A Review of the Methods for Sudden Cardiac Death Detection: A Guide for Emergency Physicians

Abstract

<p class="Abstract">Sudden cardiac death (SCD) is an unexpected death of a person with or without knowing cardiac causes are often occurring in less than an hour after the incidence of symptoms. In the case of physicians' knowledge of this incident, they can make appropriate decisions for the patients at-risk and reduce the number of such deaths significantly. The purpose of this paper is to examine different methods for predicting sudden cardiac death using electrocardiogram (ECG) signal from 1998 to recent years that can contribute to researchers to become familiar with the wide range of research conducted in this field.</p><p class="Abstract">In this paper, studies using various methods to predict sudden cardiac death that has applied the data from the Physionet and MIT-BIH databases with a sampling frequency of 256 samples per second are reviewed. Both types of data have normal and abnormal sampling labels and the data recording time varies from a few seconds to minutes. In the field of SCD prediction, various studies have addressed the processing of the electrocardiogram (ECG) signal as well as the heart rate variability (HRV) signal in different domains, including time, time-frequency, and nonlinear domain. In time-domain processing the statistical characteristics of time signal such as the mean and standard deviation of heart rate, the mean and standard deviation of RR intervals, and Root Mean Square of the Successive Differences (RSSD) are used. Also, in the frequency domain, the power spectral density (PSD) of the signal energy is used in a very-low-frequency band, low-frequency band and, high-frequency band. Similarly, in the nonlinear domain, features such as Poincare plot, detrended fluctuation analysis (DFA), common entropy, wavelet transform coefficients (WTC), and features of the recursive graph including Lmax, Lmean, correlation dimension (CD), etc. are used. In all of the proposed algorithms so far, researchers have been trying to inform the sudden death alarm in a larger interval than the time of death by separating the signals into different time periods and extracting various features.</p><p class="Abstract">To evaluate the results of the proposed methods, each of the researchers analyzed the a-few-minute intervals before the SCD. Different classification methods are available to identify the efficiency of the proposed algorithm, such as support vector machine (SVM), multilayer perceptron neural network (MLP), radial base function neural network (RBF), k-nearest neighbor (KNN) and mixture expert (ME). The use of features introduced in different domains and different classifiers has led to the observation of different horizons of prediction in various studies. The results of these predictions are often free from the interpretations of clinical symptoms, and their maximum presented time with acceptable validity eventually reaches 4 minutes before the event, which is not an acceptable time for people who have attacked outside the hospital. Accordingly, the most prominent of these evaluations is the mixture expert methodology in which the best feature extraction methods are used in a new method for selecting the optimal feature space locally. This method makes it possible to select different features every minute before the event by choosing the optimal features for each one-minute interval of the signal as an episode which increases the prediction time from 4 minutes before the death to 12 minutes and allows the interpretation of clinical symptoms in terms of multiplication of the presence of the features per minute.</p><p class="Abstract">Given the non-linear nature of the HRV signal and the similarity of the ECG signal in many time intervals, the use of the HRV signal has become more popular among scholars. The analysis of various studies shows that by approaching the time of death, linear features (time and frequency) can be predictive of death according to the sensible behavior and variations in patients’ signal. Instead of moving away from the death interval, the use of chaotic and non-linear features is more effective. Therefore, a more precise selection of features in this area can be useful for increasing the horizon of prediction of death.</p>

Mortality Prediction of ICU Cardiovascular Patient: Time-Series Analysis

“…Reducing HRV fluctuations is a useful prognosis of mortality and acute problems in patients after acute myocardial infarction. Today, HRV is of great importance in predicting the risk of cardiac death in some diseases, such as cardiac ischemia and myocardial infarction, and the classification and diagnosis of various arrhythmias and heart diseases [21,22].…”

Students' Orientation Using Machine Learning and Big Data

“…Support Vector Machine (SVM): SVMs [16] are a family of machine learning algorithms that solve classification, regression, and anomaly detection problems. They are known for their solid theoretical guarantees, their great flexibility and their ease of use even without great knowledge of data mining.…”

“…A Neural network [18] is a calculation model whose design is very schematically inspired by the functioning of real neurons (human or not). Neural networks are generally optimized by statistical learning methods thanks to their capacity for classification and generalization, such as automatic classification of postal codes or decisionmaking regarding a stock purchase according the evolution of Classes.…”

Analysis of Heart Rate Dynamics Before and During Meditation

“…In the case of neurons in the middle layer, there is no special basis and usually are chosen by trial-and-error method so that the network will have a reasonable answer. It should be noted in this issue that if the network is very complex, will learn the behavior of the input pattern exactly, and if the data change slightly than the training data, the network will not easily be able to pursue it [35].…”