VT/VF Detection Method Based on ECG Signal Quality Assessment

2018 ◽  
Vol 27 (11) ◽  
pp. 1850169 ◽  
Author(s):  
Borisav Jovanović ◽  
Srdan Milenković ◽  
Milan Pavlović
Keyword(s):  
Cardiac Arrhythmias ◽  
Signal Analysis ◽  
Detection Method ◽  
Signal Quality ◽  
Ecg Signals ◽  
Battery Charge ◽  
Time Domain Signal ◽  
Signal Parameters ◽  
Life Threatening ◽  
Electrocardiogram Ecg

Artefacts which are present in electrocardiogram (ECG) recordings distort detection of life-threatening arrhythmias such as ventricular tachycardia and ventricular fibrillation. The method examines single ECG lead and exploits time domain signal parameters for real-time detection of severe cardiac arrhythmias. The method is dedicated to implementation in mobile ECG telemetry systems, which are designed by using low-power microcontrollers, operating more than a week on a single battery charge. The method has been validated on publicly available databases and the results are presented. We verified our method on ECG signals obtained without pre-selection meaning that the noisy intervals were not omitted from signal analysis.

Accurate Detection of ECG Signals in ECG Monitoring Systems by Eliminating the Motion Artifacts and Improving the Signal Quality Using SSG Filter with DBE

2019 ◽  
Vol 29 (02) ◽  
pp. 2050024
Author(s):  
Mahesh B. Dembrani ◽  
K. B. Khanchandani ◽  
Anita Zurani
Keyword(s):  
Signal Analysis ◽  
Motion Artifact ◽  
Motion Artifacts ◽  
Signal Quality ◽  
Ecg Signal ◽  
Qrs Complex ◽  
Ecg Signals ◽  
Cardiac Disorders ◽  
Digital Processor ◽  
Ica Algorithm

The automatic recognition of QRS complexes in an Electrocardiography (ECG) signal is a critical step in any programmed ECG signal investigation, particularly when the ECG signal taken from the pregnant women additionally contains the signal of the fetus and some motion artifact signals. Separation of ECG signals of mother and fetus and investigation of the cardiac disorders of the mother are demanding tasks, since only one single device is utilized and it gets a blend of different heart beats. In order to resolve such problems we propose a design of new reconfigurable Subtractive Savitzky–Golay (SSG) filter with Digital Processor Back-end (DBE) in this paper. The separation of signals is done using Independent Component Analysis (ICA) algorithm and then the motion artifacts are removed from the extracted mother’s signal. The combinational use of SSG filter and DBE enhances the signal quality and helps in detecting the QRS complex from the ECG signal particularly the R peak accurately. The experimental results of ECG signal analysis show the importance of our proposed method.

scholarly journals Automatic ECG Diagnosis Using Convolutional Neural Network

Electronics ◽  
2020 ◽  
Vol 9 (6) ◽  
pp. 951 ◽  
Author(s):  
Roberta Avanzato ◽  
Francesco Beritelli
Keyword(s):  
Confusion Matrix ◽  
Premature Ventricular Contraction ◽  
Disease Diagnosis ◽  
Ecg Signals ◽  
Testing Dataset ◽  
Life Threatening ◽  
Causes Of Mortality ◽  
Atrial Premature Beat ◽  
Heart Disease Diagnosis ◽  
Electrocardiogram Ecg

Cardiovascular disease (CVD) is the most common class of chronic and life-threatening diseases and, therefore, considered to be one of the main causes of mortality. The proposed new neural architecture based on the recent popularity of convolutional neural networks (CNN) was a solution for the development of automatic heart disease diagnosis systems using electrocardiogram (ECG) signals. More specifically, ECG signals were passed directly to a properly trained CNN network. The database consisted of more than 4000 ECG signal instances extracted from outpatient ECG examinations obtained from 47 subjects: 25 males and 22 females. The confusion matrix derived from the testing dataset indicated 99% accuracy for the “normal” class. For the “atrial premature beat” class, ECG segments were correctly classified 100% of the time. Finally, for the “premature ventricular contraction” class, ECG segments were correctly classified 96% of the time. In total, there was an average classification accuracy of 98.33%. The sensitivity (SNS) and the specificity (SPC) were, respectively, 98.33% and 98.35%. The new approach based on deep learning and, in particular, on a CNN network guaranteed excellent performance in automatic recognition and, therefore, prevention of cardiovascular diseases.

