|
|
Application of neural networks for classification of T-wave alternations
Procházka, Tomáš ; Harabiš, Vratislav (referee) ; Hrubeš, Jan (advisor)
This thesis deals with analysis of T-wave Alternans (TWA), periodical changes of T wave in ECG signal. Presence of these alternans may predict higher risk of sudden cardiac death. From the several possible ways of TWA classification, the training algorithms of self organizing maps are used in this thesis. Result of the thesis is a program, which in the first step detects QRS complexes in the signal. Then, in the next step, gained reference points are used for T-waves detection. Detected waves are represented by a vector of significant points, which is used as an input for artificial neural network. Final output of the program is a decision about presence of TWA in the signal and its rate.
|
|
|
ST-T segments analysis of ECG signals with focusing on T-wave alternance
Tannenberg, Milan ; Sovka, Pavel (referee) ; Tyšler,, Milan (referee) ; Kozumplík, Jiří (advisor)
The Cardiovascular diseases may evocated the high percentual risk of sudden cardiac death in whole world. In several western countries is the number of death higher then number of cancer death. In this time is used a lot of methods for prediction of sudden cardiac death with focus on ECG T-wave alternance. The aim of the theses was to do stronger relation and cooperation with Internal Cardiac Clinic of Faculty Hospital Brno Bohunice on the risk analysis of sudden cardiac death. Secondly, we met the methods used for detection and quantification of simulated TWA. Last but not least was necessary to find TWA detection methods improvement and process the data on real signals obtained from Faculty Hospital Brno Bohunice. First part of the Thesis is focused on summary of pathologic artifacts in ECG signal, which are important for sudden cardiac risk stratification. There are described further known detection and quantification methods for TWA analysis. An interesting part for clinical practice is analysis of TWA trend in time and looking for the best method, which is able to catch and track the short TWA trend changes. Second part describes the new methods improvements, which were tested with interesting outputs. Further, there was developed method for TWA presence statement probability evaluation.
|
|
|
Analysis of T wave alternations in programming language C - Radek Poul
Poul, Radek ; Vítek, Martin (referee) ; Rychtárik, Milan (advisor)
The thesis deals with detection of T-wave alternans. The presence of T-wave in surface ECG is recognized as a marker of electrical instability of heart in stage his repolarization, arise increased risk of emergence ventricular fibrillation and sudden cardiac death. The goal of our project is familiarize with methods of detection T-wave alternans. In particular spectral method and spectral method which was realized in variant for running reading values in time (“sliding window”). To suggest a QRS complex detector, localize the T-wave and to make TWA detection using spectral method and modified spectral method. This project is to be made in C language in appropriate user interface.
|
|
| |
|
| |
|
|
ST-T segments analysis of ECG signals with focusing on T-wave alternance
Tannenberg, Milan ; Sovka, Pavel (referee) ; Tyšler,, Milan (referee) ; Kozumplík, Jiří (advisor)
The Cardiovascular diseases may evocated the high percentual risk of sudden cardiac death in whole world. In several western countries is the number of death higher then number of cancer death. In this time is used a lot of methods for prediction of sudden cardiac death with focus on ECG T-wave alternance. The aim of the theses was to do stronger relation and cooperation with Internal Cardiac Clinic of Faculty Hospital Brno Bohunice on the risk analysis of sudden cardiac death. Secondly, we met the methods used for detection and quantification of simulated TWA. Last but not least was necessary to find TWA detection methods improvement and process the data on real signals obtained from Faculty Hospital Brno Bohunice. First part of the Thesis is focused on summary of pathologic artifacts in ECG signal, which are important for sudden cardiac risk stratification. There are described further known detection and quantification methods for TWA analysis. An interesting part for clinical practice is analysis of TWA trend in time and looking for the best method, which is able to catch and track the short TWA trend changes. Second part describes the new methods improvements, which were tested with interesting outputs. Further, there was developed method for TWA presence statement probability evaluation.
