Arrhythmia Classification via Time and Frequency Domain Analyses of Ventricular and Atrial Contractions

Jekova, Irena; Stoyanov, Todor; Dotsinsky, Ivan

doi:10.22489/cinc.2017.345-029

Cited by 7 publications

(3 citation statements)

References 14 publications

(21 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Definitions of the features are disclosed in Table 2 . More details can be found in the cited references, as well as in the free Matlab code for their computation distributed along the PhysioNet CinC Challenge 2017 competitors [ 52 , 53 ] and available at: [ ] and [ ], accessed on 1 September 2021.…”

Section: Methodsmentioning

confidence: 99%

Application of Dense Neural Networks for Detection of Atrial Fibrillation and Ranking of Augmented ECG Feature Set

Krasteva

Christov

Naydenov

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

Considering the significant burden to patients and healthcare systems globally related to atrial fibrillation (AF) complications, the early AF diagnosis is of crucial importance. In the view of prominent perspectives for fast and accurate point-of-care arrhythmia detection, our study optimizes an artificial neural network (NN) classifier and ranks the importance of enhanced 137 diagnostic ECG features computed from time and frequency ECG signal representations of short single-lead strips available in 2017 Physionet/CinC Challenge database. Based on hyperparameters’ grid search of densely connected NN layers, we derive the optimal topology with three layers and 128, 32, 4 neurons per layer (DenseNet-3@128-32-4), which presents maximal F1-scores for classification of Normal rhythms (0.883, 5076 strips), AF (0.825, 758 strips), Other rhythms (0.705, 2415 strips), Noise (0.618, 279 strips) and total F1 relevant to the CinC Challenge of 0.804, derived by five-fold cross-validation. DenseNet-3@128-32-4 performs equally well with 137 to 32 features and presents tolerable reduction by about 0.03 to 0.06 points for limited input sets, including 8 and 16 features, respectively. The feature reduction is linked to effective application of a comprehensive method for computation of the feature map importance based on the weights of the activated neurons through the total path from input to specific output in DenseNet. The detailed analysis of 20 top-ranked ECG features with greatest importance to the detection of each rhythm and overall of all rhythms reveals DenseNet decision-making process, noticeably corresponding to the cardiologists’ diagnostic point of view.

show abstract

Section: Methodsmentioning

confidence: 99%

Application of Dense Neural Networks for Detection of Atrial Fibrillation and Ranking of Augmented ECG Feature Set

Krasteva

Christov

Naydenov

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…ECG signal examinations for AF localization are conducted in the time or recurrence area. The current AF recurrence is commonly assessed over a sign with deleted QRS complex and T peak edifice [7,8]. This study aims to provide a characterization model and evaluate its ability to separate brief single-lead ECG signals classified as AF, Normal (N), noisy, and Other Rhythms (O) using the 2017 PhysioNet/Computing in Cardiology Challenge database [9].…”

Section: Introductionmentioning

confidence: 99%

Automatic Detection of Atrial Fibrillation from ECG Signal Using Hybrid Deep Learning Techniques

Pandey

Kumar

Shukla³

et al. 2022

Journal of Sensors

View full text Add to dashboard Cite

In cardiac rhythm disorders, atrial fibrillation (AF) is among the most deadly. So, ECG signals play a crucial role in preventing CVD by promptly detecting atrial fibrillation in a patient. Unfortunately, locating trustworthy automatic AF in clinical settings remains difficult. Today, deep learning is a potent tool for complex data analysis since it requires little pre and postprocessing. As a result, several machine learning and deep learning approaches have recently been applied to ECG data to diagnose AF automatically. This study analyses electrocardiogram (ECG) data from the PhysioNet/Computing in Cardiology (CinC) Challenge 2017 to differentiate between atrial fibrillation (AF) and three other rhythms: normal, other, and too noisy for assessment. The ECG data, including AF rhythm, was classified using a novel model based on a combination of traditional machine learning techniques and deep neural networks. To categorize AF rhythms from ECG data, this hybrid model combined a convolutional neural network (Residual Network (ResNet)) with a Bidirectional Long Short Term Memory (BLSTM) network and a Radial Basis Function (RBF) neural network. Both the F1-score and the accuracy of the final hybrid model are relatively high, coming in at 0.80% and 0.85%, respectively.

show abstract

“…Furthermore, Holter ECG recordings are acquired during regular patient activity (sleep, movements, employment, sports) meaning that the ECG signal usually contains movement artifacts and power-grid noise and may also suffer from poor contact between the body and ECG electrodes (sweat, especially in connection with movements). The capability of these simple methods may suffer under the given circumstances which may also be deduced from results from the PhysioNet Challenge 2017 in which methods using only a few well-known features [7][8][9] showed rather limited performance.…”

Section: Introductionmentioning

confidence: 99%

Parallel use of a convolutional neural network and bagged tree ensemble for the classification of Holter ECG

et al. 2018

View full text Add to dashboard Cite

show abstract

Arrhythmia Classification via Time and Frequency Domain Analyses of Ventricular and Atrial Contractions

Abstract: =0.61(0.53), F1=0.68 (0.65) [0.64].

Cited by 7 publications

References 14 publications

Application of Dense Neural Networks for Detection of Atrial Fibrillation and Ranking of Augmented ECG Feature Set

Application of Dense Neural Networks for Detection of Atrial Fibrillation and Ranking of Augmented ECG Feature Set

Automatic Detection of Atrial Fibrillation from ECG Signal Using Hybrid Deep Learning Techniques

Parallel use of a convolutional neural network and bagged tree ensemble for the classification of Holter ECG

Contact Info

Product

Resources

About