|
|
Identification of Abnormal ECG Segments Using Multiple-Instance Learning
Šťávová, Karolína ; Smíšek, Radovan (referee) ; Hejč, Jakub (advisor)
Heart arrhythmias are a very common heart disease whose incidence is rising. This thesis is focused on the detection of premature ventricular contractions from 12-lead ECG records by means of deep learning. The location of these arrhythmias (key instances) in the record was found using a technique based on Multiple-Instance Learning. In the theoretical part of the thesis, basic electrophysiology of the heart and deep learning with a focus on the convolutional neural networks are described. Afterward, a program was created using the Python programming language, which contains a model based on the InceptionTime architecture, using which classification of the signals into the selected classes was performed. Grad-CAM was implemented to find locations of the key instances in the ECGs. The evaluation of the arrhythmia detection quality was done using the F1 score and the results were discussed at the end of the thesis.
|
|
|
Detection of ventricular premature beats in long-term ECG
Šagát, Martin ; Kozumplík, Jiří (referee) ; Maršánová, Lucie (advisor)
The thesis deals with problems of premature ventricular complexes and ways of their detection. Heart’s basic physiological activities and the principle of their measurement are described in the theoretical part of the thesis. It deals specifically with the appearance and manifestations of ventricular extrasystoles in the ECG. The thesis also discusses various ways of detecting premature ventricular complexes. In this thesis, detection based on morphological features, wavelet transform and signal energy was used. All methods were implemented using Matlab and tested on all signals of the MIT-BIH Arrhythmia database.
|
|
|
Detection of atrial fibrillation using ECG Signals
Běhunčíková, Vendula ; Ronzhina, Marina (referee) ; Kozumplík, Jiří (advisor)
Atrial fibrillation is one of the most common cardiac rhythm disorders. The prevalence of atrial fibrillation is reported at 1-6 % of the adult population. The chances of developing atrial fibrillation increase with age. An early detection of this arrhythmia is a key to prevent more serious conditions. Many ways have been found to detect atrial fibrillation episodes in ECG including deep learning methods. The aim of this bachelor’s thesis is to describe the problem of atrial fibrillation and the methods used for detection in the ECG record, design an atrial fibrillation detector and test its results. Detector is implemented using a Matlab R2020b software.
|
|
|
controlled pacemaker
Csekes, Attila ; Hrozek, Jan (referee) ; Čech, Petr (advisor)
The Thesis deals with the area of cardio stimulation. It describes the different stimulation modes and their specifics. It describes the creation of a virtual cardio stimulator based on R-waves, designed in the LabVIEW application. Part of the thesis is the software realization of the model and the verification of its functionality.
|
|
|
Evaluation of heart arrhythmias
Šromová, Michaela ; Kozumplík, Jiří (referee) ; Provazník, Ivo (advisor)
The thesis is a brief description of the anatomy and electrophysiology of the heart. The thesis also describes the different types of electrocardiogram and cardiac arrhythmias with a description of their treatment. The next section provides design of a programme for the classification of selected types of arrhythmias, and three options for rhythm detection, using the length of RR intervals, finding extremes of P and R waves, measuring the length of intervals and heights of amplitudes. The practical part of this work was to create a rhythm classifier assigning appropriate treatment of arrhythmias, verification of its functions on the signals available from the library of arrhythmias and its evaluation.
|
|
|
Design of On Demand Cardiac Pacemaker in LabVIEW
Borovičková, Michaela ; Tannenberg,, Milan (referee) ; Sekora, Jiří (advisor)
Proposal On Demand type pacemaker for educational purposes is designed and realized in the programming environment of LabVIEW. The thesis is a general description of pacemakers with the distribution according to various criteria including the type and duration of stimulation, scope, etc. Specifically, it dealt with a type of pacemaker On Demand system and made a proposal for implementation. To compare the effectiveness of the R wave detector includes a LabVIEW implementation of three selected methods for detection of R wave and by squaring the filtered signal, detecting the filtered envelope and wavelet transform. The outcome is a virtual pacemaker stimulation pulse with adjustable amplitude and pulse width.
