A multidifferentiator-based approach to the reliable determination of T-wave offset in electrocardiograms

The determination of T-wave offset is still a very difficult task in the measurement of the QT interval. Several methods of determining the T-wave offset can be categorized into slope methods, threshold methods, or differential methods. The threshold- and slope-based methods are sensitive to low-frequency noise. The differential methods, in which a single differential operation is usually used for feature extraction, are susceptible to morphological variations in the range of the T-wave offset. In this study, a multidifferential filter comprising a series of simple multiscale differentiators with multiorders is proposed as a feature selector and extractor for T-wave offset in electrocardiograms (ECGs). This newly proposed approach was tested on artificial ECGs (the Conformance Testing Services for Computerized Electrocardiography Test data set: 1919 ECGs were generated with signal-to-noise ratios ranging from 10 to 60 dB, in increments of 0.5 dB, with 172,306 T waves with specified references) simulated at various noise levels and a set of clinical ECGs (3415 ECGs with 14,099 T waves, annotated by 3 cardiologists) and compared with existing detection methods. The accuracies achieved with the proposed approach were -0.269 ± 5.53 and 0.400 ± 9.89 milliseconds for the artificial and clinical ECGs, respectively. These test results indicate that the proposed method outperforms the other methods evaluated on both the artificial and clinical ECGs. The proposed approach is also more suitable for clinical applications in accordance with the performance requirements of the International Electrotechnical Commission.