scholarly journals Directed networks as a novel way to describe and analyze cardiac excitation: Directed Graph mapping

2019 ◽  
Author(s):  
Nele Vandersickel ◽  
Enid Van Nieuwenhuyse ◽  
Nico Van Cleemput ◽  
Jan Goedgebeur ◽  
Milad El Haddad ◽  
...  
Keyword(s):  
Cardiac Arrhythmias ◽  
Normal Sinus Rhythm ◽  
Social Systems ◽  
Daily Practice ◽  
Directed Network ◽  
Directed Networks ◽  
Normal Sinus ◽  
Graph Mapping ◽  
Brain Data ◽  
Cardiac Excitation

AbstractNetworks provide a powerful methodology with applications in a variety of biological, technological and social systems such as analysis of brain data, social networks, internet search engine algorithms, etc. To date, directed networks have not yet been applied to characterize the excitation of the human heart. In clinical practice, cardiac excitation is recorded by multiple discrete electrodes. During (normal) sinus rhythm or during cardiac arrhythmias, successive excitation connects neighboring electrodes, resulting in their own unique directed network. This in theory makes it a perfect fit for directed network analysis. In this study, we applied directed networks to the heart in order to describe and characterize cardiac arrhythmias. Proofof-principle was established using in-silico and clinical data. We demonstrated that tools used in network theory analysis allow to determine the mechanism and location of certain cardiac arrhythmias. We show that the robustness of this approach can potentially exceed the existing state-of-the art methodology used in clinics. Furthermore, implementation of these techniques in daily practice can improve accuracy and speed of cardiac arrhythmia analysis. It may also provide novel insights in arrhythmias that are still incompletely understood.

Some effects of breath holding and apneic underwater diving on cardiac rhythm in man

1962 ◽  
Vol 17 (3) ◽  
pp. 461-466 ◽  
Author(s):  
C. Robert Olsen ◽  
Darrell D. Fanestil ◽  
Per F. Scholander
Keyword(s):  
Cardiac Arrhythmias ◽  
Cardiac Rhythm ◽  
Sinus Tachycardia ◽  
Normal Sinus Rhythm ◽  
Sinus Bradycardia ◽  
Breath Holding ◽  
Sinus Arrest ◽  
Sinus Arrhythmia ◽  
Normal Sinus ◽  
Idioventricular Rhythm

Man's bradycardic response to simple breath holding was augmented by submersion in water of 27 C and was not prevented by muscular exercise. Cardiac arrhythmias occurred with 45 of 64 periods of apnea in 16 subjects and were more frequent during the dives than during breath holding. These arrhythmias, with the exception of atrial, nodal, and ventricular premature contractions, were inhibitory in type and included sinus bradycardia and arrhythmia, sinus arrest followed by either nodal escape or ventricular escape, A-V block, A-V nodal rhythm, and idioventricular rhythm. T waves frequently became tall and peaked during both breath holding and dives. Prompt return to normal sinus rhythm was the rule with the first breath after surfacing. Sinus tachycardia, sinus arrhythmia, and atrial, nodal, or ventricular premature contractions were seen during recovery. Submitted on October 9, 1961

scholarly journals Directed Networks as a Novel Way to Describe and Analyze Cardiac Excitation: Directed Graph Mapping

2019 ◽  
Vol 10 ◽  
Author(s):  
Nele Vandersickel ◽  
Enid Van Nieuwenhuyse ◽  
Nico Van Cleemput ◽  
Jan Goedgebeur ◽  
Milad El Haddad ◽  
...  
Keyword(s):  
Directed Graph ◽  
Directed Networks ◽  
Graph Mapping ◽  
Cardiac Excitation

Cardiac Arrhythmias Auto Detection in an Electrocardiogram Using Computer-Aided Diagnosis Algorithm

