Abstract
ECG heartbeat type detection and classification are regarded as important procedures since they can significantly help to provide an accurate automated diagnosis. This paper addresses the specific problem of detecting atrial premature beats, that had been demonstrated to be a marker for stroke risk or cardiac arrhythmias. The proposed methodology consists of a stage to estimate characteristics such as morphology of P wave and QRS complex as well as indices of prematurity and a non-supervised stage used by the algorithm J-means to separate heartbeat feature vectors into classes. Partition initialization is carried out by a Max–Min approach. Experimental data set is taken from MIT-BIH arrhythmia database. Results evidence the reliability of the method since achieved sensitivity and specificity are high, 92.9 and 99.6%, respectively, for an average output number of 12 discovered clusters that can be considered as appropriate value to separate heartbeat classes from recordings.
Similar content being viewed by others
References
Ahlstrom M, Tompkins J (1985) Digital filters for real-time ecg signal processing using microprocessors. IEEE Trans Biomed Eng 32(9):708–713
Association AH (2007) Premature beats. http://www.americanheart.org
Bahmanyar M, Balachandran W (2005) Beat to beat classification of long electrocardiograms using entropies and hierarchical clustering. In: Proceedings of the 2005 IEEE engineering in medicine and biology 27th annual conference. IEEE, IEEE, Shanghai, China, pp 5579–5581
Cuesta-Frau D, Biagetti M, Micó-Tormos RQP, Aboy M (2007) Unsupervised classification of ventricular extrasystoles using bounded clustering algorithms and morphology matching. Med Biol Eng Comput 45(3):229–239
Cuesta D, Pérez-Cortés J, Andreu-García G (2003) Clustering of ecg signals in computer-aided holter analysis. Comput Methods Programs Biomed 72:179–196
De-Chazal P, O’Dwyer M, Reilly R (2004) Automatic classification of heartbeats using ecg morphology and heartbeat interval features. IEEE Trans Biomed Eng 51(7):1196–1206
Engström G, Hedblad B, Juul-Möller S, Tydén P, Janzon L (2000) Cardiac arrhythmias and stroke increased risk in men with high frequency of atrial ectopic beats. Stroke, American Heart Association, London, pp 2925–2929
Goodacre S, Irons R (2002) Abc of clinical electrocardiography, atrial arrhythmias. BMG 324:594–597
Hansen P, Mladenovic N (2001) J-means: a new local search heuristic for minimum sum of squares clustering. Pattern Recognit 34:405–413
Jain A, Murty M, Flynn P (1999) Data clustering: A review. ACM Comput Surv 31(3):265–323
Lagerholm M, Peterson C, Braccini G, Edenbrandt L, Sörnmo L (2000) Clustering ecg complexes using hermite functions and self-organising maps. IEEE Trans Biomed 48:838–847
Mark R, Moody G (1997) Mit-bih arrhythmia database. http://ecg.mit.edu/dbinfo.html
Roddy A (1991) A filter to suppress ecg baseline wander and preserve st-segment accuracy in a real-time environment. J Electrocardiol 24(4):315–323
Sahambi JS, Tandon SN, Bhatt RP (1997) Using wavelet transform for ecg charecterization. IEEE Trans Eng Med Biol 16:77–88
So H (1998) On adaptive cancellation of multiple interfering sinusoids. Tech. rep., University of Hong Kong, Tat Chee Avenue, Kowloon, Hong Kong
Talman W (2001) Atrial ectopic beats: another risk factor for stroke. J Watch Neurol 221:1
Wallmann D, Tüller D, Wustmann K, Meier P, Isenegger J, Arnold M, Mattle H, Delacrétaz E (2007) Frequent atrial premature beats predict paroxysmal atrial fibrillation in stroke patients: An opportunity for a new diagnostic strategy. STROKE J Am Heart Assoc 38:2292–2294
Acknowledgments
This research is carried out under Grants: Técnicas de computación de alto rendimiento en la interpretación de Bioseñales 20201004224, funded by Universidad Nacional de Colombia, Manizales.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Rodríguez-Sotelo, J.L., Cuesta-Frau, D. & Castellanos-Dominguez, G. Unsupervised classification of atrial heartbeats using a prematurity index and wave morphology features. Med Biol Eng Comput 47, 731–741 (2009). https://doi.org/10.1007/s11517-009-0435-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11517-009-0435-2