Publication detail

Multichannel QRS Morphology Clustering - Data Preprocessing for Ultra-High-Frequency ECG Analysis

PLEŠINGER, F. JURČO, J. HALÁMEK, J. LEINVEBER, P. POSTRÁNECKÁ, T. JURÁK, P.

Original Title

Multichannel QRS Morphology Clustering - Data Preprocessing for Ultra-High-Frequency ECG Analysis

Type

conference paper

Language

English

Original Abstract

Ultra-high-frequency ECG (UHF-ECG) in a range of 500–1,000 Hz has been tested as a new information source for analysis of left-ventricle dyssynchrony and other myocardial abnormalities. The power of UHF signals is extremely low, for which reason an averaging technique is used to improve signal-to-noise ratio. Since ventricle dyssynchrony is different for various QRS complex types, the detected QRS complexes must be clustered into morphology groups prior to averaging. Here, we present a fully-automated method for clustering. The first goal of the method is to separate previously detected QRS complexes into different morphology groups. The second goal is to precisely fit the QRS annotation marks to the exact same position against the QRS shape. The method is based on the Pearson correlation and is optimized for parallel processing. In our application with UHF-ECG data the number of detected groups was 3.24 ± 3.41 (mean and standard deviation over 1,030 records). The method can be used in other areas also where the clustering of repetitive signal formations is needed. For validation purposes, the method was tested on the MIT-BIH Arrhythmia and INCART databases from Physionet with results of purity of 98.24% and 99.50%.

Keywords

ECG; SAECG; QRS; Ultra-High-Frequency; Clustering; Multi-thread; Ventricle Dyssynchrony

Authors

PLEŠINGER, F.; JURČO, J.; HALÁMEK, J.; LEINVEBER, P.; POSTRÁNECKÁ, T.; JURÁK, P.

RIV year

2015

Released

6. 11. 2015

Publisher

Science and Technology Publications

Location

Lisbon, Portugal

ISBN

978-989-758-160-1

Book

Proceedings of the 3rd International Congress on Cardiovascular Technologies

Edition

2015

Edition number

1

Pages from

11

Pages to

19

Pages count

9

URL

Full text in the Digital Library

BibTex

@inproceedings{BUT128354,
  author="Filip {Plešinger} and Juraj {Jurčo} and Josef {Halámek} and Pavel {Leinveber} and Tereza {Postránecká} and Pavel {Jurák}",
  title="Multichannel QRS Morphology Clustering - Data Preprocessing for Ultra-High-Frequency ECG Analysis",
  booktitle="Proceedings of the 3rd International Congress on Cardiovascular Technologies",
  year="2015",
  series="2015",
  number="1",
  pages="11--19",
  publisher="Science and Technology Publications",
  address="Lisbon, Portugal",
  doi="10.5220/0005604200110019",
  isbn="978-989-758-160-1",
  url="https://www.scitepress.org/Link.aspx?doi=10.5220/0005604200110019"
}