ECG-based detection and prediction models of sudden cardiac death: Current performances and new perspectives on signal processing techniques

Mohd Zubir Suboh, Rosmina Jaafar, Nazrul Anuar Nayan, Noor Hasmiza Harun

Research output: Contribution to journalArticle

Abstract

Heart disease remains the main leading cause of death globally and around 50% of the patients died due to sudden cardiac death (SCD). Early detection and prediction of SCD have become an important topic of research and it is crucial for cardiac patient's survival. Electrocardiography (ECG) has always been the first screening method for patient with cardiac complaints and it is proven as an important predictor of SCD. ECG parameters such as RR interval, QT duration, QRS complex curve, J-point elevation and T-wave alternan are found effective in differentiating normal and SCD subjects. The objectives of this paper are to give an overview of SCD and to analyze multiple important ECG-based SCD detection and prediction models in terms of processing techniques and performance wise. Detail discussions are made in four major stages of the models developed including ECG data, signal pre-processing and processing techniques as well as classification methods. Heart rate variability (HRV) is found as an important SCD predictor as it is widely used in detecting or predicting SCD. Studies showed the possibility of SCD to be detected as early as one hour prior to the event using linear and non-linear features of HRV. Currently, up to 3 hours of analysis has been carried out. However, the best prediction models are only able to detect SCD at 6 minutes before the event with acceptable accuracy of 92.77%. A few arguments and recommendation in terms of data preparation, processing and classification techniques, as well as utilizing photoplethysmography with ECG are pointed out in this paper so that future analysis can be done with better accuracy of SCD detection accuracy.

Original languageEnglish
Pages (from-to)110-126
Number of pages17
JournalInternational journal of online and biomedical engineering
Volume15
Issue number15
DOIs
Publication statusPublished - 1 Jan 2019

Fingerprint

Electrocardiography
Signal processing
Processing
Photoplethysmography
Screening

Keywords

  • Electrocardiography
  • Photoplethysmography
  • Sudden cardiac arrest
  • Sudden cardiac death

ASJC Scopus subject areas

  • Engineering(all)

Cite this

@article{491c19903daa40d1bf75d0009509ac9f,
title = "ECG-based detection and prediction models of sudden cardiac death: Current performances and new perspectives on signal processing techniques",
abstract = "Heart disease remains the main leading cause of death globally and around 50{\%} of the patients died due to sudden cardiac death (SCD). Early detection and prediction of SCD have become an important topic of research and it is crucial for cardiac patient's survival. Electrocardiography (ECG) has always been the first screening method for patient with cardiac complaints and it is proven as an important predictor of SCD. ECG parameters such as RR interval, QT duration, QRS complex curve, J-point elevation and T-wave alternan are found effective in differentiating normal and SCD subjects. The objectives of this paper are to give an overview of SCD and to analyze multiple important ECG-based SCD detection and prediction models in terms of processing techniques and performance wise. Detail discussions are made in four major stages of the models developed including ECG data, signal pre-processing and processing techniques as well as classification methods. Heart rate variability (HRV) is found as an important SCD predictor as it is widely used in detecting or predicting SCD. Studies showed the possibility of SCD to be detected as early as one hour prior to the event using linear and non-linear features of HRV. Currently, up to 3 hours of analysis has been carried out. However, the best prediction models are only able to detect SCD at 6 minutes before the event with acceptable accuracy of 92.77{\%}. A few arguments and recommendation in terms of data preparation, processing and classification techniques, as well as utilizing photoplethysmography with ECG are pointed out in this paper so that future analysis can be done with better accuracy of SCD detection accuracy.",
keywords = "Electrocardiography, Photoplethysmography, Sudden cardiac arrest, Sudden cardiac death",
author = "Suboh, {Mohd Zubir} and Rosmina Jaafar and Nayan, {Nazrul Anuar} and Harun, {Noor Hasmiza}",
year = "2019",
month = "1",
day = "1",
doi = "10.3991/ijoe.v15i15.11688",
language = "English",
volume = "15",
pages = "110--126",
journal = "International journal of online and biomedical engineering",
issn = "2626-8493",
publisher = "Kassel University Press GmbH",
number = "15",

}

TY - JOUR

T1 - ECG-based detection and prediction models of sudden cardiac death

T2 - Current performances and new perspectives on signal processing techniques

AU - Suboh, Mohd Zubir

AU - Jaafar, Rosmina

AU - Nayan, Nazrul Anuar

AU - Harun, Noor Hasmiza

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Heart disease remains the main leading cause of death globally and around 50% of the patients died due to sudden cardiac death (SCD). Early detection and prediction of SCD have become an important topic of research and it is crucial for cardiac patient's survival. Electrocardiography (ECG) has always been the first screening method for patient with cardiac complaints and it is proven as an important predictor of SCD. ECG parameters such as RR interval, QT duration, QRS complex curve, J-point elevation and T-wave alternan are found effective in differentiating normal and SCD subjects. The objectives of this paper are to give an overview of SCD and to analyze multiple important ECG-based SCD detection and prediction models in terms of processing techniques and performance wise. Detail discussions are made in four major stages of the models developed including ECG data, signal pre-processing and processing techniques as well as classification methods. Heart rate variability (HRV) is found as an important SCD predictor as it is widely used in detecting or predicting SCD. Studies showed the possibility of SCD to be detected as early as one hour prior to the event using linear and non-linear features of HRV. Currently, up to 3 hours of analysis has been carried out. However, the best prediction models are only able to detect SCD at 6 minutes before the event with acceptable accuracy of 92.77%. A few arguments and recommendation in terms of data preparation, processing and classification techniques, as well as utilizing photoplethysmography with ECG are pointed out in this paper so that future analysis can be done with better accuracy of SCD detection accuracy.

AB - Heart disease remains the main leading cause of death globally and around 50% of the patients died due to sudden cardiac death (SCD). Early detection and prediction of SCD have become an important topic of research and it is crucial for cardiac patient's survival. Electrocardiography (ECG) has always been the first screening method for patient with cardiac complaints and it is proven as an important predictor of SCD. ECG parameters such as RR interval, QT duration, QRS complex curve, J-point elevation and T-wave alternan are found effective in differentiating normal and SCD subjects. The objectives of this paper are to give an overview of SCD and to analyze multiple important ECG-based SCD detection and prediction models in terms of processing techniques and performance wise. Detail discussions are made in four major stages of the models developed including ECG data, signal pre-processing and processing techniques as well as classification methods. Heart rate variability (HRV) is found as an important SCD predictor as it is widely used in detecting or predicting SCD. Studies showed the possibility of SCD to be detected as early as one hour prior to the event using linear and non-linear features of HRV. Currently, up to 3 hours of analysis has been carried out. However, the best prediction models are only able to detect SCD at 6 minutes before the event with acceptable accuracy of 92.77%. A few arguments and recommendation in terms of data preparation, processing and classification techniques, as well as utilizing photoplethysmography with ECG are pointed out in this paper so that future analysis can be done with better accuracy of SCD detection accuracy.

KW - Electrocardiography

KW - Photoplethysmography

KW - Sudden cardiac arrest

KW - Sudden cardiac death

UR - http://www.scopus.com/inward/record.url?scp=85077522663&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85077522663&partnerID=8YFLogxK

U2 - 10.3991/ijoe.v15i15.11688

DO - 10.3991/ijoe.v15i15.11688

M3 - Article

AN - SCOPUS:85077522663

VL - 15

SP - 110

EP - 126

JO - International journal of online and biomedical engineering

JF - International journal of online and biomedical engineering

SN - 2626-8493

IS - 15

ER -