2014 ◽  
Vol 556-562 ◽  
pp. 2728-2731
Author(s):  
Ji Ae Park ◽  
Seok Min Hwang ◽  
Ji Won Baek ◽  
Yoon Nyun Kim ◽  
Jong Ha Lee
Keyword(s):  
Heart Disease ◽  
Cardiac Arrhythmias ◽  
Heart Diseases ◽  
Normal Sinus Rhythm ◽  
Great Accuracy ◽  
Normal Sinus ◽  
Computer Aided ◽  
Diagnosis Algorithm ◽  
Aided Diagnosis ◽  
Healthy Persons

Supraventricular tachycardia (SVT) is the most common arrhythmia and can be found in not only heart disease patients, but also healthy persons. However, the occurrence of SVT in heart disease patients implies that the potential of the heart diseases worsening, and it causes cardiac arrest when it evolves into ventricular tachycardia or the ventricular fibrillation. Therefore, the detection of SVT arrhythmia, as a first stage, has significant implications for the prevention of cardiac arrests. In this paper, we propose the automatic diagnosis system for cardiac arrhythmias detection with great accuracy. To validate the algorithm, SVT and normal sinus rhythm are classified by the proposed algorithm.

scholarly journals Meeting the unmet needs of clinicians from AI systems showcased for cardiology with deep-learning–based ECG analysis

2021 ◽  
Vol 118 (24) ◽  
pp. e2020620118
Author(s):  
Yonatan Elul ◽  
Aviv A. Rosenberg ◽  
Assaf Schuster ◽  
Alex M. Bronstein ◽  
Yael Yaniv
Keyword(s):  
Large Scale ◽  
Unmet Needs ◽  
Normal Sinus Rhythm ◽  
Statistical Significance ◽  
Daily Practice ◽  
Great Promise ◽  
Specific Patient ◽  
Ecg Analysis ◽  
Normal Sinus ◽  
Out Of Sample

Despite their great promise, artificial intelligence (AI) systems have yet to become ubiquitous in the daily practice of medicine largely due to several crucial unmet needs of healthcare practitioners. These include lack of explanations in clinically meaningful terms, handling the presence of unknown medical conditions, and transparency regarding the system’s limitations, both in terms of statistical performance as well as recognizing situations for which the system’s predictions are irrelevant. We articulate these unmet clinical needs as machine-learning (ML) problems and systematically address them with cutting-edge ML techniques. We focus on electrocardiogram (ECG) analysis as an example domain in which AI has great potential and tackle two challenging tasks: the detection of a heterogeneous mix of known and unknown arrhythmias from ECG and the identification of underlying cardio-pathology from segments annotated as normal sinus rhythm recorded in patients with an intermittent arrhythmia. We validate our methods by simulating a screening for arrhythmias in a large-scale population while adhering to statistical significance requirements. Specifically, our system 1) visualizes the relative importance of each part of an ECG segment for the final model decision; 2) upholds specified statistical constraints on its out-of-sample performance and provides uncertainty estimation for its predictions; 3) handles inputs containing unknown rhythm types; and 4) handles data from unseen patients while also flagging cases in which the model’s outputs are not usable for a specific patient. This work represents a significant step toward overcoming the limitations currently impeding the integration of AI into clinical practice in cardiology and medicine in general.

scholarly journals Hybrid Deep Learning based approach for ECG Heartbeat Arrhythmia Classification

2021 ◽  
Author(s):  
Parul Madan ◽  
Vijay Singh ◽  
Devesh Pratap Singh ◽  
Bhasker Pant
Keyword(s):  
Feature Extraction ◽  
Deep Learning ◽  
Sinus Rhythm ◽  
Cardiac Arrhythmias ◽  
Normal Sinus Rhythm ◽  
Noise Filtering ◽  
Ecg Signals ◽  
Risk Of Death ◽  
Normal Sinus ◽  
Proposed Model

