ECG features and methods for automatic classification of
ventricular premature and ischemic heartbeats: A comprehensive
experimental study

J 2017

ECG features and methods for automatic classification of ventricular premature and ischemic heartbeats: A comprehensive experimental study

MARŠÁNOVÁ, Lucie, Marina RONZHINA, Radovan SMÍŠEK, Martin VÍTEK, Andrea NĚMCOVÁ et. al.

Basic information

Original name

ECG features and methods for automatic classification of ventricular premature and ischemic heartbeats: A comprehensive experimental study

Authors

MARŠÁNOVÁ, Lucie (203 Czech Republic), Marina RONZHINA (203 Czech Republic), Radovan SMÍŠEK (203 Czech Republic), Martin VÍTEK (203 Czech Republic), Andrea NĚMCOVÁ (203 Czech Republic), Lukáš SMITAL (203 Czech Republic) and Marie NOVÁKOVÁ (203 Czech Republic, guarantor, belonging to the institution)

Edition

Scientific Reports, LONDON, NATURE PUBLISHING GROUP, 2017, 2045-2322

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

30105 Physiology

Country of publisher

United Kingdom of Great Britain and Northern Ireland

Confidentiality degree

není předmětem státního či obchodního tajemství

Impact factor

Impact factor: 4.122

RIV identification code

RIV/00216224:14110/17:00097888

Organization unit

Faculty of Medicine

DOI

http://dx.doi.org/10.1038/s41598-017-10942-6

UT WoS

000410064000075

Keywords in English

ECG features

Abstract

V originále

Accurate detection of cardiac pathological events is an important part of electrocardiogram (ECG) evaluation and subsequent correct treatment of the patient. The paper introduces the results of a complex study, where various aspects of automatic classification of various heartbeat types have been addressed. Particularly, non-ischemic, ischemic (of two different grades) and subsequent ventricular premature beats were classified in this combination for the first time. ECGs recorded in rabbit isolated hearts under non-ischemic and ischemic conditions were used for analysis. Various morphological and spectral features (both commonly used and newly proposed) as well as classification models were tested on the same data set. It was found that: a) morphological features are generally more suitable than spectral ones; b) successful results (accuracy up to 98.3% and 96.2% for morphological and spectral features, respectively) can be achieved using features calculated without time-consuming delineation of QRS-T segment; c) use of reduced number of features (3 to 14 features) for model training allows achieving similar or even better performance as compared to the whole feature sets (10 to 29 features); d) k-nearest neighbours and support vector machine seem to be the most appropriate models (accuracy up to 98.6% and 93.5%, respectively).

Links

MUNI/A/1355/2016, interní kód MU

Name: Kardiovaskulární systém očima molekulární fyziologie

Investor: Masaryk University, Category A

Citovat

MARŠÁNOVÁ, Lucie, Marina RONZHINA, Radovan SMÍŠEK, Martin VÍTEK, Andrea NĚMCOVÁ, Lukáš SMITAL and Marie NOVÁKOVÁ. ECG features and methods for automatic classification of ventricular premature and ischemic heartbeats: A comprehensive experimental study. Scientific Reports. LONDON: NATURE PUBLISHING GROUP, 2017, vol. 7, No 11239, p. 1-11. ISSN 2045-2322. Available from: https://dx.doi.org/10.1038/s41598-017-10942-6.

@article{1392275,
   author = {Maršánová, Lucie and Ronzhina, Marina and Smíšek, Radovan and Vítek, Martin and Němcová, Andrea and Smital, Lukáš and Nováková, Marie},
   article_location = {LONDON},
   article_number = {11239},
   doi = {http://dx.doi.org/10.1038/s41598-017-10942-6},
   keywords = {ECG features},
   language = {eng},
   issn = {2045-2322},
   journal = {Scientific Reports},
   title = {ECG features and methods for automatic classification of ventricular premature and ischemic heartbeats: A comprehensive experimental study},
   volume = {7},
   year = {2017}
}

TY  - JOUR
ID  - 1392275
AU  - Maršánová, Lucie - Ronzhina, Marina - Smíšek, Radovan - Vítek, Martin - Němcová, Andrea - Smital, Lukáš - Nováková, Marie
PY  - 2017
TI  - ECG features and methods for automatic classification of ventricular premature and ischemic heartbeats: A comprehensive experimental study
JF  - Scientific Reports
VL  - 7
IS  - 11239
SP  - 1-11
EP  - 1-11
PB  - NATURE PUBLISHING GROUP
SN  - 20452322
KW  - ECG features
N2  - Accurate detection of cardiac pathological events is an important part of electrocardiogram (ECG) evaluation and subsequent correct treatment of the patient. The paper introduces the results of a complex study, where various aspects of automatic classification of various heartbeat types have been addressed. Particularly, non-ischemic, ischemic (of two different grades) and subsequent ventricular premature beats were classified in this combination for the first time. ECGs recorded in rabbit isolated hearts under non-ischemic and ischemic conditions were used for analysis. Various morphological and spectral features (both commonly used and newly proposed) as well as classification models were tested on the same data set. It was found that: a) morphological features are generally more suitable than spectral ones; b) successful results (accuracy up to 98.3% and 96.2% for morphological and spectral features, respectively) can be achieved using features calculated without time-consuming delineation of QRS-T segment; c) use of reduced number of features (3 to 14 features) for model training allows achieving similar or even better performance as compared to the whole feature sets (10 to 29 features); d) k-nearest neighbours and support vector machine seem to be the most appropriate models (accuracy up to 98.6% and 93.5%, respectively).
ER  -

MARŠÁNOVÁ, Lucie, Marina RONZHINA, Radovan SMÍŠEK, Martin VÍTEK, Andrea NĚMCOVÁ, Lukáš SMITAL and Marie NOVÁKOVÁ. ECG features and methods for automatic classification of ventricular premature and ischemic heartbeats: A comprehensive experimental study. \textit{Scientific Reports}. LONDON: NATURE PUBLISHING GROUP, 2017, vol.~7, No~11239, p.~1-11. ISSN~2045-2322. Available from: https://dx.doi.org/10.1038/s41598-017-10942-6.

Detailed Information on Publication Record