Classification of atrial fibrillation episodes from sparse electrocardiogram data

Satish Bukkapatnam, Ranga Komanduri, Hui Yang, Prahalad Rao, Wen Chen Lih, Milind Malshe, Lionel M. Raff, Bruce Benjamin, Mark Rockley

Research output: Contribution to journalArticlepeer-review

17 Scopus citations


Background: Atrial fibrillation (AF) is the most common form of cardiac arrhythmia. This paper presents the application of the Classification and Regression Tree (CART) technique for detecting spontaneous termination or sustenance of AF with sparse data. Method: Electrocardiogram (ECG) recordings were obtained from the PhysioNet (AF Termination Challenge Database 2004) Web site. Signal analysis, feature extraction, and classification were made to distinguish among 3 AF episodes, namely, Nonterminating (N), Soon (<1 minute) to be terminating (S), and Terminating immediately (<1 second) (T). Results: A continuous wavelet transform whose basis functions match the EKG patterns was found to yield compact representation (∼2 orders of magnitude). This facilitates the development of efficient algorithms for beat detection, QRST subtraction, and multiple ECG quantifier extraction (eg, QRS width, QT interval). A compact feature set was extracted through principal component analysis of these quantifiers. Accuracies exceeding 90% for AF episode classification were achieved. Conclusions: A wavelet representation customized to the ECG signal pattern was found to yield 98% lower entropies compared with other representations that use standard library wavelets. The Classification and Regression Tree (CART) technique seems to distinguish the N vs T, and the S vs T classifications very accurately.

Original languageEnglish (US)
Pages (from-to)292-299
Number of pages8
JournalJournal of Electrocardiology
Issue number4
StatePublished - Jul 2008

All Science Journal Classification (ASJC) codes

  • Cardiology and Cardiovascular Medicine


Dive into the research topics of 'Classification of atrial fibrillation episodes from sparse electrocardiogram data'. Together they form a unique fingerprint.

Cite this