Nonconvulsive status epilepticus is a condition where the patient is exposed to abnormally prolonged epileptic seizures without evident physical symptoms. Since these continuous seizures may cause ...permanent brain damage, it constitutes a medical emergency. This paper proposes a method to detect nonconvulsive seizures for a further nonconvulsive status epilepticus diagnosis. To differentiate between the normal and seizure electroencephalogram (EEG), a K-Nearest Neighbor, a Radial Basis Support Vector Machine, and a Linear Discriminant Analysis classifier are used. The classifier features are obtained from the Canonical Polyadic Decomposition (CPD) and Block Term Decomposition of the EEG data represented as third order tensor. To expand the EEG into a tensor, Wavelet or Hilbert-Huang transform are used. The algorithm is tested on a scalp EEG database of 139 seizures of different duration. The experimental results suggest that a Hilbert-Huang tensor representation and the CPD analysis provide the most suitable framework for nonconvulsive seizure detection. The Radial Basis Support Vector Machine classifier shows the best performance with sensitivity, specificity, and accuracy values over 98%. A rough comparison with other methods proposed in the literature shows the superior performance of the proposed method for nonconvulsive epileptic seizure detection.
Nonconvulsive epileptic seizures (NCSz) and nonconvulsive status epilepticus (NCSE) are two neurological entities associated with increment in morbidity and mortality in critically ill patients. In a ...previous work, we introduced a method which accurately detected NCSz in EEG data (referred here as ‘Batch method’). However, this approach was less effective when the EEG features identified at the beginning of the recording changed over time. Such pattern drift is an issue that causes failures of automated seizure detection methods. This paper presents a support vector machine (SVM)-based incremental learning method for NCSz detection that for the first time addresses the seizure evolution in EEG records from patients with epileptic disorders and from ICU having NCSz. To implement the incremental learning SVM, three methodologies are tested. These approaches differ in the way they reduce the set of potentially available support vectors that are used to build the decision function of the classifier. To evaluate the suitability of the three incremental learning approaches proposed here for NCSz detection, first, a comparative study between the three methods is performed. Secondly, the incremental learning approach with the best performance is compared with the Batch method and three other batch methods from the literature. From this comparison, the incremental learning method based on maximum relevance minimum redundancy (MRMR_IL) obtained the best results. MRMR_IL method proved to be an effective tool for NCSz detection in a real-time setting, achieving sensitivity and accuracy values above 99%.
•Nonconvulsive epileptic seizures (NCSz) are associated with increased morbidity and mortality in critically ill patients.•NCSz detection methods are less effective when the electroencephalographic (EEG) features of the seizure evolve over time.•Regular classifier updates via incremental learning (IL) improves NCSz detection during long-term EEG monitoring.•Our IL based method detected NCSz that appeared as a consequence of an acute brain dysfunction or an epileptic disorder.
Analyzing gene expression profiles (GEP) through artificial intelligence provides meaningful insight into cancer disease. This study introduces DeepSHAP Autoencoder Filter for Genes Selection ...(DSAF-GS), a novel deep learning and explainable artificial intelligence-based approach for feature selection in genomics-scale data. DSAF-GS exploits the autoencoder’s reconstruction capabilities without changing the original feature space, enhancing the interpretation of the results. Explainable artificial intelligence is then used to select the informative genes for chronic lymphocytic leukemia prognosis of 217 cases from a GEP database comprising roughly 20,000 genes. The model for prognosis prediction achieved an accuracy of 86.4%, a sensitivity of 85.0%, and a specificity of 87.5%. According to the proposed approach, predictions were strongly influenced by CEACAM19 and PIGP, moderately influenced by MKL1 and GNE, and poorly influenced by other genes. The 10 most influential genes were selected for further analysis. Among them, FADD, FIBP, FIBP, GNE, IGF1R, MKL1, PIGP, and SLC39A6 were identified in the Reactome pathway database as involved in signal transduction, transcription, protein metabolism, immune system, cell cycle, and apoptosis. Moreover, according to the network model of the 3D protein-protein interaction (PPI) explored using the NetworkAnalyst tool, FADD, FIBP, IGF1R, QTRT1, GNE, SLC39A6, and MKL1 appear coupled into a complex network. Finally, all 10 selected genes showed a predictive power on time to first treatment (TTFT) in univariate analyses on a basic prognostic model including IGHV mutational status, del(11q) and del(17p), NOTCH1 mutations, β2-microglobulin, Rai stage, and B-lymphocytosis known to predict TTFT in CLL. However, only IGF1R hazard ratio (HR) 1.41, 95% CI 1.08-1.84, P=0.013), COL28A1 (HR 0.32, 95% CI 0.10-0.97, P=0.045), and QTRT1 (HR 7.73, 95% CI 2.48-24.04, P<0.001) genes were significantly associated with TTFT in multivariable analyses when combined with the prognostic factors of the basic model, ultimately increasing the Harrell’s c-index and the explained variation to 78.6% (versus 76.5% of the basic prognostic model) and 52.6% (versus 42.2% of the basic prognostic model), respectively. Also, the goodness of model fit was enhanced (χ2 = 20.1, P=0.002), indicating its improved performance above the basic prognostic model. In conclusion, DSAF-GS identified a group of significant genes for CLL prognosis, suggesting future directions for bio-molecular research.
