|
|
Detection of atrial fibrillation in short-term ECG
Ambrožová, Monika ; Janoušek, Oto (referee) ; Ronzhina, Marina (advisor)
Atrial fibrillation is diagnosed in 1-2% of the population, in next decades, it expects a significant increase in the number of patients with this arrhythmia in connection with the aging of the population and the higher incidence of some diseases that are considered as risk factors of atrial fibrillation. The aim of this work is to describe the problem of atrial fibrillation and the methods that allow its detection in the ECG record. In the first part of work there is a theory dealing with cardiac physiology and atrial fibrillation. There is also basic descreption of the detection of atrial fibrillation. In the practical part of work, there is described software for detection of atrial fibrillation, which is provided by BTL company. Furthermore, an atrial fibrillation detector is designed. Several parameters were selected to detect the variation of RR intervals. These are the parameters of the standard deviation, coefficient of skewness and kurtosis, coefficient of variation, root mean square of the successive differences, normalized absolute deviation, normalized absolute difference, median absolute deviation and entropy. Three different classification models were used: support vector machine (SVM), k-nearest neighbor (KNN) and discriminant analysis classification. The SVM classification model achieves the best results. Results of success indicators (sensitivity: 67.1%; specificity: 97.0%; F-measure: 66.8%; accuracy: 92.9%).
|
|
|
Classification of ECG by artificial neural networks
Loviška, David ; Vítek, Martin (referee) ; Hrubeš, Jan (advisor)
The aim of project with name Classification ECG by artificial neural networks is simplify and speed up working a doctor. That reaches created program that the is capable simply and almost at once classify EKG signal using artificial neuronal nets. Created program will give to the doctor basic information about used electrocardiogram, as are time period and amplitude signal in single surveyed sections. Subsequently will program warn doctor about abnormalities from normal. Part of program is also graphic window with painted signal and on him in color points and partitions marked by program behind special. In next phase program alone classifies gained data and designating without doctor diagnose that doctor can evaluate and in case agreeable it sign and place for true diagnose patient. This program is also fit for data reading from bigger of the number of hours as far as days. It is concerned primarily Holter ECG monitoring.
|
|
|
Deep Neural Network for Detection of Atrial Fibrillation
Budíková, Barbora ; Ronzhina, Marina (referee) ; Hejč, Jakub (advisor)
Atrial fibrillation is an arrhythmia commonly detected from ECG using its specific characteristics. An early detection of this arrhythmia is a key to prevention of more serious conditions. Nowadays, atrial fibrillation detection is being implemented more often using deep learning. This work presents detection of atrial fibrillation from 12lead ECG using deep convolutional network. In the first section, there is a theoretical context of this work, then there is a description of proposed algorithm. Detection is implemented by a program in Python in two variations and their accuracy is rated by Accuracy and F1 measure. Results of the work are being discussed, mutually compared and compared to other similar publications.
|
|
|
ECG based atrial fibrillation detection
Prokopová, Ivona ; Kolářová, Jana (referee) ; Ronzhina, Marina (advisor)
Atrial fibrillation is one of the most common cardiac rhythm disorders characterized by ever-increasing prevalence and incidence in the Czech Republic and abroad. The incidence of atrial fibrillation is reported at 2-4 % of the population, but due to the often asymptomatic course, the real prevalence is even higher. The aim of this work is to design an algorithm for automatic detection of atrial fibrillation in the ECG record. In the practical part of this work, an algorithm for the detection of atrial fibrillation is proposed. For the detection itself, the k-nearest neighbor method, the support vector method and the multilayer neural network were used to classify ECG signals using features indicating the variability of RR intervals and the presence of the P wave in the ECG recordings. The best detection was achieved by a model using a multilayer neural network classification with two hidden layers. Results of success indicators: Sensitivity 91.23 %, Specificity 99.20 %, PPV 91.23 %, F-measure 91.23 % and Accuracy 98.53 %.
|
|
|
Deep-learning based localization of cardiac arrhythimas in ECG
Khaliullina, Sabina ; Novotná, Petra (referee) ; Ronzhina, Marina (advisor)
The thesis deals with the localization and classification of atrial atrial fibrillation. In Python, a detection method using convolutional neural networks with multi-instance learning (MIL) and the method of local maxima for localization were implemented. Segments from two ECG leads were used. In the binary classification using the first subset and subsequent post processing, the F1 score reached 100 %, in the classification using the second subset 92 %. In the discussion and conclusion of the work, the success of classification and localization was evaluated, the achieved results were discussed and compared the with the results of other authors.
