Sudden Cardiac Death is considered one of the main cause of mortality worldwide. Understanding the origin of this heart disease continues to be a challenge for the scientific community. According to the literature review, T wave alternans has been considered an important, non-invasive indicator to detect and stratify the risk of sudden cardiac death. On the other hand, dictionary learning is a digital signal processing technique that allows identify the main characteristics of a signal using a sparse representation. In this context, a new non-invasive method is proposed by mixing TWA spectral methods and dictionary learning. The method identifies the main characteristics of ECG signal by obtaining a sparse representation that adapts a matrix (dictionary) in order to use it for highlighting the TWA characteristics and then use these characteristics for detecting SCD. Experimental results show an improvement of 32% compared to the Physionet TWAnalyser program by using synthetic data set and an improvement of 20% over public databases.
6 September 2022 in IEEE Latin America Transactions
Sudden Cardiac Death (SCD) is considered one of the main causes of mortality worldwide. Often, the symptomsappear in healthy persons one hour before the fatal event. The incomprehensible nature of this cardiac disease increases the necessity to develop new methods to predict this pathology. A review of state of the art based on Kitchenham procedures is carried out. According to the literature review, several methods to predict SCD have been developed using Heart Rate Variability (HRV), and T-wave alternans (TWA). These indexes have been considered important, non-invasive, and promising indicators to stratify the risk of SCD. In this context, the work presented in this paper shows a review of the state of the art, focused on the research efforts about risk stratification indices based on HRV and TWA. The purpose of this review is developing a future research framework to stratify the risk of SCD disease, by mixing caracteristics of the HRV and TWA approaches, thus producing a new hybrid method.