A study on development of multi-parametric measure of heart rate variability diagnosing cardiovascular disease

Automated diagnosis of coronary artery disease using tunable-Q wavelet transform applied on heart rate signals

“…Various linear and nonlinear measures of heart rate signals are used for classification of control, angina pectoris and acute coronary syndrome in Table 1 Results of principal components analysis (Mean AE SD) for normal and CAD subjects after taking logarithm of absolute values of principal components. [71]. Multiple discriminant analysis coupled with the features yielded a classification accuracy of 75.0% in classifying three classes.…”

Feature extraction from a novel ECG model for arrhythmia diagnosis

“…They finally generated a sensitivity of 93.15% for normal beats and 91.07% for V arrhythmia. In paper [15], both linear (such as normalized low frequency power, normalized high frequency power, and so on) and nonlinear features (such as approximate entropy, hurst exponent, and so on) are used. They yield accuracy as high as 84.6%.…”

Automated diagnosis of Coronary Artery Disease affected patients using LDA, PCA, ICA and Discrete Wavelet Transform

“…Kim et al [30] developed a multi-parametric measure using multiple discriminant analysis of linear and nonlinear parameters extracted from the HRV signal. The ECG signals were obtained from three recumbent positions, the supine, left lateral, and right lateral positions.…”

“…Karimi et al [26] Wavelet analysis Neural network 85 Arafat et al [6] ECG Stress Signals with Probabilistic Neural Networks Fuzzy Inference Systems 80 Lee et al [33] Linear and Nonlinear Parameters SVM Classifier 90 Kim et al [30] Multiple Discriminant Analysis with linear and non linear feature Different Classifiers 72.5-84.6 Zhao and Ma [46] Emperical Mode Decomposition-Teager Energy Operator Back Propagation Neural Network 85 Lee et al [34] HRV, carotid arterial wall thickness CPAR and SVM 85-90 Babaoglu et al [7] Binary Particle Swarm Optimization SVM 81.46 Babaoglu et al [8] PCA for dimension reduction SVM 79.71 In this work HRV signals and ICA GMM 96.8…”