Advanced Methods and Tools for ECG Data Analysis

Name: Advanced Methods and Tools for ECG Data Analysis
Brand: Artech House
Price: 139.99 EUR
Availability: OnlineOnly

Gari C. Clifford(Author)

Artech House (Publisher)

1st Edition

Published on 1. January 2006

384 pages

E-Book

PDF with Adobe-DRM

System requirements

978-1-58053-967-8 (ISBN)

€139.99incl. 7% vat

System requirements

for PDF with Adobe-DRM

E-Book Single Licence

Available for download

Description

More details

Other editions

Content

Advanced Methods and Tools for ECG Data Analysis
Contents v
Preface xi
Chapter 1 The Physiological Basis of the Electrocardiogram 1
1.1 Cellular Processes That Underlie the ECG 1
1.2 The Physical Basis of Electrocardiography 4
1.3 Introduction to Clinical Electrocardiography: Abnormal Patterns 12
1.4 Summary 24
References 24
Selected Bibliography 25
Chapter 2 ECG Acquisition, Storage, Transmission, and Representation 27
2.1 Introduction 27
2.2 Initial Design Considerations 28
2.3 Choice of Data Libraries 35
2.4 Database Analysis--An Example Using WFDB 37
2.5 ECG Acquisition Hardware 41
2.6 Summary 50
References 50
Chapter 3 ECG Statistics, Noise, Artifacts, and Missing Data 55
3.1 Introduction 55
3.2 Spectral and Cross-Spectral Analysis of the ECG 55
3.3 Standard Clinical ECG Features 60
3.4 Nonstationarities in the ECG 64
3.5 Arrhythmia Detection 67
3.6 Noise and Artifact in the ECG 69
3.7 Heart Rate Variability 71
3.8 Dealing with Nonstationarities 83
3.9 Summary 92
References 93
Chapter 4 Models for ECG and RR Interval Processes 101
4.1 Introduction 101
4.2 RR Interval Models 102
4.3 ECG Models 115
4.4 Conclusion 126
References 127
Chapter 5 Linear Filtering Methods 135
5.1 Introduction 135
5.2 Wiener Filtering 136
5.3 Wavelet Filtering 140
5.4 Data-Determined Basis Functions 148
5.5 Summary and Conclusions 167
References 167
Chapter 6 Nonlinear Filtering Techniques 171
6.1 Introduction 171
6.2 Nonlinear Signal Processing 172
6.3 Evaluation Metrics 178
6.4 Empirical Nonlinear Filtering 179
6.5 Model-Based Filtering 186
6.6 Conclusion 193
References 194
Chapter 7 The Pathophysiology Guided Assessment of T-Wave Alternans 197
7.1 Introduction 197
7.2 Phenomenology of T-Wave Alternans 197
7.3 Pathophysiology of T-Wave Alternans 197
7.4 Measurable Indices of ECG T-Wave Alternans 199
7.5 Measurement Techniques 201
7.6 Tailoring Analysis of TWA to Its Pathophysiology 207
7.7 Conclusions 211
Acknowledgments 211
References 211
Chapter 8 ECG-Derived Respiratory Frequency Estimation 215
8.1 Introduction 215
8.2 EDR Algorithms Based on Beat Morphology 218
8.3 EDR Algorithms Based on HR Information 228
8.4 EDR Algorithms Based on Both Beat Morphology and HR 229
8.5 Estimation of the Respiratory Frequency 230
8.6 Evaluation 236
8.7 Conclusions 240
References 241
Appendix 8A Vectorcardiogram Synthesis from the 12-Lead ECG 243
Chapter 9 Introduction to Feature Extraction 245
9.1 Overview of Feature Extraction Phases 245
9.2 Preprocessing 248
9.3 Derivation of Diagnostic and Morphologic Feature Vectors 251
9.4 Shape Representation in Terms of Feature-Vector Time Series 260
References 263
Appendix 9A Description of the Karhunen-Lo`eve Transform 264
Chapter 10 ST Analysis 269
10.1 ST Segment Analysis: Perspectives and Goals 269
10.2 Overview of ST Segment Analysis Approaches 270
10.3 Detection of Transient ST Change Episodes 272
10.4 Performance Evaluation of ST Analyzers 278
References 287
Chapter 11 Probabilistic Approaches to ECG Segmentation and Feature Extraction 291
11.1 Introduction 291
11.2 The Electrocardiogram 292
11.3 Automated ECG Interval Analysis 293
11.4 The Probabilistic Modeling Approach 294
11.5 Data Collection 296
11.6 Introduction to Hidden Markov Modeling 296
11.7 Hidden Markov Models for ECG Segmentation 304
11.8 Wavelet Encoding of the ECG 311
11.9 Duration Modeling for Robust Segmentations 312
11.10 Conclusions 316
References 316
Chapter 12 Supervised Learning Methods for ECG Classification/Neural Networks and SVM Approaches 319
12.1 Introduction 319
12.2 Generation of Features 320
12.3 Supervised Neural Classifiers 324
12.4 Integration of Multiple Classifiers 330
12.5 Results of Numerical Experiments 331
12.6 Conclusions 336
Acknowledgments 336
References 336
Chapter 13 An Introduction to Unsupervised Learning for ECG Classification 339
13.1 Introduction 339
13.2 Basic Concepts and Methodologies 339
13.3 Unsupervised Learning Techniques and Their Applications in ECG Classification 341
13.4 GSOM-Based Approaches to ECG Cluster Discovery and Visualization 352
13.5 Final Remarks 359
References 362
About the Authors 367
Index 371

System requirements

Save as PDF Copy link into clipboard

Schweitzer Fachinformationen

Advanced Methods and Tools for ECG Data Analysis

Description

More details

Other editions

Additional editions

Content

System requirements