No abstract

Due the fact that the required therapy to treat Ventricular Fibrillation (V F) is aggressive (electric shock), the lack of a proper detection and recovering therapy could cause serious injuries to the patient or trigger a ventricular fibrillation, or even death. This work describes the development of an automatic diagnostic system for the detection of the occurrence of V F in real time by means of the time-frequency representation (T F R) image of the ECG. The main novelties are the use of the T F R image as input for a classification process, as well as the use of combined classifiers. The feature extraction stage is eliminated and, together with the use of specialized binary classifiers, this method improves the results of the classification. To verify the validity of the method, four different classifiers in different combinations are used: Regression Logistic with L2 Regularization (L 2 R L R), adaptive neural network (A N N C), Bagging (B A G G), and K-nearest neighbor (K N N). The Hierarchical Method (HM) and Voting Majority Method (VMM) combinations are used. ECG signals used for evaluation were obtained from the standard MIT-BIH and AHA databases. When the classifiers were combined, it was observed that the combination of B A G G , K N N , and A N N C using the Hierarchical Method (HM) gave the best results, with a sensitivity of 95.58 ± 0.41%, a 99.31 ± 0.08% specificity, a 98.6 ± 0.04% of overall accuracy, and a precision of 98.25 ± 0.29% for V F . Whereas a sensitivity of 94.02 ± 0.58%, a specificity of 99.31 ± 0.08%, an overall accuracy of 99.14 ± 0.43%, and a precision of 98.59 ± 0.09% was obtained for V T with a run time between 0.07 s and 0.12 s. Results show that the use of T F R image data to feed the combined classifiers yields a reduction in execution time with performance values above to those obtained by individual classifiers. This is of special utility for V F detection in real time.

A rapid and accurate detection of ventricular arrhythmias is essential to take appropriate therapeutic actions when cardiac arrhythmias occur. Furthermore, the accurate discrimination between arrhythmias is also important, provided that the required shocking therapy would not be the same. In this work, the main novelty is the use of the mathematical method known as Topological Data Analysis (TDA) to generate new types of features which can contribute to the improvement of the detection and classification performance of cardiac arrhythmias such as Ventricular Fibrillation (VF) and Ventricular Tachycardia (VT). The electrocardiographic (ECG) signals used for this evaluation were obtained from the standard MIT-BIH and AHA databases. Two input data to the classify are evaluated: TDA features, and Persistence Diagram Image (PDI). Using the reduced TDA-obtained features, a high average accuracy near 99% was observed when discriminating four types of rhythms (98.68% to VF; 99.05% to VT; 98.76% to normal sinus; and 99.09% to Other rhythms) with specificity values higher than 97.16% in all cases. In addition, a higher accuracy of 99.51% was obtained when discriminating between shockable (VT/VF) and non-shockable rhythms (99.03% sensitivity and 99.67% specificity). These results show that the use of TDA-derived geometric features, combined in this case this the k-Nearest Neighbor (kNN) classifier, raises the classification performance above results in previous works. Considering that these results have been achieved without preselection of ECG episodes, it can be concluded that these features may be successfully introduced in Automated External Defibrillation (AED) and Implantable Cardioverter Defibrillation (ICD) therapies.

ResumenEste trabajo propone la detección de FV y su discriminación de TV y otros ritmos cardiacos basándose en la representación tiempo-frecuencia del ECG y su conversión en imágen como entrada a un clasificador de vecinos más cercanos (KNN) sin necesidad de extracción de parámetros adicionales. Tres variantes de datos de entrada al clasificador son evaluados. Los resultados clasifican la señal en cuatro clases diferentes: 'Normal' para latidos con ritmo sinusal, 'FV' para fibrilación ventricular, 'TV' para taquicardia ventricular y 'Otros' para el resto de ritmos. Los resultados para detección de FV mostraron 88,27 % de sensibilidad y 98,22 % de especificidad para la entrada de imagen equivalente reducida que es la más rápida computacionalmente a pesar de obtener resultados de clasificación ligeramente inferiores a las representaciones no reducidas. En el caso de TV, se alcanzó un 88,31 % de sensibilidad y 98,80 % de especificidad, un 98,14 % de sensibilidad y 96,82 % de especificidad para ritmo sinusal normal y 96,91 % de sensibilidad con 99,06 % de especificidad para la clase 'Otros'. Finalmente, se realiza una comparación con otros algoritmos.Palabras Clave: Sistemas biomédicos, Señales Electrocardiográficas, Representación tiempo-frecuencia, Señales no estacionarias, Análisis de imágenes, Clasificación Ventricular Fibrillation detection using time-frequency and the KNN classifier without parameter extraction. AbstractThis work describes new techniques to improve VF detection and its separation from Ventricular Tachycarida (VT) and other rhythms. It is based on time-frequency representation of the ECG and its use as input in an automatic classifier (K-nearest neighbours -KNN) without any further signal parameter extraction or additional characteristics. For comparison purposes, three time-frequency variants are analysed: pseudo Wigner-Ville representation (RTF), grey-scale image obtained from RTF (IRTF), and reduced image from IRTF (reduced IRTF). Four types of rhythms (classes) are defined: 'Normal' for sinus rhythm, 'VT' for ventricular tachycardia, 'VF' for ventricular fibrillation and 'Others' for the rest of rhythms. Classification results for VF detection in case of reduced IRTF are 88.27 % sensitivity and 98.22 % specificity. In case of VT, 88.31 % sensitivity and 98.80 % specificity is obtained, 98.14 % sensitivity and 96.82 % specificity for normal rhythms, and 96.91 % sensitivity and 99.06 % specificity for other rhythms. Finally, results are compared with other authors.

The epileptogenic focus is a brain area that may be surgically removed to control of epileptic seizures. Locating it is an essential and crucial step prior to the surgical treatment. However, given the difficulty of determining the localization of this brain region responsible of the initial seizure discharge, many works have proposed machine learning methods for the automatic classification of focal and non-focal electroencephalographic (EEG) signals. These works use automatic classification as an analysis tool for helping neurosurgeons to identify focal areas off-line, out of surgery, during the processing of the huge amount of information collected during several days of patient monitoring. In turn, this paper proposes an automatic classification procedure capable of assisting neurosurgeons online, during the resective epilepsy surgery, to refine the localization of the epileptogenic area to be resected, if they have doubts. This goal requires a real-time implementation with as low a computational cost as possible. For that reason, this work proposes both a feature set and a classifier model that minimizes the computational load while preserving the classification accuracy at 95.5%, a level similar to previous works. In addition, the classification procedure has been implemented on a FPGA device to determine its resource needs and throughput. Thus, it can be concluded that such a device can embed the whole classification process, from accepting raw signals to the delivery of the classification results in a cost-effective Xilinx Spartan-6 FPGA device. This real-time implementation begins providing results after a 5 s latency, and later, can deliver floating-point classification results at 3.5 Hz rate, using overlapped time-windows.