scholarly journals Cardiac Arrhythmias in Muscular Dystrophies Associated with Emerinopathy and Laminopathy: A Cohort Study

2021 ◽  
Vol 10 (4) ◽  
pp. 732
Author(s):  
Michał Marchel ◽  
Agnieszka Madej-Pilarczyk ◽  
Agata Tymińska ◽  
Roman Steckiewicz ◽  
Ewa Ostrowska ◽  
...  
Keyword(s):  
Muscular Dystrophy ◽  
Cardiac Arrhythmias ◽  
Ventricular Arrhythmias ◽  
Cardiac Involvement ◽  
Electrocardiographic Monitoring ◽  
Life Threatening ◽  
Electrocardiogram Ecg ◽  
Surface Electrocardiogram ◽  
Implanted Device

Introduction: Cardiac involvement in patients with muscular dystrophy associated with Lamin A/C mutations (LMNA) is characterized by atrioventricular conduction abnormalities and life-threatening cardiac arrhythmias. Little is known about cardiac involvement in patients with emerin mutation (EMD). The aim of our study was to describe and compare the prevalence and time distribution of cardiac arrhythmias at extended follow-up. Patients and methods: 45 consecutive patients affected by muscular dystrophy associated to laminopathy or emerinopathy were examined. All patients underwent clinical evaluation, 12-lead surface electrocardiogram (ECG), 24 h electrocardiographic monitoring, and cardiac implanted device interrogation. Results: At the end of 11 (5.0–16.6) years of follow-up, 89% of the patients showed cardiac arrhythmias. The most prevalent was atrial standstill (AS) (31%), followed by atrial fibrillation/flutter (AF/Afl) (29%) and ventricular tachycardia (22%). EMD patients presented more frequently AF/AFl compared to LMNA (50% vs. 20%, p = 0.06). Half of the EMD patients presented with AS, whilst there was no occurrence of such in the LMNA (p = 0.001). Ventricular arrhythmias were found in 60% of patients with laminopathy compared to 3% in patients with emerinopathy (p < 0.001). The age of AVB occurrence was higher in the LMNA group (32.8 +/− 10.6 vs. 25.1 +/− 9.1, p = 0.03). Conclusions: Atrial arrhythmias are common findings in patients with muscular dystrophy associated with EMD/LMNA mutations; however, they occurred earlier in EMD patients. Ventricular arrhythmias were very common (60%) in LMNA and occurred definitely earlier compared to the EMD group.

scholarly journals Development of Graphical User Interface to Classify Cardiac Abnormalities using ECG Signal

2019 ◽  
Vol 10 (3) ◽  
pp. 1621-1625
Author(s):  
Sharanya S ◽  
Sridhar PA ◽  
Suresh MP ◽  
Poorana Mary Monisha W ◽  
Tharadevi R
Keyword(s):  
User Interface ◽  
Graphical User Interface ◽  
Signal Analysis ◽  
Cardiac Activity ◽  
Noise Removal ◽  
Ecg Signal ◽  
Online Database ◽  
Ecg Signals ◽  
Classification Technique ◽  
Electrocardiogram Ecg

Analysis of Electrocardiogram (ECG) signal can lead to better detection of cardiac arrhythmia. The important steps involved in the ECG signal analysis include acquisition of data, pre-processing of signal to remove artefacts, feature extraction of attributes and finally identifying abnormalities. This work proposes an efficient implementation of the R-R interval-based ECG classification technique for detecting abnormalities in heart functioning. ECG signals from an online database (PhysioNet.org) was analysed after noise removal for R-R interval, as R peak has the maximum prominent amplitude in ECG wave. Deviation in the R-R interval values obtained from unhealthy was observed and compared with healthy subjects. This observation of cardiac activity can be visualised in our developed Graphical User Interface (GUI). The GUI platform requires only the input of the ECG signal that is to be analysed for abnormalities, which can provide the clinician with the result of cardiac abnormality classification and can help in diagnosis.  

