Leif Sörnmo

Clustering ECG complexes using Hermite functions and self-organizing maps

An integrated method for clustering of QRS complexes is presented which includes basis function representation and self-organizing neural networks (NNs). Each QRS complex is decomposed into Hermite basis functions and the resulting coefficients and width parameter are used to represent the complex. By means of this representation, unsupervised self-organizing NNs are employed to cluster the data into 25 groups. Using the MIT-BIH arrhythmia database, the resulting clusters are found to exhibit a very low degree of misclassification (1.5%). The integrated method outperforms, on the MIT-BIH database, both a published supervised learning method as well as a conventional template cross-correlation clustering method.

Spatiotemporal QRST cancellation techniques for analysis of atrial fibrillation

A new method for QRST cancellation is presented for the analysis of atrial fibrillation in the surface electrocardiogram (ECG). The method is based on a spatiotemporal signal model which accounts for dynamic changes in QRS morphology caused, e.g., by variations in the electrical axis of the heart. Using simulated atrial fibrillation signals added to normal ECGs, the results show that the spatiotemporal method performs considerably better than does straightforward average beat subtraction (ABS). In comparison to the ABS method, the average QRST-related error was reduced to 58 percent. The results obtained from ECGs with atrial fibrillation agreed very well with those from simulated fibrillation signals.

Software QRS detection in ambulatory monitoring — a review

The QRS detection algorithm is an essential part of any computer-based system for the analysis of ambulatory ECG recordings. This review asserts that most one-channel QRS detectors described in the literature can be considered as having the same basic structure. A discussion of some of the current detection schemes is presented with regard to this structure. Some additional features of QRS detectors are mentioned. The evaluation of performance and the problem of multichannel detection, which is now gaining importance, are also briefly treated.

Principal component analysis in ECG signal processing

This paper reviews the current status of principal component analysis in the area of ECG signal processing. The fundamentals of PCA are briefly described and the relationship between PCA and Karhunen-Loève transform is explained. Aspects on PCA related to data with temporal and spatial correlations are considered as adaptive estimation of principal components is. Several ECG applications are reviewed where PCA techniques have been successfully employed, including data compression, ST-T segment analysis for the detection of myocardial ischemia and abnormalities in ventricular repolarization, extraction of atrial fibrillatory waves for detailed characterization of atrial fibrillation, and analysis of body surface potential maps.

Changes in high-frequency QRS components are more sensitive than ST-segment deviation for detecting acute coronary artery occlusion☆

OBJECTIVES This study describes changes in high-frequency QRS components (HF-QRS) during percutaneous transluminal coronary angioplasty (PTCA) and compares the ability of these changes in HF-QRS and ST-segment deviation in the standard 12-lead electrocardiogram (ECG) to detect acute coronary artery occlusion. BACKGROUND Previous studies have shown decreased HF-QRS in the frequency range of 150-250 Hz during acute myocardial ischemia. It would be important to know whether the high-frequency analysis could add information to that available from the ST segments in the standard ECG. METHODS The study population consisted of 52 patients undergoing prolonged balloon occlusion during PTCA. Signal-averaged electrocardiograms (SAECG) were recorded prior to and during the balloon inflation. The HF-QRS were determined within a bandwidth of 150-250 Hz in the preinflation and inflation SAECGs. The ST-segment deviation during inflation was determined in the standard frequency range. RESULTS The sensitivity for detecting acute coronary artery occlusion was 88% using the high-frequency method. In 71% of the patients there was ST elevation during inflation. If both ST elevation and depression were considered, the sensitivity was 79%. The sensitivity was significantly higher using the high-frequency method, p<0.002, compared with the assessment of ST elevation. CONCLUSIONS Acute coronary artery occlusion is detected with higher sensitivity using high-frequency QRS analysis compared with conventional assessment of ST segments. This result suggests that analysis of HF-QRS could provide an adjunctive tool with high sensitivity for detecting acute myocardial ischemia.

