scholarly journals ECG-Based Identification of Sudden Cardiac Death through Sparse Representations

Sensors ◽  
2021 ◽  
Vol 21 (22) ◽  
pp. 7666
Author(s):  
Josue R. Velázquez-González ◽  
Hayde Peregrina-Barreto ◽  
Jose J. Rangel-Magdaleno ◽  
Juan M. Ramirez-Cortes ◽  
Juan P. Amezquita-Sanchez
Keyword(s):  
Sudden Cardiac Death ◽  
Sparse Representation ◽  
Cardiac Death ◽  
Heart Function ◽  
Reference Signal ◽  
Extraction Process ◽  
Electrical Signal ◽  
Dynamic Feature ◽  
Ecg Signals ◽  
Representation Technique

Sudden Cardiac Death (SCD) is an unexpected sudden death due to a loss of heart function and represents more than 50% of the deaths from cardiovascular diseases. Since cardiovascular problems change the features in the electrical signal of the heart, if significant changes are found with respect to a reference signal (healthy), then it is possible to indicate in advance a possible SCD occurrence. This work proposes SCD identification using Electrocardiogram (ECG) signals and a sparse representation technique. Moreover, the use of fixed feature ranking is avoided by considering a dictionary as a flexible set of features where each sparse representation could be seen as a dynamic feature extraction process. In this way, the involved features may differ within the dictionary’s margin of similarity, which is better-suited to the large number of variations that an ECG signal contains. The experiments were carried out using the ECG signals from the MIT/BIH-SCDH and the MIT/BIH-NSR databases. The results show that it is possible to achieve a detection 30 min before the SCD event occurs, reaching an an accuracy of 95.3% under the common scheme, and 80.5% under the proposed multi-class scheme, thus being suitable for detecting a SCD episode in advance.

Understanding Circadian Mechanisms of Sudden Cardiac Death: A Report From the National Heart, Lung, and Blood Institute Workshop, Part 1: Basic and Translational Aspects

2021 ◽  
Author(s):  
Brian P. Delisle ◽  
Alfred L. George ◽  
Jeanne M. Nerbonne ◽  
Joseph T. Bass ◽  
Crystal M. Ripplinger ◽  
...  
Keyword(s):  
Sudden Cardiac Death ◽  
Cardiac Death ◽  
Animal Studies ◽  
Heart Function ◽  
Cell Types ◽  
Unexpected Death ◽  
Blood Institute ◽  
Physiological Importance ◽  
National Heart ◽  
National Heart Lung

Sudden cardiac death (SCD), the unexpected death due to acquired or genetic cardiovascular disease, follows distinct 24-hour patterns in occurrence. These 24-hour patterns likely reflect daily changes in arrhythmogenic triggers and the myocardial substrate caused by day/night rhythms in behavior, the environment, and endogenous circadian mechanisms. To better address fundamental questions regarding the circadian mechanisms, the National Heart, Lung, and Blood Institute convened a workshop, Understanding Circadian Mechanisms of Sudden Cardiac Death. We present a 2-part report of findings from this workshop. Part 1 summarizes the workshop and serves to identify research gaps and opportunities in the areas of basic and translational research. Among the gaps noted: a lack of standardization in animal studies for reporting environmental conditions (eg, timing of experiments relative to the light dark cycle or animal housing temperatures) that can impair rigor and reproducibility. Workshop participants also pointed to uncertainty regarding the importance of maintaining normal circadian rhythmic synchrony and the potential pathological impact of desynchrony in SCD risk. One related question raised was whether circadian mechanisms can be targeted to reduce SCD risk. Finally, the experts underscored the need for studies aimed at determining the physiological importance of circadian clocks in the many different cell types important to normal heart function and SCD. Addressing these gaps could lead to new therapeutic approaches/molecular targets that can mitigate the risk of SCD not only at certain times but over the entire 24-hour period.

Early Prediction of Sudden Cardiac Death using Fractal Dimension and ECG signals

Fractals ◽  
2020 ◽  
Author(s):  
Rogelio Pina-Vega ◽  
Martin Valtierra-Rodriguez ◽  
Carlos A. Perez-Ramirez ◽  
Juan P. Amezquita-Sanchez
Keyword(s):  
Fractal Dimension ◽  
Sudden Cardiac Death ◽  
Cardiac Death ◽  
Early Prediction ◽  
Ecg Signals

A Novel Wavelet Transform-Homogeneity Model for Sudden Cardiac Death Prediction Using ECG Signals

2018 ◽  
Vol 42 (10) ◽  
Author(s):  
Juan P. Amezquita-Sanchez ◽  
Martin Valtierra-Rodriguez ◽  
Hojjat Adeli ◽  
Carlos A. Perez-Ramirez
Keyword(s):  
Wavelet Transform ◽  
Sudden Cardiac Death ◽  
Cardiac Death ◽  
Ecg Signals

Automated Electrocardiogram Signals Based Risk Marker for Early Sudden Cardiac Death Prediction

2018 ◽  
Vol 8 (9) ◽  
pp. 1769-1775
Author(s):  
Khudhur A. Alfarhan ◽  
Mohd Yusoff Mashor ◽  
Ammar Zakaria ◽  
Mohammad Iqbal Omar
Keyword(s):  
Sudden Cardiac Death ◽  
Time Domain ◽  
Classification Accuracy ◽  
Cardiac Death ◽  
Nearest Neighbor ◽  
Research Work ◽  
Sudden Cardiac Arrest ◽  
Linear Discriminant ◽  
Ecg Signals ◽  
Electrocardiogram Signals

Sudden cardiac death (SCD) is one of the cardiovascular diseases that lead to millions of deaths worldwide every year. The aim of the present work is to propose a method for reducing the mortality rate of the SCD patients by an early prediction for SCD from the ECG signal. Normal and SCD MIT databases were used in this research work. One minute segments of ECG signals were segmented from MIT databases where these segments are ten minutes before sudden cardiac arrest (SCA) onset. The collected raw ECG signals were subjected to filter to remove the noise and then normalized. A frequency-domain feature and time-domain features were extracted from the Q-T segment, Q-T interval, R-R interval and QRS interval. The features were normalized to improve the performance of the classifier. Artificial intelligence classifiers; namely, K-nearest neighbor (KNN) and linear discriminant analysis (LDA) were used separately on SCD and normal ECG signals. The highest classification accuracy obtained for KNN and LDA are 97% and 95.5% respectively.

Sign in / Sign up

Export Citation Format

Share Document