Abstract Background: Myocardial infarction, or heart attack, is caused by a blockage of a coronary artery, which prevents blood and oxygen from accessing the heart properly. Arrhythmias are a form of CVD that refers to irregular variations in the normal heart rhythm, such as the heart beating too quickly or too slowly. Arrhythmias include Atrial Fibrillation(AF),Premature Ventricular Contraction(PVC), Ventricular Fibrillation(VF), and Tachycardia are just a few examples of arrhythmias. It aggravates if not detected and treated on time i.e., on-time /proper diagnosis of arrhythmias may minimize the risk of death. It is very labor-intensive to externally evaluate ECG signals, due to their small amplitude. Furthermore, the analysis of ECG signals is arbitrary and can differ between experts. As a consequence, a computer-aided diagnostic device that is more objective and reliable is needed. Methods: In the recent era, Machine Learning based approaches to detect arrhythmias has been established proficiently. In this view, we proposed a hybrid Deep Learning-based model to detect three types of arrhythmias on MIT-BIH arrhythmia databases. In particular, this paper makes two-fold contributions. First, we translated 1D ECG signals into 2D Scalogram images. When one-dimensional ECG signals are turned into two-dimensional ECG images, noise filtering and feature extraction are no longer necessary. This is notable since certain ECG beats are ignored by noise filtering and feature extraction. Then, based on experimental evidence, we suggest combining two models, 2D-CNN-LSTM, to detect three forms of arrhythmias: Cardiac Arrhythmias (ARR), Congestive Heart Failure (CHF), and Normal Sinus Rhythm (NSR). Results: The experimental findings indicate that the model attained 99\% accuracy for "normal sinus rhythm," 100\% accuracy for "cardiac arrhythmias," and 99\% accuracy for "congestive heart failures," with an overall classification accuracy of 98.6\%. The sensitivity and specificity were 98.33\% and 98.35\%, respectively. The proposed model, in particular, will aid doctors in correctly detecting arrhythmia during routine ECG screening. Conclusion: As compared to the other State-of-the-art methods our proposed model outperformed and will greatly minimise the amount of intervention required by doctors.

scholarly journals Detection of Arrhythmic Cardiac Signals from ECG Recordings Using the Entropy–Complexity Plane

Proceedings ◽  
2019 ◽  
Vol 46 (1) ◽  
pp. 8
Author(s):  
Pablo Martinez Coq ◽  
Walter Legnani ◽  
Ricardo Armentano
Keyword(s):  
Time Series ◽  
Sinus Rhythm ◽  
Shannon Entropy ◽  
Cardiac Arrhythmias ◽  
Normal Sinus Rhythm ◽  
The Other ◽  
Multivariate Statistical ◽  
Normal Sinus ◽  
Statistical Complexity

The aim of this work was to analyze in the Entropy–Complexity plane (HxC) time series coming from ECG, with the objective to discriminate recordings from two different groups of patients: normal sinus rhythm and cardiac arrhythmias. The HxC plane used in this study was constituted by Shannon’s Entropy as one of its axes, and the other was composed using statistical complexity. To compute the entropy, the probability distribution function (PDF) of the observed data was obtained using the methodology proposed by Bandt and Pompe (2002). The database used in the present study was the ECG recordings obtained from PhysioNet, 47 long-term signals of patients with diagnosed cardiac arrhythmias and 18 long-term signals from normal sinus rhythm patients were processed. Average values of statistical complexity and normalized Shannon entropy were calculated and analyzed in the HxC plane for each time series. The average values of complexity of ECG for patients with diagnosed arrhythmias were bigger than normal sinus rhythm group. On the other hand, the Shannon entropy average values for arrhythmias patients were lower than the normal sinus rhythm group. This characteristic made it possible to discriminate the position of both signals’ groups in the HxC plane. The results were analyzed through a multivariate statistical test hypothesis. The methodology proposed has a remarkable conceptual simplicity, and shows a promising efficiency in the detection of cardiovascular pathologies.

Sign in / Sign up

Export Citation Format

Share Document