Computational Diagnostic Techniques for Electrocardiogram Signal Analysis

Abstract

Cardiovascular diseases (CVDs), including asymptomatic myocardial ischemia, angina, myocardial infarction, and ischemic heart failure, are the leading cause of death globally. Early detection and treatment of CVDs significantly contribute to the prevention or delay of cardiovascular death. Electrocardiogram (ECG) records the electrical impulses generated by heart muscles, which reflect regular or irregular beating activity. Computer-aided techniques provide fast and accurate tools to identify CVDs using a patient’s ECG signal, which have achieved great success in recent years. Latest computational diagnostic techniques based on ECG signals for estimating CVDs conditions are summarized here. The procedure of ECG signals analysis is discussed in several subsections, including data preprocessing, feature engineering, classification, and application. In particular, the End-to-End models integrate feature extraction and classification into learning algorithms, which not only greatly simplifies the process of data analysis, but also shows excellent accuracy and robustness. Portable devices enable users to monitor their cardiovascular status at any time, bringing new scenarios as well as challenges to the application of ECG algorithms. Computational diagnostic techniques for ECG signal analysis show great potential for helping health care professionals, and their application in daily life benefits both patients and sub-healthy people.

ECG Heartbeat Classification Based on an Improved ResNet-18 Model

“…The recently emerged DL models are powerful, even though computationally expensive, analytical models that can greatly reduce the use of artificial features [ 8 ]. DL models are based on the use of deep neural networks (DNNs), which are subdivided into convolutional neural networks (CNNs), recursive neural networks (RNNs), and long-term short-term memory (LSTM).…”

“…One of the most important features of a CNN is that its complex structure provides a certain degree of translation, scaling, and rotation invariance, because the local receptive field allows neurons or processing units to access underlying features, such as directional edges or corners. Therefore, the CNN-based approach demonstrates very good performance in classification of ECG signals, especially to solve prediction problems in ECG arrhythmia classification, due to its strong robustness and fault tolerance to noise [ 8 ]. Xu et al [ 15 ] used a DNN to classify ECG signals end-to-end, demonstrating by this the possibility for complete intelligence of ECG analysis [ 8 ].…”

“…In clinical practice, the changes of ECG parameters are identified by doctors based on visual evaluation and manual interpretation methods in order to detect CVDs. Due to the nonstationary and nonlinear nature of ECG signals, however, CVD indicators may appear randomly on the time scale [ 8 ]. This and other factors make the classification of arrhythmic heartbeats in ECG signals a very challenging and time-consuming task, and so, it is almost unrealistic to perform it manually.…”

“…The main contributions of this article are the following: Wavelet transform is used for denoising the ECG signals, due to its high resolution of time and frequency, allowing it to successfully recognize the abstract and hidden features of ECG signals [ 8 ] An improved version of the ResNet-18 model [ 9 ] is elaborated and proposed for ECG heartbeat classification, with an ability to extract features in depth A performance comparison of the proposed model with state-of-the-art models is presented, based on experiments conducted with the Massachusetts Institute of Technology-Boston's Beth Israel Hospital (MIT-BIH) arrhythmia database, showing that the proposed model achieves the highest classification accuracy among the models compared …”

“…Wavelet transform is used for denoising the ECG signals, due to its high resolution of time and frequency, allowing it to successfully recognize the abstract and hidden features of ECG signals [ 8 ]…”