ECG pattern recognition and classification using non-linear transformations and neural networks: A review

Automatic pattern recognition in ECG time series

“…One of the most important unsolved problems in ECG analysis is (despite intensive efforts) the automatic P wave detection within long-term Holter ECG recordings [1]. The P wave corresponds to the far field induced by a specific electrical phenomenon on the cardiac surface, namely atrial depolarization.…”

“…The long-term observation, in particular, helps to characterize the underlying dynamics and is, therefore, necessary for the classification of atrial diseases. Numerous techniques ranging from digital filtering to linear and nonlinear methods [1] have been developed to recognize this specific waveform. Up to now, a reliable detection is still impossible, mainly because of the specific properties of the waveform: it has a small amplitude, it is generally deformed by offsets or contaminated with noise, its morphology has a temporal varying character, its distance to the well detectable QRS complex also varies in time, and it is represented by only a few datapoints (about 30 datapoints at a typical sampling rate of 200 Hz).…”

Applying learning algorithms to extract anxiety levels using the heart rate variability measure

“…The HRV variability obtained in this baseline ECG was submitted to the wavelets transforms and statistical measures in the present study. [2,3,25] …”

“…Thus, the potential generated by the heart during systole-diastole cycle (contraction/relaxation) can be registered by measuring the potential difference across electrodes placed on the skin surface, according to pre-established guidelines. [1][2][3] Registration is accomplished by measuring the difference in electrical potential between two points in the electric field generated by electric dipole heart during the cardiac cycle. The normal ECG consists of characteristics waves (P, Q, R, S and T -see Figure 1 [4] ) which correspond to electrical events of myocardial activation and deactivation.…”

Comparison of four methods for premature ventricular contraction and normal beat clustering

“…Some arrhythmias appear infrequently, and in order to capture them the clinicians use Holter devices. The use of specific algorithms for automatic analysis of ECG recordings may facilitate the analysis of the very long Holter ECG recordings.Several algorithms for the discrimination between normal beats (N) and premature ventricular contractions (PVC) have been proposed in literature, some of them using heart beat morphology parameters [1][2][3][4][5][6] or frequency-based parameters [7,8].In addition numerous classification methods have been studied, and they include: adaptive signal processing for on-line estimation of non-stationary signals that present a recurrent behaviour [9][10][11][12][13], linear discriminants [4,5], neural networks [14,15,3,8], fuzzy adaptive resonance theory mapping [16], operation on vectors in the multidimensional space [6] and self-organized maps [17].A particular aspect of the learning strategy is studied, paying attention to the organization of the classifiers' training set, and considering two main strategies: local learning set and global learning set [18,4,6]. In the first case the learning set is customized to the tested patient, while in the latter it is built from a large ECG database.…”