Early Detection of Atrial Fibrillation Based on ECG Signals

Ahmed, Nuzhat; Zhu, Yong

doi:10.3390/bioengineering7010016

Cited by 30 publications

(12 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, SI m which can be considered as G 0 , the rectified linear unit (ReLU) is usually chosen as the activation function. Since the features extracted by the CNN follow a time series, the temporal information embedded in the ECG signal is preserved and will be used as input to the GRU layer [ 11 ]. It is known that stochastic gradient descent (SGD) can help improve the convergence of neural network-based algorithms and make the loss function as small as possible, so the SGD method is utilized in the proposed CNN-GRU-based algorithm.…”

Section: Methodsmentioning

confidence: 99%

“…Accuracy: The classification accuracy of the model test set can directly reflect the classification performance ACC = (TP + TN)/(TP + FN + FP + TN) (11) Jaccard similarity: It is a measure of distance between the prediction and the ground truth, i.e.,…”

Section: Cnn-gru Layermentioning

confidence: 99%

“…Although traditional arrhythmia classification methods use various classifiers to achieve certain results in some test datasets [ 11 , 12 ], they have a disadvantage in processing capabilities or are less researched on complex types, such as time series, multi-label and multi-instance data, etc. Traditional classification methods require pre-knowledge requirements for data waveforms and a large number of operations such as data preprocessing [ 13 ] and feature extraction, which hinder large-scale learning and training, and are not conducive to actual clinical applications [ 14 ].…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Multi-Label Attribute Selection of Arrhythmia for Electrocardiogram Signals with Fusion Learning

Yang

Lan

et al. 2022

Bioengineering

View full text Add to dashboard Cite

There are three primary challenges in the automatic diagnosis of arrhythmias by electrocardiogram (ECG): the significant variation among individual patients, the multiple pathologies in the ECG signal and the high cost in annotating clinical ECG with the corresponding labels. Traditional ECG processing approaches rely heavily on prior knowledge, such as those from feature extraction and waveform analysis. The preprocessing for prior knowledge incurs computational overhead. Furthermore, standard deep learning methods do not fully consider the dynamic temporal, spatial and multi-labeling characteristics of ECG data. In clinical ECG waveforms, it is common to see multi-labeling in which a patient is labeled with multiple classes of arrhythmias. However, multiclass approaches in current research mainly solve the multi-label machine learning problem, ignoring the correlation between diseases, resulting in information loss. In this paper, an arrhythmia detection and classification scheme called multi-label fusion deep learning is proposed. The objective is to build a unified system with automatic feature learning which supports effective multi-label classification. First, a multi-label ECG-based feature selection method is combined with a matrix decomposition and sparse learning theory. The optimal feature subset is selected as a preprocessing algorithm for ECG data. A multi-label classifier is then constructed by fusing CNN and RNN networks to fully exploit the interactions and features of the time and space dimensions. The experimental result demonstrates that the proposed method can achieve a state-of-the-art performance compared to other algorithms in multi-label database experiments.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Cnn-gru Layermentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Label Attribute Selection of Arrhythmia for Electrocardiogram Signals with Fusion Learning

Yang

Lan

et al. 2022

Bioengineering

View full text Add to dashboard Cite

show abstract

“…As a common type, atrial fibrillation (AF) occurs when the atria fail to contract properly, thereby increasing the risk of stroke, hospitalization, heart failure, and death [ 2 , 3 , 4 , 5 ]. Thus, an accurate and effective detection of arrhythmias, including AF, is essential for the early diagnosis of cardiovascular diseases and their clinical treatments to prevent serious complications [ 6 , 7 , 8 ].…”

Section: Introductionmentioning

confidence: 99%

Learning Explainable Time-Morphology Patterns for Automatic Arrhythmia Classification from Short Single-Lead ECGs

Lee

Shin

2021

Sensors

View full text Add to dashboard Cite

Automatic detection of abnormal heart rhythms, including atrial fibrillation (AF), using signals obtained from a single-lead wearable electrocardiogram (ECG) device, is useful for daily cardiac health monitoring. In this study, we propose a novel image-based deep learning framework to classify single-lead ECG recordings of short variable length into several different rhythms associated with arrhythmias. By transforming variable-length 1D ECG signals into fixed-size 2D time-morphology representations and feeding them to the beat–interval–texture convolutional neural network (BIT-CNN) model, we aimed to learn the comprehensible characteristics of beat shape and inter-beat patterns over time for arrhythmia classification. The proposed approach allows feature embedding vectors to provide interpretable time-morphology patterns focused at each step of the learning process. In addition, this method reduces the number of model parameters needed to be trained and aids visual interpretation, while maintaining similar performance to other CNN-based approaches to arrhythmia classification. For experiments, we used the PhysioNet/CinC Challenge 2017 dataset and achieved an overall F1_NAO of 81.75% and F1_NAOP of 76.87%, which are comparable to those of the state-of-the-art methods for variable-length ECGs.

show abstract

“…As widely showed in the literature concerning heart rate variability [ 1 , 2 , 3 , 4 ], computerized signal processing techniques proved to be an effective way to detect different types of cardiovascular disorders. Indeed, the processing and computerized analysis of heart rate signals, with particular regard to the heart rate variability (HRV), contributed to enhance the diagnostic value brought by the clinical diagnostic techniques, by providing additional information and data that can support the clinical decision-making and leading to standardized, reliable, and early diagnoses [ 5 , 6 , 7 , 8 , 9 , 10 , 11 , 12 , 13 ].…”

Section: Introductionmentioning

confidence: 99%

Multiparametric Investigation of Dynamics in Fetal Heart Rate Signals

2021

View full text Add to dashboard Cite

In the field of electronic fetal health monitoring, computerized analysis of fetal heart rate (FHR) signals has emerged as a valid decision-support tool in the assessment of fetal wellbeing. Despite the availability of several approaches to analyze the variability of FHR signals (namely the FHRV), there are still shadows hindering a comprehensive understanding of how linear and nonlinear dynamics are involved in the control of the fetal heart rhythm. In this study, we propose a straightforward processing and modeling route for a deeper understanding of the relationships between the characteristics of the FHR signal. A multiparametric modeling and investigation of the factors influencing the FHR accelerations, chosen as major indicator of fetal wellbeing, is carried out by means of linear and nonlinear techniques, blockwise dimension reduction, and artificial neural networks. The obtained results show that linear features are more influential compared to nonlinear ones in the modeling of HRV in healthy fetuses. In addition, the results suggest that the investigation of nonlinear dynamics and the use of predictive tools in the field of FHRV should be undertaken carefully and limited to defined pregnancy periods and FHR mean values to provide interpretable and reliable information to clinicians and researchers.

show abstract

Early Detection of Atrial Fibrillation Based on ECG Signals

Cited by 30 publications

References 18 publications

Multi-Label Attribute Selection of Arrhythmia for Electrocardiogram Signals with Fusion Learning

Multi-Label Attribute Selection of Arrhythmia for Electrocardiogram Signals with Fusion Learning

Learning Explainable Time-Morphology Patterns for Automatic Arrhythmia Classification from Short Single-Lead ECGs

Multiparametric Investigation of Dynamics in Fetal Heart Rate Signals

Contact Info

Product

Resources

About