A real time QRS complex classification method using Mahalanobis distance

Moraes, J.C.T.B.; Seixas, M.O.; Vilani, F.N.; Costa, E.V.

doi:10.1109/cic.2002.1166742

Cited by 42 publications

(21 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The achieved statistical indices are comparable or even better than the performance of embedded algorithms in ECG monitoring devices available on the market, 15 as well as than published results of other authors who use morphological, time-frequency, and/ or RR interval ECG features, and test their methods with almost all files in MIT-BIH [2][3][4]14,19 (see Table 4). Although commercially available systems facilitate the manual editing by automatic initial learning of the patient's normal QRS morphology, the presence of artifacts could considerably increase the number of template classes and therefore, both the computations and the memory used, as well as the time spent for expert annotations.…”

Section: Discussionsupporting

confidence: 63%

QRS Template Matching for Recognition of Ventricular Ectopic Beats

Krasteva

Jekova

2007

Ann Biomed Eng

View full text Add to dashboard Cite

We propose a quasi real-time method for discrimination of ventricular ectopic beats from both supraventricular and paced beats in the electrocardiogram (ECG). The heartbeat waveforms were evaluated within a fixed-length window around the fiducial points (100 ms before, 450 ms after). Our algorithm was designed to operate with minimal expert intervention and we define that the operator is required only to initially select up to three 'normal' heartbeats (the most frequently seen supraventricular or paced complexes). These were named original QRS templates and their copies were substituted continuously throughout the ECG analysis to capture slight variations in the heartbeat waveforms of the patient's sustained rhythm. The method is based on matching of the evaluated heartbeat with the QRS templates by a complex set of ECG descriptors, including maximal cross-correlation, area difference and frequency spectrum difference. Temporal features were added by analyzing the R-R intervals. The classification criteria were trained by statistical assessment of the ECG descriptors calculated for all heartbeats in MIT-BIH Supraventricular Arrhythmia Database. The performance of the classifiers was tested on the independent MIT-BIH Arrhythmia Database. The achieved unbiased accuracy is represented by sensitivity of 98.4% and specificity of 98.86%, both being competitive to other published studies. The provided computationally efficient techniques enable the fast post-recording analysis of lengthy Holter-monitor ECG recordings, as well as they can serve as a quasi real-time detection method embedded into surface ECG monitors.

show abstract

Section: Discussionsupporting

confidence: 63%

QRS Template Matching for Recognition of Ventricular Ectopic Beats

Krasteva

Jekova

2007

Ann Biomed Eng

View full text Add to dashboard Cite

show abstract

“…Distance measures widely used in the time domain ECG classification algorithms include the L 1 -norm (city block) [4], L 2 -norm (Euclidean distance) [3,5] normalized cross correlation [6], likelihood function [7], and Mahalanobis distance [8]. In Mahalanobis distance, the covariance matrices can be hard to determine accurately, and the memory and the time requirements grow quadratically rather than linearly with the number of features.…”

Section: Biomedical Engineering-applications Basis and Communicationsmentioning

confidence: 99%

A Comparison of Similarity Measures for Clustering of QRS Complexes

Chang

Cheng

Yeh

et al. 2005

Biomed. Eng. Appl. Basis Commun.

View full text Add to dashboard Cite

show abstract

“…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].…”

Section: Introductionmentioning

confidence: 99%

“…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.…”

mentioning

confidence: 99%

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

Bortolan

Jekova

Christov

2005

Computers in Cardiology, 2005

View full text Add to dashboard Cite

The learning capacity and the classification ability for normal beats and premature ventricular contractions clustering by four classification methods were compared: neural networks (NN), K-th nearest neighbour rule (Knn), discriminant analysis (DA) and fuzzy logic (FL). IntroductionDetection and classification of different types of heartbeats in the electrocardiogram (ECG) is of major importance in the diagnosis of cardiac dysfunctions. 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. The local learning set requires a cardiologist to annotate a set of normal (N) and premature ventricular contraction (PVC) heart beats of the patient under consideration. On the other hand, the capacity of the global learning set to classify new records without additional training is balanced by a lower accuracy, since the morphology of N and PVC differ not only from patient to patient, but also from lead to lead of a same individual.In the present work, the local and global classifiers were investigated, considering 26 morphology heart beat parameters for the classification of normal beats and premature ventricular contractions in the electrocardiogram. For this purpose, the learning capacity and the classification ability of four classification methods were compared: neural networks (NN), K-th nearest neighbour rule (Knn), discriminant analysis (DA) and fuzzy logic (FL). 2.Methods and material ECG databaseAll 48 ECG recordings from the Massachusetts Institute of Technology -Beth Israel Hospital (MIT-BIH) arrhythmia database were used. Each recording has a duration of 30 min and includes two leads -the modified limb lead II and one of the modified leads V1, V2, V4 or V5 [19]. The sampling frequency is 360 Hz and the resolution is 200 samples per mV. Two cardiologists have annotated all beats in the database. Approximately 70% of the beats have been a...

show abstract

A real time QRS complex classification method using Mahalanobis distance

Cited by 42 publications

References 4 publications

QRS Template Matching for Recognition of Ventricular Ectopic Beats

QRS Template Matching for Recognition of Ventricular Ectopic Beats

A Comparison of Similarity Measures for Clustering of QRS Complexes

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

Contact Info

Product

Resources

About