In this paper, we developed and evaluated a robust single-lead electrocardiogram (ECG) delineation system based on the wavelet transform (WT). In a first step, QRS complexes are detected. Then, each QRS is delineated by detecting and identifying the peaks of the individual waves, as well as the complex onset and end. Finally, the determination of P and T wave peaks, onsets and ends is performed. We evaluated the algorithm on several manually annotated databases, such as MIT-BIH Arrhythmia, QT, European ST-T and CSE databases, developed for validation purposes. The QRS detector obtained a sensitivity of Se=99.66% and a positive predictivity of P+=99.56% over the first lead of the validation databases (more than 980,000 beats), while for the well-known MIT-BIH Arrhythmia Database, Se and P+ over 99.8% were attained. As for the delineation of the ECG waves, the mean and standard deviation of the differences between the automatic and manual annotations were computed. The mean error obtained with the WT approach was found not to exceed one sampling interval, while the standard deviations were around the accepted tolerances between expert physicians, outperforming the results of other well known algorithms, especially in determining the end of T wave.

In this paper, we studied and validated a simple heart beat classifier based on ECG feature models selected with the focus on an improved generalization capability. We considered features from the RR series, as well as features computed from the ECG samples and different scales of the wavelet transform, at both avail able leads. The classification performance and generalization were studied using publicly available databases: the MIT-BIH Arrhythmia, the MIT-BIH Supraventricular Arrhythmia, and the St. Pe tersburg Institute of Cardiological Technics (INCART) databases. The Association for the Advancement of Medical Instrumentation recommendations for class labeling and results presentation were followed. A floating feature selection algorithm was used to obtain the best performing and generalizing models in the training and validation sets for different search configurations. The best model found comprehends eight features, was trained in a partition of the MIT-BIH Arrhythmia, and was evaluated in a completely disjoint partition of the same database. The results obtained were: global accuracy of 93%; for normal beats, sensitivity (S) 95%, positive predictive value (P⁺) 98%; for supraventricular beats, S 11%, P⁺ 39%; and for ventricular beats S 81%, P⁺ 87%. In order to test the generalization capability, performance was also evaluated in the INCART, with results comparable to those obtained in the test set. This classifier model has fewer features and performs better than other state-of-the-art methods with results suggesting better generalization capability.

This study tackles the ECG classification problem by means of a methodology, which is able to enhance classification performance while simultaneously reducing the computational resources, making it specially adequate for its application in the improvement of ambulatory settings. For this purpose, the sequential forward floating search (SFFS) algorithm is applied with a new criterion function index based on linear discriminants. This criterion has been devised specifically to be a quality indicator in ECG arrhythmia classification. Based on this measure, a comprehensive feature set is analyzed with the SFFS algorithm, and the most suitable subset returned is additionally evaluated with a multilayer perceptron (MLP) to assess the robustness of the model. Aiming at obtaining meaningful estimates of the real-world performance and facilitating comparison with similar studies, the present contribution follows the Association for the Advancement of Medical Instrumentation standard EC57:1998 and the same interpatient division scheme used in several previous studies. Results show that by applying the proposed methods, the performance obtained in similar studies under the same constraints can be exceeded, while keeping the requirements suitable for ambulatory monitoring.

In this paper, we present a patient-adaptable algorithm for ECG heartbeat classification, based on a previously developed automatic classifier and a clustering algorithm. Both classifier and clustering algorithms include features from the RR interval series and morphology descriptors calculated from the wavelet transform. Integrating the decisions of both classifiers, the presented algorithm can work either automatically or with several degrees of assistance. The algorithm was comprehensively evaluated in several ECG databases for comparison purposes. Even in the fully automatic mode, the algorithm slightly improved the performance figures of the original automatic classifier; just with less than two manually annotated heartbeats (MAHB) per recording, the algorithm obtained a mean improvement for all databases of 6.9% in accuracy A, of 6.5% in global sensitivity S and of 8.9% in global positive predictive value P⁺. An assistance of just 12 MAHB per recording resulted in a mean improvement of 13.1% in A, of 13.9% in S, and of 36.1% in P⁺. For the assisted mode, the algorithm outperformed other state-of-the-art classifiers with less expert annotation effort. The results presented in this paper represent an improvement in the field of automatic and patient-adaptable heartbeats classification, concluding that the performance of an automatic classifier can be improved with an efficient handling of the expert assistance.

T-wave alternans (TWA) is a cardiac phenomenon associated with the mechanisms leading to sudden cardiac death. Several methods exist to automatically detect and estimate TWA in the ECG on a single-lead basis, and their main drawback is their poor sensitivity to low-amplitude TWA. In this paper, we propose a multilead analysis scheme to improve the detection and estimation of TWA. It combines principal component analysis with a single-lead method based on the generalized likelihood ratio test. The proposed scheme is evaluated and compared to a single-lead scheme by means of a simulation study, in which different types of simulated and physiological noise are considered under realistic conditions. Simulation results show that the multilead scheme can detect TWA with an SNR 30 dB lower and allows the estimation of TWA with an SNR 25 dB lower than the single-lead scheme. The two analysis schemes are also applied to stress test ECG records. Results show that the multilead scheme provides a higher detection power and that TWA detections obtained with this scheme are significantly different in healthy volunteers and ischemic patients, whereas they are not with the single-lead scheme.