scholarly journals ECG signal diagnoses using intelligent systems

2018 ◽  
Vol 7 (4) ◽  
pp. 2733
Author(s):  
Raaed Faleh Hassan ◽  
Sally Abdulmunem Shaker
Keyword(s):  
Cardiac Arrhythmias ◽  
Intelligent Systems ◽  
Fuzzy Inference ◽  
Accurate Diagnosis ◽  
Ecg Signal ◽  
Backpropagation Neural Network ◽  
Inference System ◽  
Ecg Signals ◽  
Heart Patients ◽  
Electrocardiogram Ecg

Accurate diagnosis of arrhythmias plays a crucial role in saving the lives of many heart patients. The aim of this research is to find the more efficient method to diagnosis electrocardiogram (ECG) diseases. This work presents the use of Backpropagation neural network (BPNN) and fuzzy logic for automatic detection of cardiac arrhythmias based on analysis of the ECG. These a more valuable tool used to classify ECG signals in cardiac patients. Data collected from physioBank ATM. The analysis of the ECG signal is performed in MATLAB environment. In BPNN the results appear that the only two misclassifications happened to result in an accuracy of 90.4%. while in fuzzy inference system the results appear that the classification accuracy is 100%.   

scholarly journals Computational Diagnostic Techniques for Electrocardiogram Signal Analysis

Sensors ◽  
2020 ◽  
Vol 20 (21) ◽  
pp. 6318
Author(s):  
Liping Xie ◽  
Zilong Li ◽  
Yihan Zhou ◽  
Yiliu He ◽  
Jiaxin Zhu
Keyword(s):  
Health Care Professionals ◽  
Signal Analysis ◽  
Cardiovascular Death ◽  
Diagnostic Techniques ◽  
Portable Devices ◽  
Ecg Signal ◽  
Great Success ◽  
Ecg Signals ◽  
Electrical Impulses ◽  
Electrocardiogram Ecg

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.

Efficient RPM Method for Detecting R and S Waves of ECG Signals

2013 ◽  
Vol 284-287 ◽  
pp. 1584-1588
Author(s):  
Yun Chi Yeh ◽  
Che Wun Chiou ◽  
Hong Jhih Lin
Keyword(s):  
Relative Position ◽  
Execution Time ◽  
Detection Rate ◽  
Detection Method ◽  
Finite Impulse Response ◽  
Ecg Signal ◽  
S Waves ◽  
Ecg Signals ◽  
Efficient Detection ◽  
Electrocardiogram Ecg

This study proposes a simple and effective method, termed Relative Position Mapping (RPM) method, to detect the Q and S waves of an electrocardiogram (ECG) signal. This detection method employs the Finite-Impulse-Response (FIR) filter. The proposed RPM method consists of four procedures, (1) ECG signals under test are filtered by FIR and then their difference signal is obtained, (2) based on such difference signal, the search intervals for both Q and S waves are found, (3) the search intervals of both Q and S waves are mapped back to the original ECG signals under test, and (4) based on the R wave, both Q and S waves are detected. This study is examined by using 48 records from MIT-BIH arrhythmia database, each record is a 30-min ML-II ECG signals. Experimental results show that the average failed detection rate of the proposed RPM method is approximately 0.82% and their execution time is less than 1 minute for each 30-min record. The proposed RPM method is a simple and efficient detection method for detecting both R and S waves of ECG signals.

scholarly journals Less computational approach to detect QRS complexes in ECG rhythms