Sequential characterization of atrial tachyarrhythmias based on ECG time-frequency analysis

A new method for characterization of atrial arrhythmias is presented which is based on the time-frequency distribution of an atrial electrocardiographic signal. A set of parameters are derived which describe fundamental frequency, amplitude, shape, and signal-to-noise ratio. The method uses frequency-shifting of an adaptively updated spectral profile, representing the shape of the atrial waveforms, in order to match each new spectrum of the distribution. The method tracks how well the spectral profile fits each spectrum as well as if a valid atrial signal is present. The results are based on the analysis of a learning database with signals from 40 subjects, of which 24 have atrial arrhythmias, and an evaluation database with 211 patients diagnosed with atrial fibrillation. It is shown that the method robustly estimates fibrillation frequency and amplitude and produces spectral profiles with narrower peaks and more discernible harmonics when compared to the conventional power spectrum. The results suggest that a rather strong correlation exist between atrial fibrillation frequency and f wave shape. The developed set of parameters may be used as a basis for automated classification of different atrial rhythms.

Delineation of the QRS complex using the envelope of the e.c.g.

A new algorithm for QRS delineation has been developed. Based on the envelope of the e.c.g. signal a delineation function is defined, which yields a single positive pulse for each complex. From this function the onset and end of the QRS or, alternatively, a fiducial point is determined. To remove low-frequency component such as S-T abnormalities without distortion of the QRS complex, a filter with time-varying characteristics is used. The accuracy of the method has been evaluated in a test set of different QRS complexes obtained from coronary care patients. For QRS onset, the standard deviation of the difference between automated and manual determination was 7 ms in normal beats and 14 ms in ectopic beats. With simulated noise added to each waveform an average dispersion of 7 ms was observed in the recognition of the QRS onset at a signal-to-noise ratio of 15 dB. The corresponding dispersion in the location of a fiducial point was 2 ms. Using simulated e.c.g. data, the stability of the method is demonstrated for transitions between different waveform morphologies.

Characterization of atrial fibrillation using the surface ECG: time-dependent spectral properties

Time-frequency analysis is considered for characterizing atrial fibrillation in the surface electrocardiogram (ECG). Variations in fundamental frequency of the fibrillatory waves are tracked by using different time-frequency distributions which are appropriate to short- and long-term variations. The cross Wigner-Ville distribution is found to be particularly useful for short-term analysis due to its ability to handle poor signal-to-noise ratios. In patients with chronic atrial fibrillation, substantial short-term variations exist in fibrillation frequency and variations up to 2.5 Hz can be observed within a few seconds. Although time-frequency analysis is performed independently in each lead, short-term variations in fibrillation frequency often exhibit a similar pattern in the leads V/sub 1/, V/sub 2/ and V/sub 3/. Using different techniques for short- and long-term analysis, it is possible to reliably detect subtle long-term changes in fibrillation frequency, e.g., related to an intervention, which otherwise would have been obscured by spontaneous variations in fibrillation frequency.

A robust method for ECG-based estimation of the respiratory frequency during stress testing

A robust method is presented for electrocardiogram (ECG)-based estimation of the respiratory frequency during stress testing. Such ECGs contain highly nonstationary noise and exhibit changes in QRS morphology which, when combined with the dynamic nature of the respiratory frequency, make most existing methods break down. The present method exploits the oscillatory pattern of the rotation angles of the hearts electrical axis as induced by respiration. The series of rotation angles, obtained from least-squares loop alignment, is subject to power spectral analysis and estimation of the respiratory frequency. Robust techniques are introduced to handle the nonstationary properties of exercise ECGs. The method is evaluated by means of both simulated signals, and ECG/airflow signals recorded from 14 volunteers and 20 patients during stress testing. The resulting respiratory frequency estimation error is, for simulated signals, equal to 0.5% /spl plusmn/ 0.2%, mean /spl plusmn/ SD (0.002 /spl plusmn/ 0.001 Hz), whereas the error between respiratory frequencies of the ECG-derived method and the airflow signals is 5.9% /spl plusmn/ 4% (0.022 /spl plusmn/ 0.016 Hz). The results suggest that the method is highly suitable for analysis of noisy ECG signals recorded during stress testing.

A Method for Evaluation of QRS Shape Features Using a Mathematical Model for the ECG

Automated classification of ECG patterns is facilitated by careful selection of waveform features. This paper presents a method for evaluating the properties of features that describe the shape of a QRS complex. By examining the distances in the feature space for a class of nearly similar complexes, shape transitions which are poorly described by the feature under investigation can be readily identified. To obtain a continuous range of waveforms, which is required by the method, a mathematical model is used to simulate the QRS complexes.