|
|
|
Accuracy of methods for detection of atrial fibrillation in ECG signals
Veleba, Josef ; Janoušek, Oto (referee) ; Provazník, Ivo (advisor)
This thesis focuses on the issue of atrial fibrillation and the success of their detection in the ECG signal. It provides a description of electrical activity of the heart with the theoretical analysis of atrial fibrillation and methods for their detection. Additionally the work describes procedures for the implementation of three selected methods for the detection of atrial fibrillation in the MATLAB environment, presents the results of their tests on two atrial fibrillation signal databases and assesses the accuracy of each method.
|
|
|
Atrial fibrillation model
Ředina, Richard ; Smíšek, Radovan (referee) ; Ronzhina, Marina (advisor)
The aim of this master thesis is to create a 3D electroanatomical model of a heart atria, which would be able to perform atrial fibrillation. To control the model, the differential equations of the FitzHugh-Nagumo model were chosen. These equations describe the change of voltage on the cell membrane. The equations have established parameters. The modification of them leads to changes in the behavior of the model. The simulations were performed in the COMSOL Multiphysics environment. In the first step, the simulations were performed on 2D models. Simulations of healthy heart, atrial flutter and atrial fibrillation were created. The acquired knowledge served as a basis for the creation of a 3D model on which atrial fibrillation was simulated on the basis of ectopic activity and reentry mechanism. Convincing results were obtained in accordance with the used literature. The advantages of computational modeling are its availability, zero ethical burden and the ability to simulate even rarer arrhythmias. The disadvantage of the procedure is the need to compromise between accuracy and computational complexity of simulations.
|
|
|
Detection of atrial fibrillation in ECG
Húsková, Michaela ; Vítek, Martin (referee) ; Maršánová, Lucie (advisor)
Aim of this thesis is description of problems of atrial fibrillation and methods that could be used for detection in the electrocardiogram. The introductory part of the theoretical analysis deals with the principle of electrophysiology of the heart and mainly the pathophysiology of atrial fibrillation. Additionally the work is focused on describing methods on automatic atrial fibrillation detection and capabilities of PhysioNet database. In the practical part methods are implemented in the MATLAB environment. After using the statistics to evaluate the quality of the parameters, the automatic classification of the data was performed by the method of The Nearest Neighbour. Finally, the accuracy of testing is presented.
|
|
|
Detection of atrial fibrillation in long-term ECG records
Imramovská, Klára ; Kozumplík, Jiří (referee) ; Maršánová, Lucie (advisor)
The thesis deals with problems of automatic detection of atrial fibrillation in long-term ECG records. The preface of the theoretical part describes the electrophysiology of the heart and the principle of atrial fibrillation. Furthermore, it introduces methods of automatic detection of atrial fibrillation. In the practical part a method which uses the symbolic dynamics and a calculation of Shannon entropy is implemented in the MATLAB software environment. The method is tested on signals from the MIT-BIH Atrial Fibrillation Database and the Long-Term AF Database. Lastly, the accuracy of the classification is compared with methods described in different papers.
|
|
|
Atrial fibrillation detection using time-domain methods
Sámel, Maroš ; Ronzhina, Marina (referee) ; Janoušek, Oto (advisor)
The purpose of this work is to get better understanding of the problems of atrial fibrillation followed by the processing methods for detection of atrial fibrillation based on an analysis of the ventricular rhythm. Methods that are described: method of medians, methods based on histograms (using coefficient of variation and density histograms of RR and RR intervals), method using RdR map, method using complexity of RR intervals and methods based on a statistical framework by Gaussian distribution and Laplace function The practical part of this work is focused on comparing these methods and selecting the best one – method of medians is the chosen one. This is followed by implementation of this method in the Matlab and testing it on the real data from a selected database. In the end, the detection ability of our method is evaluated and compared with the thoeretical detection abilities of the other methods. Our algorithm for detection of atrial fibrillations, based on the median method, achieved excellent results with the highest value of specificity obtained at 93,976%, sensitivity at 89,182% and AUC (area under the curve) at 0,973.
|
guest ::