2020 ◽  
Vol 2 (3) ◽  
pp. 113-120
Author(s):  
Tariq M. Younes ◽  
Mohammad Alkhedher ◽  
Mohamad Al Khawaldeh ◽  
Jalal Nawash ◽  
Ibrahim Al-Abbas
Keyword(s):  
Signal Analysis ◽  
Adaptive Threshold ◽  
Computational Approach ◽  
Threshold Function ◽  
Heart Rate Monitoring ◽  
Ecg Signals ◽  
Filter Structure ◽  
Reference Signals ◽  
Low Pass ◽  
Electrocardiogram Ecg

Electrocardiogram (ECG) signals are normally affected by artifacts that require manual assessment or use of other reference signals. Currently, Cardiographs are used to achieve basic necessary heart rate monitoring in real conditions. This work aims to study and identify main ECG features, QRS complexes, as one of the steps of a comprehensive ECG signal analysis. The proposed algorithm suggested an automatic recognition of QRS complexes in ECG rhythm. This method is designed based on several filter structure composes low pass, difference and summation filters. The filtered signal is fed to an adaptive threshold function to detect QRS complexes. The algorithm was validated and results were checked with experimental data based on sensitivity test.

scholarly journals Deep Neural Networks Learn by Using Human-Selected ECG Features and Novel Features

2021 ◽  
Author(s):  
Zachi I Attia ◽  
Gilad Lerman ◽  
Paul A Friedman
Keyword(s):  
Neural Networks ◽  
Signal Analysis ◽  
Deep Neural Networks ◽  
Linear Models ◽  
Nonlinear Models ◽  
Superior Performance ◽  
Ecg Signals ◽  
Shared Information ◽  
Human Feature ◽  
Electrocardiogram Ecg

Abstract Aims We sought to investigate whether artificial intelligence (AI) and specifically deep neural networks for electrocardiogram (ECG) signal analysis can be explained using human selected features. We also sought to quantify such explainability and test if the AI model learns features that are similar to a human expert. Methods We used a set of 100,000 ECGs that were annotated by human explainable features. We applied both linear and nonlinear models to predict published ECG AI models output for the detection of patients' age and sex. We further used canonical correlation analysis to quantify the amount of shared information between the features found in an unsupervised way. We reconstructed single human-selected ECG features from the unexplained neural network features using a simple linear model. Results We noticed a strong correlation between the simple models and the AI output (R2 of 0.49-0.57 for the linear models and R2 of 0.69-0.70 for the nonlinear models). We found that the correlation of the human explainable features with either 13 of the strongest age AI features or 15 of the strongest sex AI features was above 0.85 (for comparison, the first 14 principal components explain 90% of the human feature variance). We linearly reconstructed single human-selected ECG features from the AI features with R2 up to 0.86. Conclusion This work shows that neural networks for ECG signals extract features in a similar manner to human experts and that they also generate additional novel features that help achieve superior performance.

scholarly journals Real-Time Concept Drift Detection and Its Application to ECG Data

2021 ◽  
Vol 17 (10) ◽  
pp. 160
Author(s):  
Ketan Sanjay Desale ◽  
Swati Shinde
Keyword(s):  
Real Time ◽  
Data Streams ◽  
Detection Method ◽  
Concept Drift ◽  
Model Performance ◽  
Adaptive Mechanism ◽  
Ecg Signals ◽  
Electrocardiogram Signals ◽  
Concept Drift Detection ◽  
Electrocardiogram Ecg

Prediction of cardiac disease is one the most crucial topics in the sector of medical info evaluation. The stochastic nature and the variation concerning time in electrocardiogram (ECG) signals make it burdensome to investigate its characteristics. Being evolving in nature, it requires a dynamic predictive model. With the presence of concept drift, the model performance will get worse. Thus learning algorithms require an apt adaptive mechanism to accurately handle the drifting data streams. This paper proposes an inceptive approach, Corazon Concept Drift Detection Method (Corazon CDDM), to detect drifts and adapt to them in real-time in electrocardiogram signals. The proposed methodology results in achieving competitive results compared to the methods proposed in the literature for all types of datasets like synthetic, real-world &amp; time-series datasets.

Sign in / Sign up

Export Citation Format

Share Document