Densely connected convolutional networks for detection of atrial fibrillation from short single-lead ECG recordings

Rubin, Jonathan; Parvaneh, Saman; Rahman, Asif; Conroy, Bryan; Babaeizadeh, Saeed

doi:10.1016/j.jelectrocard.2018.08.008

Cited by 80 publications

(45 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cross-validation has been widely used to test and evaluate the generalisation of CNN models [25,28,35]. In previous work, the generalisation of classifiers was evaluated using the same data source.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of convolutional neural network for recognizing uterine contractions with electrohysterogram

Hao

Jin

Wang

et al. 2019

Computers in Biology and Medicine

View full text Add to dashboard Cite

Uterine contraction (UC) activity is commonly used to monitor the approach of labour and delivery. Electrohysterograms (EHGs) have recently been used to monitor UC and distinguish between efficient and inefficient contractions. In this study, we aimed to identify UC in EHG signals using a convolutional neural network (CNN). An open-access database (Icelandic 16-electrode EHG database from 45 pregnant women with 122 recordings, DB1) was used to develop a CNN model, and 14000 segments with a length of 45 s (7000 from UCs and 7000 from non-UCs, which were determined with reference to the simultaneously recorded tocography signals) were manually extracted from the 122 EHG recordings. Five-fold cross-validation was applied to evaluate the ability of the CNN to identify UC based on its sensitivity (SE), specificity (SP), accuracy (ACC), and area under the receiver operating characteristic curve (AUC). The CNN model developed using DB1 was then applied to an independent clinical database (DB2) to further test its generalisation for recognizing UCs. The EHG signals in DB2 were recorded from 20 pregnant women using our multi-channel system, and 308 segments (154 from UCs and 154 from non-UCs) were extracted. The CNN model from five-fold cross-validation achieved average SE, SP, ACC, and AUC of 0.87, 0.98, 0.93, and 0.92 for DB1, and 0.88, 0.97, 0.93, and 0.87 for DB2, respectively. In summary, we demonstrated that CNN could effectively identify UCs using EHG signals and could be used as a tool for monitoring maternal and foetal health.

show abstract

Section: Discussionmentioning

confidence: 99%

“…In future studies, the effect of UC duration on the CNN classification results will be investigated [34,35], and the performance of 1-D and 2-D CNNs will be compared for this specific clinical application. More EHG signals will be recorded to improve the recognition ability of the CNNs.…”

Section: Discussionmentioning

confidence: 99%

Evaluation of convolutional neural network for recognizing uterine contractions with electrohysterogram

Hao

Jin

Wang

et al. 2019

Computers in Biology and Medicine

View full text Add to dashboard Cite

show abstract

“…P-wave, QRS, and Twave onset and offset) and then will perform feature extraction using extracted annotations for traditional machine leaning. [9,17,18]. The combination of CNNs and long short-term memory (LSTM) networks was used for cardiac arrhythmia detection in another study [19].…”

Section: Deep Learning For Automated Ecg Interpretationmentioning

confidence: 99%

Electrocardiogram Monitoring and Interpretation: From Traditional Machine Learning to Deep Learning, and Their Combination

Parvaneh¹,

Rubin²

2018

Computing in Cardiology Conference (CinC)

Self Cite

View full text Add to dashboard Cite

Cardiac arrhythmia can lead to morbidity and mortality and is a substantial economic burden. Electrocardiogram (ECG) monitoring is widely used to detect arrhythmia. The number of ECG recordings is increasing due to aging populations and availability of easy-to-use wearable devices. Manual interpretation of the high volume of recorded ECGs might not be a feasible and scalable solution. Therefore, machine learning algorithms are widely used for automatic ECG interpretation. In this paper, the challenges and differences between machine learning techniques for ECG monitoring and interpretation are reviewed, from traditional machine learning classifiers to deep learning and their combination.

show abstract

“…Wang et al [ 18 ] developed a novel approach of an 11-layer neural network and the modified Elman neural network (MENN) for the automated AF detection, and the proposed model achieved exceptional results with the accuracy, sensitivity, and specificity of 97.4%, 97.9%, and 97.1%, respectively. Jonathan et al [ 19 ] combined a signal quality index (SQI) algorithm and CNN to detect AF, the results achieved on the test dataset were an overall F1 score of 0.82. In the above research, the researchers did not better solve the long-term dependence between ECG data under the premise of ensuring accurate feature extraction, and did not pay attention to the time of processing and transmitting data.…”

Section: Introductionmentioning

confidence: 99%

Automatic Detection of Atrial Fibrillation Based on CNN-LSTM and Shortcut Connection

et al. 2020

View full text Add to dashboard Cite

Atrial fibrillation (AF) is one of the most common persistent arrhythmias, which has a close connection to a large number of cardiovascular diseases. However, if spotted early, the diagnosis of AF can improve the effectiveness of clinical treatment and effectively prevent serious complications. In this paper, a combination of an 8-layer convolutional neural network (CNN) with a shortcut connection and 1-layer long short-term memory (LSTM), named 8CSL, was proposed for the Electrocardiogram (ECG) classification task. Compared with recurrent neural networks (RNN) and multi-scale convolution neural networks (MCNN), not only can 8CSL extract features skillfully, but also deal with long-term dependency between data. In particular, 8CSL includes eight shortcut connections that can improve the speed of the data transmission and processing as a result of the shortcut connections. The model was evaluated on the base of the test set of the Computing in Cardiology Challenge 2017 dataset with the F1 score. The ECG recordings were cropped or padded to the same length. After 10-fold cross-validation, the average test F1 score was 84.89%, 89.55%, and 85.64% when the segment length was 5, 10, 20 s, respectively. The experiment results demonstrate excellent performance with potential practical applications.

show abstract

Densely connected convolutional networks for detection of atrial fibrillation from short single-lead ECG recordings

Cited by 80 publications

References 2 publications

Evaluation of convolutional neural network for recognizing uterine contractions with electrohysterogram

Evaluation of convolutional neural network for recognizing uterine contractions with electrohysterogram

Electrocardiogram Monitoring and Interpretation: From Traditional Machine Learning to Deep Learning, and Their Combination

Automatic Detection of Atrial Fibrillation Based on CNN-LSTM and Shortcut Connection

Contact Info

Product

Resources

About