|
|
Use of neural networks in classification of heart diseases
Skřížala, Martin ; Tannenberg, Milan (referee) ; Hrubeš, Jan (advisor)
This thesis discusses the design and the utilization of the artificial neural networks as ECG classifiers and the detectors of heart diseases in ECG signal especially myocardial ischaemia. The changes of ST-T complexes are the important indicator of ischaemia in ECG signal. Different types of ischaemia are expressed particularly by depression or elevation of ST segments and changes of T wave. The first part of this thesis is orientated towards the theoretical knowledges and describes changes in the ECG signal rising close to different types of ischaemia. The second part deals with to the ECG signal pre-processing for the classification by neural network, filtration, QRS detection, ST-T detection, principal component analysis. In the last part there is described design of detector of myocardial ischaemia based on artificial neural networks with utilisation of two types of neural networks back – propagation and self-organizing map and the results of used algorithms. The appendix contains detailed description of each neural networks, description of the programme for classification of ECG signals by ANN and description of functions of programme. The programme was developed in Matlab R2007b.
|
|
|
Support of the patients indicated for coronary artery bypass graft surgery
KALVASOVÁ, Eliška
The bachelor thesis deals with the support of patients indicated for coronary artery bypass graft (CABG) surgery and their satisfaction with it. Psychological support of patients played an important role in preventing complications and therefore it was important to focus on the patient as a holistic human being. The objective of this bachelor thesis was to find out the method of patient education; to map the knowledge of healthy lifestyle, non-adherence to which led to indication of coronary artery bypass graft surgery; and to find out the level of mental support of patients indicated for coronary artery bypass graft surgery. To achieve these objectives, a qualitative investigation method was used, where data was further collected through semi-structured interviews with patients after coronary artery bypass graft surgery. A total of 10 patients were interviewed just after this procedure. The result of the research investigation which indicated that patients had not enough information regarding a healthy lifestyle, non-adherence to which led to the indication of coronary artery bypass graft surgery. Another shortcoming resulting from our research was the fact that patients had not have enough psychological support before the procedure, despite the fact that it was so important for physical health. However, the patient education by medical staff was satisfactory in our research. The research showed that the staff provided sufficient and good quality education in verbal as well as demonstrative form. The information booklet for patients undergoing cardiac surgery, which they all received before the procedure, was very positively evaluated by the patients as part of the education. According to the results, it was recommended that it would be appropriate to appeal to the necessity and need to offer psychological support to patients during their hospitalization as part of staff training.
|
|
|
Use of neural networks in classification of heart diseases
Skřížala, Martin ; Tannenberg, Milan (referee) ; Hrubeš, Jan (advisor)
This thesis discusses the design and the utilization of the artificial neural networks as ECG classifiers and the detectors of heart diseases in ECG signal especially myocardial ischaemia. The changes of ST-T complexes are the important indicator of ischaemia in ECG signal. Different types of ischaemia are expressed particularly by depression or elevation of ST segments and changes of T wave. The first part of this thesis is orientated towards the theoretical knowledges and describes changes in the ECG signal rising close to different types of ischaemia. The second part deals with to the ECG signal pre-processing for the classification by neural network, filtration, QRS detection, ST-T detection, principal component analysis. In the last part there is described design of detector of myocardial ischaemia based on artificial neural networks with utilisation of two types of neural networks back – propagation and self-organizing map and the results of used algorithms. The appendix contains detailed description of each neural networks, description of the programme for classification of ECG signals by ANN and description of functions of programme. The programme was developed in Matlab R2007b.
|
|
|
Problems of Keeping Non Pharmacological Treatment Measures by Clients with Arterial Hypertension
FUKOVÁ, Jitka
Hypertension is a very common cardiovascular disease. About 20-25 % of population in developed countries suffer from this problem. Long-term hypertension involves higher risk of myocardial infarction, celebrovascular accident, renal failure or eye problems. The treatment starts from non-farmacological measures connected with healthy living. The patients should stop smoking, reduce sodium, alcohol and animal fat intake, lose weight, avoid stress and improve physical training. The aim of this work is to find out if hypertensive patients know non-pharmacological measures and if they follow them. Two hypotheses were stated at the beginning: A questionnare as a quantitative research strategy was used in this work. The questionnaire consisted of 25 questions. The results were grafically processed. The questionnaire was distributed to hypertensive patients of hospital wards in Písek, cardiological clinic in Písek and general practitioners in Písek and Milevsko. The number of respondents involved in the research was 111. Hypothesis 1: Hypertensive patients do not know non-pharmacological treatment measures. Hypothesis 2: Hypertensive patients do not follow non-pharmacological measures. Analysing the data, hypertensive patients know the non-pharmacological measures very well, hypertensive patients do not follow them. Hypothesis 1 was refuted and hypothesis 2 was proved. The analysis will be offered to cooperative hospital wards and general practitioners so that it can contribute to better secondary prevention of hypertensive patients.
|
guest ::