|
|
|
ECG arrhythmia detection
Šoltés, Tomáš ; Filipenská, Marina (referee) ; Novotná, Petra (advisor)
This bachelor thesis describes commonly present arrhytmias such as premature ventricular complex, bundle branch blocks and their detection using conventional methods and modern methods, utilising neural networks. Practical part includes: Detection of premature ventricular complexes and detection of bundle branch blocks using statistical analysis of QRS complex and their classification with K-nearest neighbors
|
|
|
ECG arrhythmia detection
Šoltés, Tomáš ; Filipenská, Marina (referee) ; Novotná, Petra (advisor)
This bachelor thesis describes commonly present arrhytmias such as premature ventricular complex, bundle branch blocks and their detection using conventional methods and modern methods, utilising neural networks. Practical part includes: Detection of premature ventricular complexes by their RR intervals and detection of bundle branch blocks using statistical analysis of QRS complex and their clustering with K-nearest neighbors
|
|
|
Evaluation of ECG in prehospital care
GROSSMANN, Matyáš
This bachelor thesis deals with the issue of ECG evaluations in pre-hospital emergency care by a paramedic. The thesis is divided into two parts, theoretical and practical. The theoretical part focuses on the definition of a paramedic and his/her competencies, instrumentation, and anatomy of the cardiac conduction system. Furthermore, it describes the methods of ECG evaluations, types of arrhythmias and their treatment in pre-hospital emergency care. The major objective of the thesis was to map the ability of paramedics to interpret the waveforms of ECG recordings. The practical part of the bachelor thesis was based on a quantitative research investigation carried out in the form of non-standardized questionnaires. The research sample consisted of 51 paramedics from the Region of South Bohemia. The research took place from March to April 2023, with the participation in it being entirely voluntary. The collected data were subsequently analysed and compiled into graphs, which were completed with a commentary. The knowledge in interpretation of ECG waveforms was mapped by a series of 24 questions in which the respondents could obtain a total of 35 points. The high knowledge of the respondents is demonstrated by the fact that three quarters of the respondents achieved 80 percent or more correct answers. Two hypotheses were determined in the research part. The first hypothesis suggested that the knowledge in interpreting ECG waveforms is affected by the length of experience. The respondents working in emergency medical services for 0-3 years had the highest score (median 93%). However, the result of the Kruskal-Waliss test revealed no statistically significant difference between the four groups compared (p = 0.51). The second hypothesis assumed that the knowledge in interpreting ECG waveforms is influenced by the type of previous workplace. The respondents who had worked in the accident and emergency department before joining the emergency medical service were the most proficient in ECG assessment and interpretation (median 96%). Here again, the Kruskal-Wallis test revealed no statistically significant difference between the four groups compared (p = 0.31). The obtained results can provide useful information for the possible implementation of an educational seminar for paramedics.
|
|
|
Needs for Electrocardiogram Evaluation by a Paramedic
PROKOP, Jakub
This bachelor's thesis deals with the issue of the needs of a paramedic in the evaluation of an electrocardiogram. In the theoretical part, the evaluation of the electrocardiogram was described, starting with the basic anatomy and physiology of the vascular supply of the heart and the conduction system of the heart. Furthermore, a description of the electrocardiograph was given, and at the end, arrhythmias with ischemic changes were evaluated. The aim was to map the abilities of paramedics in evaluating the electrocardiogram and their need for education with possible suggestions for changes in education before and after starting work. Quantitative research was used in the empirical part. Data collection was carried out using a self-structured questionnaire, in which 24 items were listed. The questions were of both open-ended and closed-ended type, with responses rated using a modified Likert scale. The questionnaire was fully anonymous and intended for paramedics from the entire Czech Republic. The basic descriptive characteristics of the research group were processed. Quantitative data were expressed by mean and standard deviation and optionally supplemented with histograms according to predefined limits. For qualitative data, frequency characteristics (absolute and relative frequencies) were processed. The results of our research investigation point to the unpreparedness of paramedics in the evaluation of pathological changes on the ECG. Respondents were also found to have a need for further training in ECG assessment and would welcome periodic training on the latest in cardiology, assessment practice at their field bases, or specialist hospital internships. To improve undergraduate education, they would include an internship in a cardiac center, practical training in a cardiology department, or professional seminars focused on EKG evaluation.
|
guest ::
