Classification of Premature Ventricular Contraction based on ECG Signal using Multiorder Rényi Entropy

2019 ◽  
Author(s):  
Achmad Rizal ◽  
Inung Wijayanto
Keyword(s):  
Premature Ventricular Contraction ◽  
Renyi Entropy ◽  
Rényi Entropy ◽  
Ecg Signal ◽  
Ventricular Contraction

scholarly journals Robust deep learning pipeline for PVC beats localization

2021 ◽  
Vol 29 ◽  
pp. 475-486
Author(s):  
Bohdan Petryshak ◽  
Illia Kachko ◽  
Mykola Maksymenko ◽  
Oles Dobosevych
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Premature Ventricular Contraction ◽  
Ecg Signal ◽  
Ventricular Contraction ◽  
Localization Task ◽  
Robust Performance ◽  
Extensive Evaluation ◽  
Decoder Architecture ◽  
Public Datasets

BACKGROUND: Premature ventricular contraction (PVC) is among the most frequently occurring types of arrhythmias. Existing approaches for automated PVC identification suffer from a range of disadvantages related to hand-crafted features and benchmarking on datasets with a tiny sample of PVC beats. OBJECTIVE: The main objective is to address the drawbacks described above in the proposed framework, which takes a raw ECG signal as an input and localizes R peaks of the PVC beats. METHODS: Our method consists of two neural networks. First, an encoder-decoder architecture trained on PVC-rich dataset localizes the R peak of both Normal and anomalous heartbeats. Provided R peaks positions, our CardioIncNet model does the delineation of healthy versus PVC beats. RESULTS: We have performed an extensive evaluation of our pipeline with both single- and cross-dataset paradigms on three public datasets. Our approach results in over 0.99 and 0.979 F1-measure on both single- and cross-dataset paradigms for R peaks localization task and above 0.96 and 0.85 F1 score for the PVC beats classification task. CONCLUSIONS: We have shown a method that provides robust performance beyond the beats of Normal nature and clearly outperforms classical algorithms both in the case of a single and cross-dataset evaluation. We provide a Github1 repository for the reproduction of the results.

scholarly journals Intelligent Analysis of Premature Ventricular Contraction Based on Features and Random Forest

2019 ◽  
Vol 2019 ◽  
pp. 1-10
Author(s):  
Tiantian Xie ◽  
Runchuan Li ◽  
Shengya Shen ◽  
Xingjin Zhang ◽  
Bing Zhou ◽  
...  
Keyword(s):  
At Risk ◽  
Random Forest ◽  
Premature Ventricular Contraction ◽  
Ventricular Contraction ◽  
Rr Intervals ◽  
Intelligent Analysis

Premature ventricular contraction (PVC) is one of the most common arrhythmias in the clinic. Due to its variability and susceptibility, patients may be at risk at any time. The rapid and accurate classification of PVC is of great significance for the treatment of diseases. Aiming at this problem, this paper proposes a method based on the combination of features and random forest to identify PVC. The RR intervals (pre_RR and post_RR), R amplitude, and QRS area are chosen as the features because they are able to identify PVC better. The experiment was validated on the MIT-BIH arrhythmia database and achieved good results. Compared with other methods, the accuracy of this method has been significantly improved.

scholarly journals Identification of Premature Ventricular Contraction (PVC) Based on ECG Using Convolutional Neural Network

2020 ◽  
Vol 9 (1) ◽  
pp. 2173-2177
Keyword(s):  
Neural Network ◽  
Performance Measures ◽  
Premature Ventricular Contraction ◽  
High Accuracy ◽  
Vital Role ◽  
Ventricular Contraction ◽  
Effective Technique ◽  
Ecg Signals ◽  
Traditional Approaches

Premature Ventricular Contraction (PVC) arrhythmia patients are subjected to dangerous heart rhythms that can be chaotic, and possibly result in abrupt death. Therefore, early detection of arrhythmia with high accuracy is extremely important to detect cardiovascular diseases. The classification of heartbeats based on ECG signals plays a vital role it the field of cardiac sciences to identify arrhythmias. The use of Artificial Neural Networks (ANN) has proven to be the most effective technique for sole agenda of classification. The use of CNN is simple and more noise immune method in comparison to various other techniques. In this paper, a survey of numerous algorithms and classification techniques along with their performance measures are presented. This paper proposes the identification of PVC on the basis of heart beats by using CNN and the results obtained are compared to other traditional approaches

Sign in / Sign up

Export Citation Format

Share Document