Automatic detection of the electrocardiogram T-wave end

Abstract

Various methods for automatic electrocardiogram T-wave detection and Q-T interval assessment have been developed. Most of them use threshold level crossing. Comparisons with observer detection were performed due to the lack of objective measurement methods. This study followed the same approach. Observer assessments were performed on 43 various T-wave shapes recorded: (i) with 100 mm s-1 equivalent paper speed and 0.5 mV cm-1 sensitivity; and (ii) with 160 mm s-1 paper speed and vertical scaling ranging from 0.07 to 0.02 mV cm-1, depending on the T-wave amplitude. An automatic detection algorithm was developed by adequate selection of the T-end search interval, improved T-wave peak detection and computation of the angle between two 10 ms long adjacent segments along the search interval. The algorithm avoids the use of baseline crossing and direct signal differentiation. It performs well in cases of biphasic and/or complex T-wave shapes. Mean differences with respect to observer data are 13.5 ms for the higher gain/speed records and 14.7 ms for the lower gain/speed records. The algorithm was tested with 254 various T-wave shapes. Comparisons with two other algorithms are presented. The lack of a 'gold standard' for the T-end detection, especially if small waves occur around it, impeded adequate interobserver assessment and evaluation of automatic methods. It is speculated that a simultaneous presentation of normal and high-gain records might turn more attention to this problem. Automatic detection methods are in fact faced with 'high-gain' data, as high-resolution analogue-to-digital conversion is already widely used.

A review of beat-to-beat vectorcardiographic (VCG) parameters for analyzing repolarization variability in ECG signals

“…The main reason may the computational feasibility with fewer errors in the parameters (TCRT/TMD) compared to other ECG parameters. One of the critical problems is in finding an accurate T-wave end for extracting other non-invasive ECG parameters for risk stratification [20,56], which is considered to be a major source of inaccuracy in automatic QT extracted measurements [48,52]. Proper identification of T-wave offset becomes a difficult task because of the slow transition of cardiac cells to the termination of the ventricular repolarization process, where accurate localization of the T-wave end point becomes a challenging task.…”

New approach for T-wave end detection on electrocardiogram: Performance in noisy conditions

“…Various methods have been proposed for detection of Tend point based on: intersection of lines [5], threshold on the amplitude of T wave [6], threshold on the first derivative of ECG signal [7], computation of: distances [8], angles [9] and areas [10], correlation with a template [11], mathematical models of ECG [12], and wavelet transform [13], among others methods. All have some advantages and some drawbacks in relation to complexity, computational cost, waveforms morphological variations, noise sensitivity and Tend dependence on threshold.…”

Estimation and Modeling of QT-Interval Adaptation to Heart Rate Changes

“…Classical segmentation methods are based on filtering the derivative of the ECG [22]- [25], on wavelet transform [26]- [30], or on an indicator related to the area covered by the T wave [31]. The major drawback of these methods lies in their sensitivity to noise.…”

“…Several algorithms for automated measurement have been proposed to locate QRS onsets and ends and QT interval limits. Classical segmentation methods are based on filtering the derivative of the ECG [22]- [25], or on wavelet transform [26]- [30]. The advantage of the methods based on derivative filtering lies in their robustness to variations in the morphology of the ECG waves.…”