|
|
|
Application of neural networks for classification of T-wave alternations
Procházka, Tomáš ; Harabiš, Vratislav (referee) ; Hrubeš, Jan (advisor)
This thesis deals with analysis of T-wave Alternans (TWA), periodical changes of T wave in ECG signal. Presence of these alternans may predict higher risk of sudden cardiac death. From the several possible ways of TWA classification, the training algorithms of self organizing maps are used in this thesis. Result of the thesis is a program, which in the first step detects QRS complexes in the signal. Then, in the next step, gained reference points are used for T-waves detection. Detected waves are represented by a vector of significant points, which is used as an input for artificial neural network. Final output of the program is a decision about presence of TWA in the signal and its rate.
|
|
|
Analysis of T wave alternations in programming language C - Radek Poul
Poul, Radek ; Vítek, Martin (referee) ; Rychtárik, Milan (advisor)
The thesis deals with detection of T-wave alternans. The presence of T-wave in surface ECG is recognized as a marker of electrical instability of heart in stage his repolarization, arise increased risk of emergence ventricular fibrillation and sudden cardiac death. The goal of our project is familiarize with methods of detection T-wave alternans. In particular spectral method and spectral method which was realized in variant for running reading values in time (“sliding window”). To suggest a QRS complex detector, localize the T-wave and to make TWA detection using spectral method and modified spectral method. This project is to be made in C language in appropriate user interface.
|
|
|
Patients with implanted cardioverter defibrillators
HEŘMANSKÁ, Marie
This Bachelor Thesis deals with the issue of implantable cardioverter defibrillator usage, namely with the impact of implantable cardioverter defibrillator on patient life and the details of nursing care in scope of implantation of these devices. The implantable cardioverter defibrillator (hereinafter referred as to "ICD") enables to prevent or avert heart failure which affects approximately 2 % of population. Nearly 3/4 of cases of sudden death take place at home and 2/3 of these cases are witnessed by other person. Indications for the ICD implantation are severe malignant ventricular tachycardia (ventricular tachycardia, fibrillation and chamber flutter) which rapidly lead to the circulation failure, unconsciousness and, finally, death. The rapid termination of such arrhythmias by ICD saves the life of its holder. The diagnostics shall commence by the standard electrocardiogram (ECG). The field study of the Bachelor Thesis includes results of the qualitative research based on the semi structured interview. The research group contained thirteen patients with implantable cardioverter defibrillator, residing in Středočeský kraj (Central Bohemia Region) and Jihočeský kraj (South Bohemia Region), who have had their ICD at least for a year. All respondents were asked ten basic questions as a part of the interview. The interviews were recorded over voice recorder and subsequently were directly transcribed to text. The interviews were processed while using the open coding, paper and pencil method. The data analysis produced five categories: Difficulties before the implementation of ICD, Changes in lifestyle after the implementation of ICD (with subcategories of Life certainties, Common activities, Employment, Driving and State of mind), Defibrillator shock, Nursing care and Importance of ICD for patients. The research shows that patients are predominantly satisfied with the nursing care. Nearly all respondents do not feel the need for increased nursing care while being in hospital. Patients greatly appreciated the wound care all respondents were satisfied with this precise type of care as no complications did occur while healing and the wounds healed per primam. I see imperfections in the patient education although ten patients state that they were duly informed, they were informed only by their doctor. Only one patient states that he was given "certain" information from the nurse. However, these results may be misrepresented by patients due to the time lapse (from the hospitalization). Furthermore, the research shows that ICD device does not influence common activities of majority of respondents. Nearly all respondents experience mental relief and the improvement of life quality. The respondents do not consider the restriction connected to the ICD usage to be negative. The majority of them try to observe given advices (in scope of driving, travelling, magnetic security systems, etc.) which do not restrict them in their common life significantly. Even though their disease is severe and endangers their life, the patients with these devices may travel abroad, do sports, work and live their normal life with less risk of sudden heart failure. Twelve respondents out of thirteen consider the ICD to be of great significance to their life. The outcome of this Bachelor Thesis is the Guide for ICD Patients.
|
|
| |
guest ::
