Transient ST-Segment Episode Detection for ECG Beat Classification

Suma Bulusu, Miad Faezipour, Vincent Ng, Mehrdad Nourani, Lakshman Tamil, and Subhash Banerjee.
Proceedings of the IEEE/NIH 5th Life Science Systems and Application Workshop, pp. 121-124, 2011.

Click here for the PDF version.

Abstract

Sudden Cardiac Death (SCD) is an unexpected death caused by loss of heart function when the electrical impulses fired from the ventricles become irregular. Most common SCDs are caused by cardiac arrhythmias and coronary heart disease. They are mainly due to Acute Myocardial Infarction (AMI), myocardial ischaemia and cardiac arrhythmia. This paper aims at automating the recognition of ST-segment deviations and transient ST episodes which helps in the diagnosis of myocardial ischaemia and also classifying major cardiac arrhythmia. Our approach is based on the application of signal processing and artificial intelligence to the heart signal known as the ECG (Electrocardiogram). We propose an improved morphological feature vector including ST-segment information for heart beat classification by supervised learning using the support vector machine learning approach. Our system has been tested and yielded an accuracy of 93.33% for the ST episode detection on the European ST-T Database and 96.35% on MIT-BIH Arrhythmia Database for classifying six major groups, i.e., Normal, Ventricular, Atrial, Fusion, Right Bundle and Left Bundle Branch Block beats.

BibTeX entry

@InProceedings{Balusu+etal:11a,
  author = {Suma Bulusu and Miad Faezipour and Vincent Ng and Mehrdad Nourani and Lakshman Tamil and Subhash Banerjee},
  title = {Transient ST-Segment Episode Detection for ECG Beat Classification},
  booktitle = {Proceedings of the IEEE/NIH 5th Life Science Systems and Application Workshop},
  pages = {121--124},
  year = 2011
}