ABSTRACT Nonconvulsive status epilepticus (NCSE) is a condition where the patient is exposed to abnormally prolonged nonconvulsive epileptic seizures (NCES)(epileptic seizures without evident ...physical symptoms). Hence, the diagnosis can only be stated by means of EEG monitoring. NCSE and NCES are associated with severe irreversible brain damage and poor outcome. Hence, the prompt recognition of patients at risk of suffering NCSE is necessary in order to manage them properly and to prevent further brain injury. However, despite the clinical efforts to manage NCES and NCSE, and improve the patient’s outcome, monitoring this pathology in real-time is very difficult. In a previous work of these authors, a patient specific method is proposed to detect the NCES. This method identifies the NCES by exploiting the similarity between the first NCES detected by the physician on the EEG and the rest of NCES in the recording. The method used a support vector machine classifier to perform the classification, obtaining specificity, and sensitivity, results over 98%. However, the method was vulnerable to missclassify epochs with EEG patterns resembling a NCES. In this paper, we propose a complementary method based in partial least squares (PLS) to improve the identification of the NCES patterns of the previously proposed method in dubious EEG segments. The proposed method improved the SVM based model performance obtaining specificity ans sensitivity values over 99%.
Nonconvulsive status epilepticus (NCSE) is observed when the patient undergoes a persistent electroencephalographic epileptic episode without physical symptoms. This condition is commonly found in ...critically ill patients from intensive care units and constitutes a medical emergency. This paper proposes a method to detect nonconvulsive epileptic seizures (NCES). To perform the NCES detection the electroencephalogram (EEG) is represented as a third order tensor with axes frequency χ time χ channels using Wavelet or Hilbert-Huang transform. The signatures obtained from the tensor decomposition are used to train five classifiers to separate between the normal and seizure EEG. Classification is performed in two ways: (1) with each signature of the different modes separately, (2) with all signatures assembled. The algorithm is tested on a database containing 139 nonconvulsive seizures. From all performed analysis, Hilbert-Huang Tensors Space and assembled signatures demonstrate to be the best features to classify between seizure and non-seizure EEG.
Introducción: los métodos de medición del nivel de profundidad del efecto hipnótico de los fármacos anestésicos, a partir del análisis cuantitativo del electroencefalograma, necesitan ser ...perfeccionados y optimizados para garantizar su aplicación eficiente en la práctica clínica. Objetivo: evaluar los efectos del nivel de profundidad anestésica y de la derivación del registro en los parámetros del electroencefalograma cuantitativo, para garantizar la selección de los parámetros óptimos en la clasificación del nivel de profundidad anestésica. Métodos: se estudió una muestra de 29 adultos con afecciones abdominales, tratados quirúrgicamente por vía endoscópica, bajo anestesia general. El registro electroencefalográfico se realizó mediante un montaje de 19 canales y el nivel de profundidad anestésica fue cuantificado clínicamente mediante una escala de 8 niveles. Igualmente, los parámetros del electroencefalograma cuantitativo fueron estimados mediante el sistema de análisis del equipo Medicid 5 de Neuronic. Resultados: el nivel de profundidad anestésica presentó un efecto significativo en los parámetros del electroencefalograma cuantitativo, en los modelos espectrales de banda ancha y estrecha. Entre los parámetros con mayor significación figuraron: el poder absoluto delta, theta, el poder relativo theta y la frecuencia media theta, alpha y total; mientras que en los parámetros de banda estrecha se obtuvo un efecto significativo en todas las derivaciones, con una interacción significativa entre la topografía y el nivel de profundidad anestésica. Conclusiones: los parámetros del electroencefalograma cuantitativo pueden ser utilizados de forma eficaz en la predicción del nivel de profundidad anestésica, con una mayor resolución en los niveles de clasificación que los utilizados hasta el presente. Asimismo, se confirmó el efecto selectivo de los agentes hipnóticos en las diferentes áreas corticales
Durante un procedimiento quirúrgico es esencial inducir al paciente estados de inconsciencia, amnesia, analgesia y relajación muscular, sin embargo, debido a la inexactitud en la monitorización de la ...anestesia se reportan casos de despertar intraoperatorio. A causa de la incidencia de este fenómeno, el Centro de Estudios de Neurociencias, Procesamiento de Imágenes y Señales en la Universidad de Oriente, Cuba, lleva a cabo la implementación de un prototipo de monitor de anestesia basado en el reconocimiento automático de estados de sedación en las señales electroencefalográficas usando técnicas de Inteligencia Artificial. Para alcanzar el objetivo propuesto se evaluó el desempeño de un clasificador Naive Bayes y tres Máquinas de Aprendizaje: Redes Neuronales Artificiales con cinco topologías diferentes, Sistemas de Inferencia Difusa basada en Redes Adaptativas y las Máquinas de Soporte Vectorial para reconocer tres estados de sedación caracterizados por nueve parámetros de potencia obtenidos a partir del espectro de frecuencia de las señales registradas por los canales electroencefalográficos frontales F4 y Fz. Como resultados de los experimentos se reconocieron los estados de Sedación Profunda, Sedación Moderada y Sedación Ligera con una Exactitud de 96.12%, 90.06% y 90.24% respectivamente usando las Máquinas de Soporte Vectorial y los registros del canal electroencefalográfico F4.
