Heart failure is a common disease which is difficult to diagnose. To aid physicians in diagnosing heart failure, a decision support system has been proposed. Parameters useful to the system are suggested. Some of these, such as age and gender, should be provided by the physician, and some should be derived from electro- and phonocardiographic signals.Various methods of signal processing, such as wavelet theory and principal components analysis, are described. Heart failure should be diagnosed based on the parameters, and so various forms of decision support systems, such as neural networks and support vector machines, are described. The methods of signal processing and classification are discussed and suggestions on how to develop the system are made.
Contents
1 Introduction
1.1 Background
1.2 Aim
1.3 Materials and methods
1.4 Limitations
1.5 Outline of the thesis
2 Anatomy and physiology of the heart
2.1 Circulation of blood
2.2 The conduction system
2.3 Electrocardiography
2.4 Phonocardiography
3 Time frequency analysis
3.1 The wavelet transform
3.2 Multiresolution representation
4 Characteristics of a heart failure patient
4.1 Heart failure
4.2 Diagnosing heart failure
4.3 Common signs and symptoms
4.4 Signs and symptoms present in systolic heart failure
4.5 Signs and symptoms present in diastolic heart failure
4.6 Summary of parameters
5 Extracting visible features
5.1 Pre-processing of the ECG signal
5.2 Left ventricular hypertrophy
5.3 Left bundle branch block
5.4 Myocardial ischemia
5.5 Arrhythmias
5.5.1 Atrial fibrillation
5.5.2 Premature ventricular contractions
6 Extracting invisible features
6.1 Heart rate variability analysis
6.1.1 Spectral analysis
6.1.2 Detrended fluctuation analysis
6.1.3 Multiresolution wavelet analysis
6.2 High frequency, low amplitude parameters
6.2.1 Ventricular late potentials
6.2.2 P wave duration
6.3 T wave alternans
7 Extracting features with wavelets
7.1 Using wavelet coefficients
7.2 Using a tailored wavelet
8 Principal components analysis
9 Neural networks
9.1 Multilayer perceptrons
9.2 Radial-basis function networks
10 Support vector machines
11 Committee machines
11.1 Ensemble averaging
11.2 Bagging
11.3 Boosting
11.4 Mixtures of experts
12 Self-organising maps
13 Clinical decision support systems
13.1 Model selection
13.2 Some examples of decision support systems
14 Discussion
14.1 General demands
14.2 Feature selection
14.3 Using the features
14.4 System selection
14.5 Summary
14.6 Usefulness
14.7 Future work
References
Author: Olsson, Linda
Source: Linköping University
Download URL 2: Visit Now