were significantly higher in the EDT positive group. There was a high concordance between sonography and nerve conduction. A cut-off of 9.5 mm2 resulted in the correct classification of 83% of cases (sensitivity 88% and specificity 67%). Conversely, a cut-off of >14 mm2 or <7 mm2 had excellent power to rule in CTS, with a post-test probability of 100% of specificity and sensitivity respectively. The interobserver acquisition ICC was 0.915-0.980, and the inter-reader ICC was 0.912-0.987. Ultrasound cost savings in this study were J3217.59 (J42.9 per symptomatic wrist) and the discomfort perceived by the patient was significantly lesser 6.3 vs 56 in EDT (P<.0005). Conclusions: Ultrasound median nerve crosssectional area is reliable and may be used to accurately rule in or rule out CTS. Sonography as a first-line test is cost-effective and is more satisfactory to the patients (AU)

[Validity and usefulness of echography in the carpal tunnel syndrome]. / Validez y utilidad de la ecografía en el síndrome del túnel carpiano.

OBJECTIVE: To evaluate the accuracy and utility of ultrasonography for the diagnosis of carpal tunnel syndrome (CTS). MATERIAL AND METHOD: Prospective and blind study of 75 wrists in 42 consecutive patients with suspected CTS. Electrodiagnostic testing (EDT) was used as gold standard. We measure different ultrasonographic parameters and based on a fitted receiver operating characteristic curve, we estimated post-test probabilities for the proximal, middle and distal cross-sectional area of median nerve. We analyzed interobserver and interreader reliability by 3 different explorers and 2 different readers, cost and the patient discomfort. RESULTS: Mean ultrasound measurements were significantly higher in the EDT positive group. There was a high concordance between sonography and nerve conduction. A cut-off of 9.5 mm(2) resulted in the correct classification of 83% of cases (sensitivity 88% and specificity 67%). Conversely, a cut-off of >14 mm(2) or <7 mm(2) had excellent power to rule in CTS, with a post-test probability of 100% of specificity and sensitivity respectively. The interobserver acquisition ICC was 0.915-0.980, and the inter-reader ICC was 0.912-0.987. Ultrasound cost savings in this study were €J3217.59 (€42.9 per symptomatic wrist) and the discomfort perceived by the patient was significantly lesser 6.3 vs 56 in EDT (P <.0005). CONCLUSIONS: Ultrasound median nerve crosssectional area is reliable and may be used to accurately rule in or rule out CTS. Sonography as a first-line test is cost-effective and is more satisfactory to the patients.