Detection and Classification of Cardiac Arrhythmias by a Challenge-Best Deep Learning Neural Network Model

Chen, Tsai-Min; Huang, Chih-Han; Shih, Edward S.C.; Hu, Yu‐Feng; Hwang, Ming‐Jing

doi:10.1016/j.isci.2020.100886

Cited by 140 publications

(73 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Being tested on the CPSC 2020 dataset, the proposed model shows F1 scores significantly higher than those of the Challenge-best model (13) for all seven types of cardiac arrhythmias (Figure 8). The computed ROC curve and AUC (shown in Supplementary Figure 5) also demonstrate the better performance of the proposed model (with an averaged AUC of 0.951) than the challenge-best model (13). It is interesting to note that the Challenge-best model is much harder to converge on the CPCS 2020 than those of CPSC 2018.…”

Section: Robustness Testingmentioning

confidence: 96%

Automatic Detection for Multi-Labeled Cardiac Arrhythmia Based on Frame Blocking Preprocessing and Residual Networks

Zhang

2021

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

Introduction: Electrocardiograms (ECG) provide information about the electrical activity of the heart, which is useful for diagnosing abnormal cardiac functions such as arrhythmias. Recently, several algorithms based on advanced structures of neural networks have been proposed for auto-detecting cardiac arrhythmias, but their performance still needs to be further improved. This study aimed to develop an auto-detection algorithm, which extracts valid features from 12-lead ECG for classifying multiple types of cardiac states.Method: The proposed algorithm consists of the following components: (i) a preprocessing component that utilizes the frame blocking method to split an ECG recording into frames with a uniform length for all considered ECG recordings; and (ii) a binary classifier based on ResNet, which is combined with the attention-based bidirectional long-short term memory model.Result: The developed algorithm was trained and tested on ECG data of nine types of cardiac states, fulfilling a task of multi-label classification. It achieved an averaged F1-score and area under the curve at 0.908 and 0.974, respectively.Conclusion: The frame blocking and bidirectional long-short term memory model represented an improved algorithm compared with others in the literature for auto-detecting and classifying multi-types of cardiac abnormalities.

show abstract

Section: Robustness Testingmentioning

confidence: 96%

Automatic Detection for Multi-Labeled Cardiac Arrhythmia Based on Frame Blocking Preprocessing and Residual Networks

Zhang

2021

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

show abstract

“…The model used in this study is a modified CRNN from [11] with 24 convolutional filters per layer to account for the extra number of target classes. The convolutions are 1D, treating the 12 leads as channels and the activation function is the LeakyReLU.…”

Section: Convolutional Recurrent Neural Networkmentioning

confidence: 99%

Convolutional Recurrent Neural Network and LightGBM Ensemble Model for 12-lead ECG Classification

Zisou¹,

Sochopoulos²,

Kitsios³

2020

Computing in Cardiology Conference (CinC)

View full text Add to dashboard Cite

Automatic abnormality detection of ECG signals is a challenging topic of great research and commercial interest. It can provide a cost-effective and accessible tool for early and accurate diagnosis, which increases the chances of successful treatment. In this study, an ensemble classifier that identifies 24 types of cardiac abnormalities is proposed, as part of the PhysioNet/Computing in Cardiology Challenge 2020. The ensemble model consists of a convolutional recurrent neural network that is able to automatically learn deep features, and LightGBM, a gradient boosting machine that relies on hand-engineered expert features. The individual models are combined using class-specific weights and thresholds, which are tuned by a genetic algorithm. Results from 5-fold cross validation on the full training set, report the Challenge metric of 0.593 that outperforms both individual models. On the full hidden test set, the proposed architecture by "AUTh Team" achieves a score of 0.281 with an official ranking of 13/41.

show abstract

“…The deep convolutional neural network (DNN) was based on the 2018 China Physiological Signal Challenge (CSPC) winners' model [6]. This model consists of 5 1Dconvolutional blocks (see Table 3).…”

Section: Deep Convolutional Streammentioning

confidence: 99%

Multi-Stream Deep Neural Network for 12-Lead ECG Classification

Baumgärtner

Eggerth

Ziegl

et al. 2020

2020 Computing in Cardiology Conference (CinC)

View full text Add to dashboard Cite

Advances in artificial intelligence and computer science have allowed for powerful assistive tools in a wide range of fields. Decision support systems could help health professionals to provide patients with quick and cost-efficient diagnostic analysis. The 2020 CinC Challenge challenges participants to develop such a tool for 12-lead ECG recordings. In this paper, an approach for a multi-stream neural network is presented. Two parallel models were trained with different input data to combine the two relevant paradigms in modern machine learning. A simple multilayer perceptron and a deep convolutional neural network were concatenated for the final classification. Since the data originated from different sources, an ensemble of models was trained. Due to technical difficulties, we (easyG) submitted a trimmed version and achieved a test score of-0.290, which ranked as the 39 th entry. Validation score was 0.403. Although these results were mixed, offline 5-fold cross validation showed the potency of the full version. Our results indicate that deep learning methods could in fact benefit from the addition of features derived via classical signal processing.

show abstract

Detection and Classification of Cardiac Arrhythmias by a Challenge-Best Deep Learning Neural Network Model

Abstract: Accurate AI diagnosis of cardiac arrhythmia on ECG data from 11 hospitals Capable of diagnosing concurrent cardiac arrhythmiasAn ensemble model combining 12-and 1-lead models ranked first in CPSC2018 aVR and V1 found to be the best-performing single leads

Cited by 140 publications

References 30 publications

Automatic Detection for Multi-Labeled Cardiac Arrhythmia Based on Frame Blocking Preprocessing and Residual Networks

Automatic Detection for Multi-Labeled Cardiac Arrhythmia Based on Frame Blocking Preprocessing and Residual Networks

Convolutional Recurrent Neural Network and LightGBM Ensemble Model for 12-lead ECG Classification

Multi-Stream Deep Neural Network for 12-Lead ECG Classification

Contact Info

Product

Resources

About