Publication detail

Single-Feature Method for Fast Atrial Fibrillation Detection in ECG Signals

MARŠÁNOVÁ, L. NĚMCOVÁ, A. SMÍŠEK, R. SMITAL, L. VÍTEK, M.

Original Title

Single-Feature Method for Fast Atrial Fibrillation Detection in ECG Signals

English Title

Single-Feature Method for Fast Atrial Fibrillation Detection in ECG Signals

Type

conference paper

Language

en

Original Abstract

Atrial fibrillation (AF) is the most common arrhthmia in adults and is associated with higher risk of heart failure or death. Here, we introduce simple and efficient method for automatic AF detection based on symbolic dynamics and Shannon entropy. This method comprises of three parts. Firstly, QRS complex detection is provided, than the raw RR sequence is transformed into a sequence of specific symbols and subsequently into a word sequence and finally, Shannon entropy of the word sequence is calculated. According to the value of Shannon entropy, it is decided, whether AF is present in the current cardiac beat. We achieved sensitivity Se=96.32% and specificity Sp=98.61 on MIT-BIH Atrial Fibrillation database, Se=91.30% and Sp=90.80% on MIT-BIH Arrhythmia database, Se=95.6% and Sp=80.27% for CinC Challenge database 2020. The achieved results of our one-feature method are comparable with other authors of more complicated and computationally expensive methods.

English abstract

Atrial fibrillation (AF) is the most common arrhthmia in adults and is associated with higher risk of heart failure or death. Here, we introduce simple and efficient method for automatic AF detection based on symbolic dynamics and Shannon entropy. This method comprises of three parts. Firstly, QRS complex detection is provided, than the raw RR sequence is transformed into a sequence of specific symbols and subsequently into a word sequence and finally, Shannon entropy of the word sequence is calculated. According to the value of Shannon entropy, it is decided, whether AF is present in the current cardiac beat. We achieved sensitivity Se=96.32% and specificity Sp=98.61 on MIT-BIH Atrial Fibrillation database, Se=91.30% and Sp=90.80% on MIT-BIH Arrhythmia database, Se=95.6% and Sp=80.27% for CinC Challenge database 2020. The achieved results of our one-feature method are comparable with other authors of more complicated and computationally expensive methods.

Keywords

ECG, atrial fibrillation, phasor transform, symbolic dynamic

Released

28.12.2020

Location

Rimini, Italy

ISBN

2325-887X

Periodical

Computing in Cardiology

State

US

Pages from

1

Pages to

4

Pages count

4

Documents

BibTex


@inproceedings{BUT166074,
  author="Lucie {Maršánová} and Andrea {Němcová} and Radovan {Smíšek} and Lukáš {Smital} and Martin {Vítek}",
  title="Single-Feature Method for Fast Atrial Fibrillation Detection in ECG Signals",
  annote="Atrial fibrillation (AF) is the most common arrhthmia in adults and is associated with higher risk of heart failure or death. Here, we introduce simple and efficient method for automatic AF detection based on symbolic dynamics and Shannon entropy. This method comprises of three parts. Firstly, QRS complex detection is provided, than the raw RR sequence is transformed into a sequence of specific symbols and subsequently into a word sequence and finally, Shannon entropy of the word sequence is calculated. According to the value of Shannon entropy, it is decided, whether AF is present in the current cardiac beat. We achieved sensitivity Se=96.32% and specificity Sp=98.61 on MIT-BIH Atrial Fibrillation database, Se=91.30% and Sp=90.80% on MIT-BIH Arrhythmia database, Se=95.6% and Sp=80.27% for CinC Challenge database 2020. The achieved results of our one-feature method are comparable with other authors of more complicated and computationally expensive methods.",
  booktitle="Computing in Cardiology  2020",
  chapter="166074",
  doi="10.22489/CinC.2020.335",
  howpublished="online",
  year="2020",
  month="december",
  pages="1--4",
  type="conference paper"
}