Limits...
Cardiac arrhythmia classification using autoregressive modeling.

Ge D, Srinivasan N, Krishnan SM - Biomed Eng Online (2002)

Bottom Line: AR modeling results showed that an order of four was sufficient for modeling the ECG signals.The results show that AR modeling is useful for the classification of cardiac arrhythmias, with reasonably high accuracies.Further validation of the proposed technique will yield acceptable results for clinical implementation.

View Article: PubMed Central - HTML - PubMed

Affiliation: Biomedical Engineering Research Centre, Nanyang Technological University, Singapore 639798. gedingfei@hotmail.com

ABSTRACT

Background: Computer-assisted arrhythmia recognition is critical for the management of cardiac disorders. Various techniques have been utilized to classify arrhythmias. Generally, these techniques classify two or three arrhythmias or have significantly large processing times. A simpler autoregressive modeling (AR) technique is proposed to classify normal sinus rhythm (NSR) and various cardiac arrhythmias including atrial premature contraction (APC), premature ventricular contraction (PVC), superventricular tachycardia (SVT), ventricular tachycardia (VT) and ventricular fibrillation (VF).

Methods: AR Modeling was performed on ECG data from normal sinus rhythm as well as various arrhythmias. The AR coefficients were computed using Burg's algorithm. The AR coefficients were classified using a generalized linear model (GLM) based algorithm in various stages.

Results: AR modeling results showed that an order of four was sufficient for modeling the ECG signals. The accuracy of detecting NSR, APC, PVC, SVT, VT and VF were 93.2% to 100% using the GLM based classification algorithm.

Conclusion: The results show that AR modeling is useful for the classification of cardiac arrhythmias, with reasonably high accuracies. Further validation of the proposed technique will yield acceptable results for clinical implementation.

Show MeSH

Related in: MedlinePlus

A patient ECG and simulated ECG with SVT
© Copyright Policy
Related In: Results  -  Collection


getmorefigures.php?uid=PMC149374&req=5

Figure 6: A patient ECG and simulated ECG with SVT

Mentions: Two main criteria, SNR and ρ were used to evaluate the performance of the AR model with different model orders. The correction coefficients for all ECG signals were 0.99. The SNR was calculated to be from 15.7 dB to 29.43 dB. Figure 2 shows the variation of SNR as a function of model order P. The SNR increased initially with model order P, but remains almost constant for model orders greater than or equal to four. In addition, computing the AR coefficients of higher orders would increase the number of computations. Hence, AR model of order four was used for further classification. The parameters computed using this model order were good enough to achieve a good SNR and correlation coefficient ρ and were found to be sensitive enough to differentiate the five types of ECG signals. The original NSR, APC, PVC, SVT, VT and VF segments as well as the modeled segments are shown in Figs 3,4,5,6,7 and 8.


Cardiac arrhythmia classification using autoregressive modeling.

Ge D, Srinivasan N, Krishnan SM - Biomed Eng Online (2002)

A patient ECG and simulated ECG with SVT
© Copyright Policy
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC149374&req=5

Figure 6: A patient ECG and simulated ECG with SVT
Mentions: Two main criteria, SNR and ρ were used to evaluate the performance of the AR model with different model orders. The correction coefficients for all ECG signals were 0.99. The SNR was calculated to be from 15.7 dB to 29.43 dB. Figure 2 shows the variation of SNR as a function of model order P. The SNR increased initially with model order P, but remains almost constant for model orders greater than or equal to four. In addition, computing the AR coefficients of higher orders would increase the number of computations. Hence, AR model of order four was used for further classification. The parameters computed using this model order were good enough to achieve a good SNR and correlation coefficient ρ and were found to be sensitive enough to differentiate the five types of ECG signals. The original NSR, APC, PVC, SVT, VT and VF segments as well as the modeled segments are shown in Figs 3,4,5,6,7 and 8.

Bottom Line: AR modeling results showed that an order of four was sufficient for modeling the ECG signals.The results show that AR modeling is useful for the classification of cardiac arrhythmias, with reasonably high accuracies.Further validation of the proposed technique will yield acceptable results for clinical implementation.

View Article: PubMed Central - HTML - PubMed

Affiliation: Biomedical Engineering Research Centre, Nanyang Technological University, Singapore 639798. gedingfei@hotmail.com

ABSTRACT

Background: Computer-assisted arrhythmia recognition is critical for the management of cardiac disorders. Various techniques have been utilized to classify arrhythmias. Generally, these techniques classify two or three arrhythmias or have significantly large processing times. A simpler autoregressive modeling (AR) technique is proposed to classify normal sinus rhythm (NSR) and various cardiac arrhythmias including atrial premature contraction (APC), premature ventricular contraction (PVC), superventricular tachycardia (SVT), ventricular tachycardia (VT) and ventricular fibrillation (VF).

Methods: AR Modeling was performed on ECG data from normal sinus rhythm as well as various arrhythmias. The AR coefficients were computed using Burg's algorithm. The AR coefficients were classified using a generalized linear model (GLM) based algorithm in various stages.

Results: AR modeling results showed that an order of four was sufficient for modeling the ECG signals. The accuracy of detecting NSR, APC, PVC, SVT, VT and VF were 93.2% to 100% using the GLM based classification algorithm.

Conclusion: The results show that AR modeling is useful for the classification of cardiac arrhythmias, with reasonably high accuracies. Further validation of the proposed technique will yield acceptable results for clinical implementation.

Show MeSH
Related in: MedlinePlus