Durante un procedimiento quirúrgico es esencial inducir al paciente estados de inconsciencia, amnesia, analgesia y relajación muscular, sin embargo, debido a la inexactitud en la monitorización de la ...anestesia se reportan casos de despertar intraoperatorio. A causa de la incidencia de este fenómeno, el Centro de Estudios de Neurociencias, Procesamiento de Imágenes y Señales en la Universidad de Oriente, Cuba, lleva a cabo la implementación de un prototipo de monitor de anestesia basado en el reconocimiento automático de estados de sedación en las señales electroencefalográficas usando técnicas de Inteligencia Artificial. Para alcanzar el objetivo propuesto se evaluó el desempeño de un clasificador Naive Bayes y tres Máquinas de Aprendizaje: Redes Neuronales Artificiales con cinco topologías diferentes, Sistemas de Inferencia Difusa basada en Redes Adaptativas y las Máquinas de Soporte Vectorial para reconocer tres estados de sedación caracterizados por nueve parámetros de potencia obtenidos a partir del espectro de frecuencia de las señales registradas por los canales electroencefalográficos frontales F4 y Fz. Como resultados de los experimentos se reconocieron los estados de Sedación Profunda, Sedación Moderada y Sedación Ligera con una Exactitud de 96.12%, 90.06% y 90.24% respectivamente usando las Máquinas de Soporte Vectorial y los registros del canal electroencefalográfico F4. Palabras claves: Máquinas de Aprendizaje, Estados de Sedación, Señales Electroencefalográficas During a surgical procedure it is essential induce to the patient, unconsciousness states, amnesia, analgesia and muscle relaxation, however, cases of intraoperative awareness are reported for the inaccuracy in monitoring anesthesia. Due the incidence of this phenomenon, the Center for Neuroscience Studies, Images and Signals Processing from Universidad de Oriente, Cuba, is carried out the development of an anesthesia monitor prototype, based on automatic recognition of sedation states in electroencephalographic signals using Artificial Intelligence techniques. To achieve the proposed objective, were evaluated the performance of a Naive Bayes classifier and three Machines Learning: Artificial Neural Networks with five different topologies, Adaptive Network Based Fuzzy Inference System and Support Vector Machines to recognize three sedation states characterized by nine power parameters obtained from the frequency spectrum of the signals recorded by two electroencephalographic channels front F4 and Fz. As results of the experiments, the states Profound Sedation, Moderate Sedation and Mild Sedation were recognized with an Accuracy of 96.12%, 90.06% and 90.24% respectively using Support Vector Machines and the registers of F4 electroencephalographic channel. Key words: Machines Learning, Sedation States, Electroencephalographic Signals
Introduction: Anesthesiology is the medical specialty concerned with the specific care of patients during surgical and intensive care procedures. This specialty, based on scientific and technological ...advances, has incorporated the use of electroencephalographic monitoring, facilitating the continuous control in the use of anesthesia for patient´s sedation states during surgeries, with an adequate concentration of drugs. Objective: proposal for a classification strategy for automatic recognition of three sedation states in electroencephalographic signals. Methods: we used, with written informed consent, the electroencephalographic records of 27 patients undergoing abdominal surgery, excluding those with a history of epilepsy, cerebrovascular disease and other neurological conditions. A total of 12 drugs to produce anesthesia and two muscle relaxants with 19 electrodes, mounted according to the International System 10 -20, were applied. Artifacts in the records were eliminated and artificial intelligence techniques were applied to perform automatic recognition of sedation states. Results: a strategy based on the use of support vector machines with a multiclass algorithm One-against-Rest and the Cosine Similarity metric was proposed to perform the automatic recognition of three sedation states: deep, moderate and light, in signals recorded by the frontal channel F4 and the occipital channels O1 and O2. A comparison was carried out between the proposal showed and other classification methods. Conclusions: a balanced accuracy of 92.67% is computed about the recognition of the three states of sedation in the signals recorded by the electroencephalographic channel F4, which helps in a better anesthetic monitoring process.