Automatic detection of ST and T episodes using polynomial approximation

  • G. Y. Jeong
  • , K. H. Yu*
  • *Corresponding author for this work

Research output: Contribution to conferenceConference paperpeer-review

Abstract

The morphological change of ECG is the important diagnostic parameter to finding the malfunction of a heart. Accordingly, physicians make theirs effort to find the change of ST segment level, RR interval, PR interval, P wave, T wave, etc. Generally ST segment deviation and T deviation is concerned with myocardial abnormality. The aim of this study is to detect the change of ST and T in shape using a polynomial approximation method. The developed algorithm makes the least squares curve for the data between S wave and T wave in ECG and calculates the variance of ST and T shape. An approximate curve of ST is represented by one polynomial over the whole ST or three polynomials for the segmented ST by three parts. We applied the developed algorithm to the ECGs in European ST database. The algorithm detects the relative change of ST shape based on the reference ST that is the average ST about 10 ST from the beginning of test ECG. We compared the annotations checked by cardiologists with the result of our algorithm. From the results of the auto-analysis using our algorithm, we could acquire the information about the place including ST and T episode in the test ECG.

Original languageEnglish
Title of host publicationIFMBE Proceedings
EditorsSun I. Kim, Tae Suk Suh
PublisherSpringer Verlag
Pages1119-1122
Number of pages4
Edition1
ISBN (Print)9783540368397
DOIs
StatePublished - 2007
Event10th World Congress on Medical Physics and Biomedical Engineering, WC 2006 - Seoul, Korea, Republic of
Duration: 2006.08.272006.09.1

Publication series

NameIFMBE Proceedings
Number1
Volume14
ISSN (Print)1680-0737
ISSN (Electronic)1433-9277

Conference

Conference10th World Congress on Medical Physics and Biomedical Engineering, WC 2006
Country/TerritoryKorea, Republic of
CitySeoul
Period06.08.2706.09.1

Keywords

  • ECG
  • Morphological change
  • Polynomial approximation
  • ST segment

Quacquarelli Symonds(QS) Subject Topics

  • Engineering - Chemical
  • Biological Sciences

Fingerprint

Dive into the research topics of 'Automatic detection of ST and T episodes using polynomial approximation'. Together they form a unique fingerprint.

Cite this